diff --git a/reproducibility_journal.csv b/reproducibility_journal.csv index 371e5426..9f5232b8 100644 --- a/reproducibility_journal.csv +++ b/reproducibility_journal.csv @@ -1,78 +1,85 @@ -git_user,agent_name,benchmark,benchmark_version,date,study_id,avg_reward,std_err,n_err,n_completed,comment,os,python_version,playwright_version,agentlab_version,agentlab_git_hash,agentlab__local_modifications,browsergym_version,browsergym_git_hash,browsergym__local_modifications -recursix,GenericAgent-gpt-4o-mini-2024-07-18,miniwob_tiny_test,0.6.3,2024-09-19_21-07-34,,0.75,0.217,0,4/4,,Darwin (Darwin Kernel Version 23.6.0: Mon Jul 29 21:13:00 PDT 2024; root:xnu-10063.141.2~1/RELEASE_X86_64),3.12.2,1.39.0,0.2.1,c99bdf74c98f323cc6a646467ba5f21154b6fd18,,0.6.4,b73531271d2ce688c104eb4dfba2819583f1ba36, -recursix,GenericAgent-gpt-4o-mini-2024-07-18,miniwob_tiny_test,0.6.3,2024-09-19_21-28-58,,1.0,0.0,0,4/4,,Darwin (Darwin Kernel Version 23.6.0: Mon Jul 29 21:13:00 PDT 2024; root:xnu-10063.141.2~1/RELEASE_X86_64),3.12.2,1.39.0,0.2.1,c99bdf74c98f323cc6a646467ba5f21154b6fd18," M: reproducibility_journal.csv - M: src/agentlab/experiments/task_collections.py",0.6.4,b73531271d2ce688c104eb4dfba2819583f1ba36, -recursix,GenericAgent-gpt-4o-mini-2024-07-18,miniwob,0.6.3,2024-09-20_07-16-21,,0.546,0.02,0,625/625,,Darwin (Darwin Kernel Version 23.6.0: Mon Jul 29 21:13:00 PDT 2024; root:xnu-10063.141.2~1/RELEASE_X86_64),3.12.2,1.39.0,0.2.1,295f01005faf8f2c73a31be6a18cec19d563b54b,,0.6.4,b73531271d2ce688c104eb4dfba2819583f1ba36, -recursix,GenericAgent-gpt-4o-2024-05-13,miniwob,0.6.3,2024-09-20_22-09-43,,0.656,0.019,0,625/625,,Darwin (Darwin Kernel Version 23.6.0: Mon Jul 29 21:13:00 PDT 2024; root:xnu-10063.141.2~1/RELEASE_X86_64),3.12.2,1.39.0,0.2.1,f6216486d5faac2c8b3fb0a63e114e5a4bafde47,,0.6.4,8cef8fe34940ff490d0cc06b0c8f100180d09d43, -recursix,GenericAgent-gpt-4o-2024-05-13,miniwob,0.6.3,2024-09-21_12-04-39,,0.656,0.019,0,625/625,None,Darwin (Darwin Kernel Version 23.6.0: Mon Jul 29 21:13:00 PDT 2024; root:xnu-10063.141.2~1/RELEASE_X86_64),3.12.2,1.39.0,0.2.1,fe561b93c5f053e9f9625358862f542523b5e14a,,0.7.0,ed6d6992ef64bfb91aca7002d33cb6ed5ec031ef, -recursix,GenericAgent-gpt-4o-mini-2024-07-18,miniwob,0.6.3,2024-10-01_11-45-23,,0.539,0.02,0,625/625,None,Darwin (Darwin Kernel Version 23.6.0: Mon Jul 29 21:13:00 PDT 2024; root:xnu-10063.141.2~1/RELEASE_X86_64),3.12.2,1.39.0,0.2.1,fe27819a99b163fd9240ba3e144e010413bff24d,,0.7.1,b0ad675572e01cac0d7255100112de0828877148, -recursix,GenericAgent-gpt-4o-mini-2024-07-18,workarena.l1,0.3.2,2024-10-05_13-21-27,,0.23,0.023,0,330/330,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.6,1.39.0,0.2.1,aadf86b397cd36c581e1a61e491aec649ac5a140," M: main.py",0.7.0,2a0ab7e8e8795f8ca35fe4d4d67c6892d635dc12, -recursix,GenericAgent-gpt-4o-2024-05-13,workarena.l1,0.3.2,2024-10-05_15-45-42,,0.382,0.027,0,330/330,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.6,1.39.0,0.2.1,ab447e997af589bbd022de7a5189a7685ddfa6ef,,0.7.0,2a0ab7e8e8795f8ca35fe4d4d67c6892d635dc12, -recursix,GenericAgent-meta-llama_llama-3-70b-instruct,workarena.l1,0.3.2,2024-10-09_21-16-37,,0.176,0.021,0,330/330,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.6,1.39.0,0.2.1,c847dbd334184271b32b252409a1b6c1042d7442,,0.7.0,2a0ab7e8e8795f8ca35fe4d4d67c6892d635dc12, -recursix,GenericAgent-meta-llama_llama-3.1-70b-instruct,miniwob_tiny_test,0.7.0,2024-10-05_17-49-15,,1.0,0.0,0,4/4,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.6,1.39.0,0.2.1,a98fa24426a6ddde8443e8be44ed94cd9522e5ca,,0.7.0,2a0ab7e8e8795f8ca35fe4d4d67c6892d635dc12, -ThibaultLSDC,GenericAgent-gpt-4o-mini-2024-07-18,miniwob,0.8.1,2024-10-17_10-13-28,,0.557,0.02,0,625/625,None,Darwin (Darwin Kernel Version 23.6.0: Mon Jul 29 21:13:00 PDT 2024; root:xnu-10063.141.2~1/RELEASE_X86_64),3.12.7,1.39.0,0.2.2,7bba275c004f1f90dfd83eaaab963ab5066e2baf,,0.8.1,None, -ThibaultLSDC,GenericAgent-gpt-4o-mini-2024-07-18,miniwob,0.8.1,2024-10-17_10-50-53,,0.563,0.02,0,625/625,None,Darwin (Darwin Kernel Version 23.6.0: Mon Jul 29 21:13:00 PDT 2024; root:xnu-10063.141.2~1/RELEASE_X86_64),3.12.7,1.39.0,0.2.2,057b7d4a201cc1cd1ebd7bc884f6a91e104c479d,,0.8.1,None, -ThibaultLSDC,GenericAgent-gpt-4o-mini-2024-07-18,workarena.l1,0.4.1,2024-10-17_17-30-43,,0.258,0.024,0,330/330,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.2,7bba275c004f1f90dfd83eaaab963ab5066e2baf,,0.8.1,None, -ThibaultLSDC,GenericAgent-gpt-4o-mini-2024-07-18,workarena.l1,0.4.1,2024-10-17_18-30-28,,0.273,0.025,0,330/330,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.2,8b2b3f39a2bdb9efafad97791536a0b8cff4e708,,0.8.1,None, -ThibaultLSDC,GenericAgent-gpt-4o-mini-2024-07-18,miniwob_all,0.9.0,2024-10-20_01-54-16,2024-10-20_01-54-02,0.588,0.014,0,1250/1250,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.2,1770eba87fabfe1e32cdf6078d71032fe00db736,,0.9.0,None, -ThibaultLSDC,GenericAgent-gpt-4o-mini-2024-07-18,workarena_l1,0.4.1,2024-10-22_18-41-55,2024-10-22_15-24-53,0.215,0.023,1,330/330,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,a6c1f93c59fb7a838d06ca02ef6c62abe2ce278c,,0.9.0,None, -ThibaultLSDC,GenericAgent-gpt-4o-mini,workarena_l1,0.4.1,2024-10-23_12-17-24,2024-10-23_02-00-49,0.252,0.024,1,330/330,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,d364ce7d5f566889830cdc0ef58b320d2093694e,,0.9.0,None, -ThibaultLSDC,GenericAgent-gpt-4o,workarena_l1,0.4.1,2024-10-23_12-17-24,2024-10-23_02-00-49,0.488,0.028,1,330/330,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,d364ce7d5f566889830cdc0ef58b320d2093694e,,0.9.0,None, -ThibaultLSDC,GenericAgent-anthropic_claude-3.5-sonnet:beta,workarena_l1,0.4.1,2024-10-23_12-17-24,2024-10-23_02-00-49,0.579,0.027,2,330/330,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,d364ce7d5f566889830cdc0ef58b320d2093694e,,0.9.0,None, -ThibaultLSDC,GenericAgent-meta-llama_llama-3.1-70b-instruct,workarena_l1,0.4.1,2024-10-23_12-17-24,2024-10-23_02-00-49,0.309,0.025,2,330/330,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,d364ce7d5f566889830cdc0ef58b320d2093694e,,0.9.0,None, -ThibaultLSDC,GenericAgent-openai_o1-mini-2024-09-12,workarena_l1,0.4.1,2024-10-23_12-17-24,2024-10-23_02-00-49,0.527,0.027,2,330/330,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,d364ce7d5f566889830cdc0ef58b320d2093694e,,0.9.0,None, -ThibaultLSDC,GenericAgent-gpt-4o-mini,workarena_l1,0.4.1,2024-10-23_22-30-06,2024-10-23_14-17-40,0.27,0.024,1,330/330,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,4cd1e2d4189ddfbeb94129f7b0c9a00c3400ebac,,0.9.0,f25bdcd6b946fc4a79cdbee5fbcad53548af8724, -ThibaultLSDC,GenericAgent-gpt-4o,workarena_l1,0.4.1,2024-10-23_22-30-06,2024-10-23_14-17-40,0.455,0.027,1,330/330,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,4cd1e2d4189ddfbeb94129f7b0c9a00c3400ebac,,0.9.0,f25bdcd6b946fc4a79cdbee5fbcad53548af8724, -ThibaultLSDC,GenericAgent-anthropic_claude-3.5-sonnet:beta,workarena_l1,0.4.1,2024-10-23_22-30-06,2024-10-23_14-17-40,0.564,0.027,1,330/330,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,4cd1e2d4189ddfbeb94129f7b0c9a00c3400ebac,,0.9.0,f25bdcd6b946fc4a79cdbee5fbcad53548af8724, -ThibaultLSDC,GenericAgent-meta-llama_llama-3.1-70b-instruct,workarena_l1,0.4.1,2024-10-23_22-30-06,2024-10-23_14-17-40,0.279,0.025,0,330/330,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,4cd1e2d4189ddfbeb94129f7b0c9a00c3400ebac,,0.9.0,f25bdcd6b946fc4a79cdbee5fbcad53548af8724, -ThibaultLSDC,GenericAgent-openai_o1-mini-2024-09-12,workarena_l1,0.4.1,2024-10-23_22-30-06,2024-10-23_14-17-40,0.567,0.027,4,330/330,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,4cd1e2d4189ddfbeb94129f7b0c9a00c3400ebac,,0.9.0,f25bdcd6b946fc4a79cdbee5fbcad53548af8724, -recursix,GenericAgent-anthropic_claude-3.5-sonnet:beta,webarena,0.11.3,2024-11-02_23-50-17,22a9d3f5-9d86-455e-b451-3ea17690ce8a,0.329,0.016,0,812/812,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.6,1.39.0,0.2.3,418a05d90c74800cd66371b7846ef861185b8c47,,0.11.3,160167ff0d2631826f0131e8e30b92ef448d6881, -ThibaultLSDC,GenericAgent-gpt-4o-mini,workarena_l2_agent_curriculum_eval,0.4.1,2024-10-24_17-08-53,2024-10-23_17-10-46,0.013,0.007,2,235/235,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,827d847995f19dc337f3899427340bdddbd81cd5,,0.10.0,None, -ThibaultLSDC,GenericAgent-gpt-4o,workarena_l2_agent_curriculum_eval,0.4.1,2024-10-24_17-08-53,2024-10-23_17-10-46,0.085,0.018,3,233/235,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,827d847995f19dc337f3899427340bdddbd81cd5,,0.10.0,None, -ThibaultLSDC,GenericAgent-anthropic_claude-3.5-sonnet:beta,workarena_l2_agent_curriculum_eval,0.4.1,2024-10-24_17-08-53,2024-10-23_17-10-46,0.391,0.032,3,235/235,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,827d847995f19dc337f3899427340bdddbd81cd5,,0.10.0,None, -ThibaultLSDC,GenericAgent-meta-llama_llama-3.1-70b-instruct,workarena_l2_agent_curriculum_eval,0.4.1,2024-10-24_17-08-53,2024-10-23_17-10-46,0.021,0.009,2,235/235,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,827d847995f19dc337f3899427340bdddbd81cd5,,0.10.0,None, -ThibaultLSDC,GenericAgent-openai_o1-mini-2024-09-12,workarena_l2_agent_curriculum_eval,0.4.1,2024-10-24_17-08-53,2024-10-23_17-10-46,0.149,0.023,1,235/235,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,827d847995f19dc337f3899427340bdddbd81cd5,,0.10.0,None, -ThibaultLSDC,GenericAgent-anthropic_claude-3.5-sonnet:beta,workarena_l3_agent_curriculum_eval,0.4.1,2024-10-24_23-03-30,2024-10-24_18-06-57,0.004,0.004,1,235/235,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,de67ed8ad4321740ff05cf26ab889978be706460,,0.10.2,a9e44a88139798543ba53fc8c45d44997665ccca, -ThibaultLSDC,GenericAgent-gpt-4o-mini,miniwob,0.10.2,2024-10-25_17-16-23,2024-10-25_06-08-16,0.566,0.02,0,625/625,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,f12887f776525bcad6a0c42cb49651ff4f65af43,,0.10.2,a9e44a88139798543ba53fc8c45d44997665ccca, -ThibaultLSDC,GenericAgent-gpt-4o,miniwob,0.10.2,2024-10-25_17-16-23,2024-10-25_06-08-16,0.638,0.019,0,625/625,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,f12887f776525bcad6a0c42cb49651ff4f65af43,,0.10.2,a9e44a88139798543ba53fc8c45d44997665ccca, -ThibaultLSDC,GenericAgent-anthropic_claude-3.5-sonnet:beta,miniwob,0.10.2,2024-10-25_17-16-23,2024-10-25_06-08-16,0.698,0.018,0,625/625,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,f12887f776525bcad6a0c42cb49651ff4f65af43,,0.10.2,a9e44a88139798543ba53fc8c45d44997665ccca, -ThibaultLSDC,GenericAgent-meta-llama_llama-3.1-70b-instruct,miniwob,0.10.2,2024-10-25_17-16-23,2024-10-25_06-08-16,0.576,0.02,0,625/625,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,f12887f776525bcad6a0c42cb49651ff4f65af43,,0.10.2,a9e44a88139798543ba53fc8c45d44997665ccca, -ThibaultLSDC,GenericAgent-openai_o1-mini-2024-09-12,miniwob,0.10.2,2024-10-25_17-16-23,2024-10-25_06-08-16,0.678,0.019,0,625/625,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,f12887f776525bcad6a0c42cb49651ff4f65af43,,0.10.2,a9e44a88139798543ba53fc8c45d44997665ccca, -ThibaultLSDC,GenericAgent-meta-llama_llama-3.1-405b-instruct,workarena_l1,0.4.1,2024-10-25_20-32-26,2024-10-25_17-34-45,0.433,0.027,1,330/330,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,177ba72a7469e5610e6b615adf1bdcde58cb0298,,0.10.2,a9e44a88139798543ba53fc8c45d44997665ccca, -Maxime Gasse,GenericAgent-gpt-4o-2024-05-13,weblinx_test,0.0.1.dev13,2024-11-04_16-01-14,2024-11-04_15-59-12,0.123,0.006,0,2650/2650,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.0,1.39.0,0.2.3,6e18fb818a64ec1e3f379c1a6480411d2fd0628b,,0.11.3,3ab1843edb14bfce7d39485f0106d0dc0c2d7486, -ThibaultLSDC,GenericAgent-gpt-4o-mini,weblinx_test,0.0.1.dev13,2024-11-07_21-42-30,b9451759-4f0e-492c-a3c8-fa5109d2d9b1,0.116,0.006,0,2650/2650,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,7a5b91e62056fa8fb26efdd2f64f5b25a92b817c,,0.12.0,8633c30c31e6a5a1d5122835c035aa56d18f3f0a, -ThibaultLSDC,GenericAgent-gpt-4o,weblinx_test,0.0.1.dev13,2024-11-07_21-42-30,b9451759-4f0e-492c-a3c8-fa5109d2d9b1,0.125,0.006,0,2650/2650,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,7a5b91e62056fa8fb26efdd2f64f5b25a92b817c,,0.12.0,8633c30c31e6a5a1d5122835c035aa56d18f3f0a, -ThibaultLSDC,GenericAgent-anthropic_claude-3.5-sonnet:beta,weblinx_test,0.0.1.dev13,2024-11-07_21-42-30,b9451759-4f0e-492c-a3c8-fa5109d2d9b1,0.137,0.006,0,2650/2650,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,7a5b91e62056fa8fb26efdd2f64f5b25a92b817c,,0.12.0,8633c30c31e6a5a1d5122835c035aa56d18f3f0a, -ThibaultLSDC,GenericAgent-meta-llama_llama-3.1-70b-instruct,weblinx_test,0.0.1.dev13,2024-11-07_21-42-30,b9451759-4f0e-492c-a3c8-fa5109d2d9b1,0.089,0.005,0,2650/2650,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,7a5b91e62056fa8fb26efdd2f64f5b25a92b817c,,0.12.0,8633c30c31e6a5a1d5122835c035aa56d18f3f0a, -ThibaultLSDC,GenericAgent-openai_o1-mini-2024-09-12,weblinx_test,0.0.1.dev13,2024-11-07_21-42-30,b9451759-4f0e-492c-a3c8-fa5109d2d9b1,0.125,0.006,0,2650/2650,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,7a5b91e62056fa8fb26efdd2f64f5b25a92b817c,,0.12.0,8633c30c31e6a5a1d5122835c035aa56d18f3f0a, -ThibaultLSDC,GenericAgent-meta-llama_llama-3.1-405b-instruct,weblinx_test,0.0.1.dev13,2024-11-07_21-42-30,b9451759-4f0e-492c-a3c8-fa5109d2d9b1,0.079,0.005,0,2650/2650,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,7a5b91e62056fa8fb26efdd2f64f5b25a92b817c,,0.12.0,8633c30c31e6a5a1d5122835c035aa56d18f3f0a, -ThibaultLSDC,GenericAgent-meta-llama_llama-3.1-405b-instruct,workarena_l2_agent_curriculum_eval,0.4.1,2024-11-29_14-28-47,528da1f2-1949-41dc-b988-85f19f435af2,0.072,0.017,2,235/235,None,Linux (#68-Ubuntu SMP Mon Oct 7 14:34:20 UTC 2024),3.12.7,1.39.0,0.3.1,b115b2716d8a6328824684a692ed642297f0b1dc,,0.13.3,70dac253628c476aff1af6a975f27f8563453ad2, -ThibaultLSDC,GenericAgent-meta-llama_llama-3.1-405b-instruct,miniwob,0.13.3,2024-11-29_16-14-00,4d748972-6d35-4489-a197-138b656a7db3,0.646,0.019,0,625/625,None,Linux (#68-Ubuntu SMP Mon Oct 7 14:34:20 UTC 2024),3.12.7,1.39.0,0.3.1,becb4856fb1612f44010fe74ef8155d367ca17fc,,0.13.3,70dac253628c476aff1af6a975f27f8563453ad2, -ThibaultLSDC,GenericAgent-gpt-4o,assistantbench,0.13.1,2024-11-28_19-34-58,d93a2398-2b70-41ce-b989-364fed988d73,0.005,0.003,2,213/214,None,Linux (#68-Ubuntu SMP Mon Oct 7 14:34:20 UTC 2024),3.12.7,1.39.0,0.3.0,32865050045c8c71df35c34ff30a6b420a4e258c, M: src/agentlab/experiments/study.py,0.13.1,None, -ThibaultLSDC,GenericAgent-gpt-4o-mini,assistantbench,0.13.1,2024-11-28_19-34-58,d93a2398-2b70-41ce-b989-364fed988d73,0.002,0.002,1,214/214,None,Linux (#68-Ubuntu SMP Mon Oct 7 14:34:20 UTC 2024),3.12.7,1.39.0,0.3.0,32865050045c8c71df35c34ff30a6b420a4e258c, M: src/agentlab/experiments/study.py,0.13.1,None, -ThibaultLSDC,GenericAgent-meta-llama_llama-3.1-405b-instruct,assistantbench,0.13.1,2024-11-28_19-34-58,d93a2398-2b70-41ce-b989-364fed988d73,0.008,0.003,1,212/214,None,Linux (#68-Ubuntu SMP Mon Oct 7 14:34:20 UTC 2024),3.12.7,1.39.0,0.3.0,32865050045c8c71df35c34ff30a6b420a4e258c, M: src/agentlab/experiments/study.py,0.13.1,None, -ThibaultLSDC,GenericAgent-meta-llama_llama-3.1-70b-instruct,assistantbench,0.13.1,2024-11-28_19-34-58,d93a2398-2b70-41ce-b989-364fed988d73,0.007,0.005,8,206/214,None,Linux (#68-Ubuntu SMP Mon Oct 7 14:34:20 UTC 2024),3.12.7,1.39.0,0.3.0,32865050045c8c71df35c34ff30a6b420a4e258c, M: src/agentlab/experiments/study.py,0.13.1,None, -ThibaultLSDC,GenericAgent-meta-llama_llama-3.1-8b-instruct,assistantbench,0.13.1,2024-11-28_19-34-58,d93a2398-2b70-41ce-b989-364fed988d73,0.001,0.001,15,214/214,None,Linux (#68-Ubuntu SMP Mon Oct 7 14:34:20 UTC 2024),3.12.7,1.39.0,0.3.0,32865050045c8c71df35c34ff30a6b420a4e258c, M: src/agentlab/experiments/study.py,0.13.1,None, -ThibaultLSDC,GenericAgent-anthropic_claude-3.5-sonnet:beta,assistantbench,0.13.1,2024-11-28_19-34-58,d93a2398-2b70-41ce-b989-364fed988d73,0.007,0.003,1,212/214,None,Linux (#68-Ubuntu SMP Mon Oct 7 14:34:20 UTC 2024),3.12.7,1.39.0,0.3.0,32865050045c8c71df35c34ff30a6b420a4e258c, M: src/agentlab/experiments/study.py,0.13.1,None, -ThibaultLSDC,GenericAgent-openai_o1-mini-2024-09-12,assistantbench,0.13.1,2024-11-28_19-34-58,d93a2398-2b70-41ce-b989-364fed988d73,0.009,0.005,1,214/214,None,Linux (#68-Ubuntu SMP Mon Oct 7 14:34:20 UTC 2024),3.12.7,1.39.0,0.3.0,32865050045c8c71df35c34ff30a6b420a4e258c, M: src/agentlab/experiments/study.py,0.13.1,None, -ThibaultLSDC,GenericAgent-gpt-4o-mini,webarena,0.13.3,2024-11-29_19-25-49,c6bdeb87-9879-4c06-aa70-00d895001156,0.174,0.013,1,812/812,None,Linux (#68-Ubuntu SMP Mon Oct 7 14:34:20 UTC 2024),3.12.7,1.39.0,0.3.1,b115b2716d8a6328824684a692ed642297f0b1dc,,0.13.3,None, -ThibaultLSDC,GenericAgent-gpt-4o,webarena,0.13.3,2024-11-29_22-28-32,d2eed215-91bb-4603-b69c-8ef8f9d57f34,0.314,0.016,3,812/812,None,Linux (#68-Ubuntu SMP Mon Oct 7 14:34:20 UTC 2024),3.12.7,1.39.0,0.3.1,430fe9456ba766398380454a6335f094004607af,,0.13.3,None, -ThibaultLSDC,GenericAgent-anthropic_claude-3.5-sonnet:beta,webarena,0.13.3,2024-11-29_22-37-46,b5fc5be7-54cc-4fc1-a9ee-73447b9c3eae,0.362,0.017,0,812/812,None,Linux (#68-Ubuntu SMP Mon Oct 7 14:34:20 UTC 2024),3.12.7,1.39.0,0.3.1,7b224971fb7a90fb76924ca9386a1e8bf609dd2a,,0.13.3,None, -ThibaultLSDC,GenericAgent-openai_o1-mini-2024-09-12,webarena,0.13.3,2024-11-30_00-22-44,1827983d-5e84-4b63-ad49-bf45ec2a6348,0.286,0.016,0,812/812,None,Linux (#68-Ubuntu SMP Mon Oct 7 14:34:20 UTC 2024),3.12.7,1.39.0,0.3.1,3f54ef13b778e69a1706c732f776147e9523ad3d,,0.13.3,None, -ThibaultLSDC,GenericAgent-meta-llama_llama-3.1-405b-instruct,webarena,0.13.3,2024-12-01_00-04-43,aaeca13d-0cf5-444f-8445-590350b54746,0.24,0.015,9,812/812,None,Linux (#68-Ubuntu SMP Mon Oct 7 14:34:20 UTC 2024),3.12.7,1.39.0,0.3.1,5a5b94d544424517cdd11602b27100b82e35eac0,,0.13.3,None, -ThibaultLSDC,GenericAgent-gpt-4o-mini_vision,visualwebarena,0.13.3,2024-12-02_02-54-33,8d8642d3-757a-4346-ba45-01398f85b1f4,0.169,0.012,37,909/910,None,Linux (#68-Ubuntu SMP Mon Oct 7 14:34:20 UTC 2024),3.12.7,1.39.0,0.3.1,df7bc706f3793f47a456d1bda0485b306b8cf612,,0.13.3,None, -ThibaultLSDC,GenericAgent-gpt-4o_vision,visualwebarena,0.13.3,2024-12-02_07-17-28,7fb7eac8-4bbd-4ebe-be32-15901a7678f2,0.267,0.015,65,910/910,None,Linux (#68-Ubuntu SMP Mon Oct 7 14:34:20 UTC 2024),3.12.7,1.39.0,0.3.1,df7bc706f3793f47a456d1bda0485b306b8cf612,,0.13.3,None, -ThibaultLSDC,GenericAgent-anthropic_claude-3.5-sonnet:beta_vision,visualwebarena,0.13.3,2024-12-02_09-11-35,22f0611d-aeea-4ee9-a533-b45442b5e080,0.21,0.013,178,910/910,None,Linux (#68-Ubuntu SMP Mon Oct 7 14:34:20 UTC 2024),3.12.7,1.39.0,0.3.1,df7bc706f3793f47a456d1bda0485b306b8cf612,,0.13.3,None, -ThibaultLSDC,GenericAgent-meta-llama_llama-3.1-70b-instruct,webarena,0.13.3,2024-12-02_23-18-38,fc5747bc-d998-4942-a0eb-e55a3ccc1cb3,0.184,0.014,213,811/812,None,Linux (#68-Ubuntu SMP Mon Oct 7 14:34:20 UTC 2024),3.12.7,1.39.0,0.3.1,df7bc706f3793f47a456d1bda0485b306b8cf612,,0.13.3,None, -Leo Boisvert,GenericAgent-o3-mini-2025-01-31,workarena_l1,0.4.1,2025-01-31_22-08-33,a74cc00f-f743-43a1-9cab-59af8bffa3a2,0.482,0.028,3,330/330,None,Linux (#68-Ubuntu SMP Mon Oct 7 14:34:20 UTC 2024),3.12.3,1.44.0,v0.3.2,73baabee6d7ac37a5b8677c80baf83914a4f4dc4," M: src/agentlab/agents/generic_agent/__init__.py - M: src/agentlab/agents/generic_agent/agent_configs.py - M: src/agentlab/analyze/agent_xray.py - M: src/agentlab/llm/chat_api.py - M: src/agentlab/llm/llm_configs.py",0.13.3,1d2d7160e5b7ec9954ecb48988f71eb56288dd29," -Leo Boisvert,GenericAgent-openai_o1-mini-2024-09-12,workarena_l1,0.4.1,2025-02-02_01-55-04,f3e1fcb8-5fc5-4115-9e00-27251508e2c7,0.518,0.028,5,330/330,None,Linux (#68-Ubuntu SMP Mon Oct 7 14:34:20 UTC 2024),3.12.3,1.44.0,v0.3.2,73baabee6d7ac37a5b8677c80baf83914a4f4dc4," M: src/agentlab/agents/generic_agent/__init__.py - M: src/agentlab/agents/generic_agent/agent_configs.py - M: src/agentlab/analyze/agent_xray.py - M: src/agentlab/llm/llm_configs.py",0.13.3,1d2d7160e5b7ec9954ecb48988f71eb56288dd29," -Leo Boisvert,GenericAgent-anthropic_claude-3.7-sonnet,workarena_l1,0.4.1,2025-02-25_02-32-09,d4f900c2-1de1-4e4b-a3ab-495ff2675fff,0.515,0.028,0,330/330,None,Linux (#68-Ubuntu SMP Mon Oct 7 14:34:20 UTC 2024),3.12.3,1.44.0,v0.4.0,c9d2ef9648435ef1119950ecb1a0734497ccc33b,,0.13.3,1d2d7160e5b7ec9954ecb48988f71eb56288dd29, -agentlabtraces,GenericAgent-meta-llama_llama-4-maverick,workarena_l1,0.4.1,2025-04-14_17-15-56,a6dc4022-2bb7-4b46-8b37-f62c010defc1,0.27,0.024,0,330/330,None,Linux (#135-Ubuntu SMP Fri Sep 27 13:53:58 UTC 2024),3.12.7,1.39.0,v0.4.0,5eb2ecb5e5b293170230bcbed8b17fe192af214a,,0.13.3,70dac253628c476aff1af6a975f27f8563453ad2, -agentlabtraces,GenericAgent-meta-llama_llama-4-maverick,workarena_l2_agent_curriculum_eval,0.4.1,2025-04-22_15-38-44,d62fed39-caac-4ef3-92ac-b29897c69f88,0.085,0.018,1,235/235,None,Linux (#68-Ubuntu SMP Mon Oct 7 14:34:20 UTC 2024),3.12.7,1.39.0,v0.4.0,43bafbcfbe398fca39e4ffdc57b2f226d2c6d3e1,,0.13.3,70dac253628c476aff1af6a975f27f8563453ad2, +git_user,agent_name,benchmark,benchmark_version,date,study_id,avg_reward,std_err,n_err,n_completed,comment,os,python_version,playwright_version,agentlab_version,agentlab_git_hash,agentlab__local_modifications,browsergym_version,browsergym_git_hash,browsergym__local_modifications +recursix,GenericAgent-gpt-4o-mini-2024-07-18,miniwob_tiny_test,0.6.3,2024-09-19_21-07-34,,0.75,0.217,0,4/4,,Darwin (Darwin Kernel Version 23.6.0: Mon Jul 29 21:13:00 PDT 2024; root:xnu-10063.141.2~1/RELEASE_X86_64),3.12.2,1.39.0,0.2.1,c99bdf74c98f323cc6a646467ba5f21154b6fd18,,0.6.4,b73531271d2ce688c104eb4dfba2819583f1ba36, +recursix,GenericAgent-gpt-4o-mini-2024-07-18,miniwob_tiny_test,0.6.3,2024-09-19_21-28-58,,1.0,0.0,0,4/4,,Darwin (Darwin Kernel Version 23.6.0: Mon Jul 29 21:13:00 PDT 2024; root:xnu-10063.141.2~1/RELEASE_X86_64),3.12.2,1.39.0,0.2.1,c99bdf74c98f323cc6a646467ba5f21154b6fd18," M: reproducibility_journal.csv + M: src/agentlab/experiments/task_collections.py",0.6.4,b73531271d2ce688c104eb4dfba2819583f1ba36, +recursix,GenericAgent-gpt-4o-mini-2024-07-18,miniwob,0.6.3,2024-09-20_07-16-21,,0.546,0.02,0,625/625,,Darwin (Darwin Kernel Version 23.6.0: Mon Jul 29 21:13:00 PDT 2024; root:xnu-10063.141.2~1/RELEASE_X86_64),3.12.2,1.39.0,0.2.1,295f01005faf8f2c73a31be6a18cec19d563b54b,,0.6.4,b73531271d2ce688c104eb4dfba2819583f1ba36, +recursix,GenericAgent-gpt-4o-2024-05-13,miniwob,0.6.3,2024-09-20_22-09-43,,0.656,0.019,0,625/625,,Darwin (Darwin Kernel Version 23.6.0: Mon Jul 29 21:13:00 PDT 2024; root:xnu-10063.141.2~1/RELEASE_X86_64),3.12.2,1.39.0,0.2.1,f6216486d5faac2c8b3fb0a63e114e5a4bafde47,,0.6.4,8cef8fe34940ff490d0cc06b0c8f100180d09d43, +recursix,GenericAgent-gpt-4o-2024-05-13,miniwob,0.6.3,2024-09-21_12-04-39,,0.656,0.019,0,625/625,None,Darwin (Darwin Kernel Version 23.6.0: Mon Jul 29 21:13:00 PDT 2024; root:xnu-10063.141.2~1/RELEASE_X86_64),3.12.2,1.39.0,0.2.1,fe561b93c5f053e9f9625358862f542523b5e14a,,0.7.0,ed6d6992ef64bfb91aca7002d33cb6ed5ec031ef, +recursix,GenericAgent-gpt-4o-mini-2024-07-18,miniwob,0.6.3,2024-10-01_11-45-23,,0.539,0.02,0,625/625,None,Darwin (Darwin Kernel Version 23.6.0: Mon Jul 29 21:13:00 PDT 2024; root:xnu-10063.141.2~1/RELEASE_X86_64),3.12.2,1.39.0,0.2.1,fe27819a99b163fd9240ba3e144e010413bff24d,,0.7.1,b0ad675572e01cac0d7255100112de0828877148, +recursix,GenericAgent-gpt-4o-mini-2024-07-18,workarena.l1,0.3.2,2024-10-05_13-21-27,,0.23,0.023,0,330/330,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.6,1.39.0,0.2.1,aadf86b397cd36c581e1a61e491aec649ac5a140," M: main.py",0.7.0,2a0ab7e8e8795f8ca35fe4d4d67c6892d635dc12, +recursix,GenericAgent-gpt-4o-2024-05-13,workarena.l1,0.3.2,2024-10-05_15-45-42,,0.382,0.027,0,330/330,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.6,1.39.0,0.2.1,ab447e997af589bbd022de7a5189a7685ddfa6ef,,0.7.0,2a0ab7e8e8795f8ca35fe4d4d67c6892d635dc12, +recursix,GenericAgent-meta-llama_llama-3-70b-instruct,workarena.l1,0.3.2,2024-10-09_21-16-37,,0.176,0.021,0,330/330,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.6,1.39.0,0.2.1,c847dbd334184271b32b252409a1b6c1042d7442,,0.7.0,2a0ab7e8e8795f8ca35fe4d4d67c6892d635dc12, +recursix,GenericAgent-meta-llama_llama-3.1-70b-instruct,miniwob_tiny_test,0.7.0,2024-10-05_17-49-15,,1.0,0.0,0,4/4,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.6,1.39.0,0.2.1,a98fa24426a6ddde8443e8be44ed94cd9522e5ca,,0.7.0,2a0ab7e8e8795f8ca35fe4d4d67c6892d635dc12, +ThibaultLSDC,GenericAgent-gpt-4o-mini-2024-07-18,miniwob,0.8.1,2024-10-17_10-13-28,,0.557,0.02,0,625/625,None,Darwin (Darwin Kernel Version 23.6.0: Mon Jul 29 21:13:00 PDT 2024; root:xnu-10063.141.2~1/RELEASE_X86_64),3.12.7,1.39.0,0.2.2,7bba275c004f1f90dfd83eaaab963ab5066e2baf,,0.8.1,None, +ThibaultLSDC,GenericAgent-gpt-4o-mini-2024-07-18,miniwob,0.8.1,2024-10-17_10-50-53,,0.563,0.02,0,625/625,None,Darwin (Darwin Kernel Version 23.6.0: Mon Jul 29 21:13:00 PDT 2024; root:xnu-10063.141.2~1/RELEASE_X86_64),3.12.7,1.39.0,0.2.2,057b7d4a201cc1cd1ebd7bc884f6a91e104c479d,,0.8.1,None, +ThibaultLSDC,GenericAgent-gpt-4o-mini-2024-07-18,workarena.l1,0.4.1,2024-10-17_17-30-43,,0.258,0.024,0,330/330,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.2,7bba275c004f1f90dfd83eaaab963ab5066e2baf,,0.8.1,None, +ThibaultLSDC,GenericAgent-gpt-4o-mini-2024-07-18,workarena.l1,0.4.1,2024-10-17_18-30-28,,0.273,0.025,0,330/330,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.2,8b2b3f39a2bdb9efafad97791536a0b8cff4e708,,0.8.1,None, +ThibaultLSDC,GenericAgent-gpt-4o-mini-2024-07-18,miniwob_all,0.9.0,2024-10-20_01-54-16,2024-10-20_01-54-02,0.588,0.014,0,1250/1250,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.2,1770eba87fabfe1e32cdf6078d71032fe00db736,,0.9.0,None, +ThibaultLSDC,GenericAgent-gpt-4o-mini-2024-07-18,workarena_l1,0.4.1,2024-10-22_18-41-55,2024-10-22_15-24-53,0.215,0.023,1,330/330,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,a6c1f93c59fb7a838d06ca02ef6c62abe2ce278c,,0.9.0,None, +ThibaultLSDC,GenericAgent-gpt-4o-mini,workarena_l1,0.4.1,2024-10-23_12-17-24,2024-10-23_02-00-49,0.252,0.024,1,330/330,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,d364ce7d5f566889830cdc0ef58b320d2093694e,,0.9.0,None, +ThibaultLSDC,GenericAgent-gpt-4o,workarena_l1,0.4.1,2024-10-23_12-17-24,2024-10-23_02-00-49,0.488,0.028,1,330/330,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,d364ce7d5f566889830cdc0ef58b320d2093694e,,0.9.0,None, +ThibaultLSDC,GenericAgent-anthropic_claude-3.5-sonnet:beta,workarena_l1,0.4.1,2024-10-23_12-17-24,2024-10-23_02-00-49,0.579,0.027,2,330/330,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,d364ce7d5f566889830cdc0ef58b320d2093694e,,0.9.0,None, +ThibaultLSDC,GenericAgent-meta-llama_llama-3.1-70b-instruct,workarena_l1,0.4.1,2024-10-23_12-17-24,2024-10-23_02-00-49,0.309,0.025,2,330/330,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,d364ce7d5f566889830cdc0ef58b320d2093694e,,0.9.0,None, +ThibaultLSDC,GenericAgent-openai_o1-mini-2024-09-12,workarena_l1,0.4.1,2024-10-23_12-17-24,2024-10-23_02-00-49,0.527,0.027,2,330/330,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,d364ce7d5f566889830cdc0ef58b320d2093694e,,0.9.0,None, +ThibaultLSDC,GenericAgent-gpt-4o-mini,workarena_l1,0.4.1,2024-10-23_22-30-06,2024-10-23_14-17-40,0.27,0.024,1,330/330,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,4cd1e2d4189ddfbeb94129f7b0c9a00c3400ebac,,0.9.0,f25bdcd6b946fc4a79cdbee5fbcad53548af8724, +ThibaultLSDC,GenericAgent-gpt-4o,workarena_l1,0.4.1,2024-10-23_22-30-06,2024-10-23_14-17-40,0.455,0.027,1,330/330,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,4cd1e2d4189ddfbeb94129f7b0c9a00c3400ebac,,0.9.0,f25bdcd6b946fc4a79cdbee5fbcad53548af8724, +ThibaultLSDC,GenericAgent-anthropic_claude-3.5-sonnet:beta,workarena_l1,0.4.1,2024-10-23_22-30-06,2024-10-23_14-17-40,0.564,0.027,1,330/330,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,4cd1e2d4189ddfbeb94129f7b0c9a00c3400ebac,,0.9.0,f25bdcd6b946fc4a79cdbee5fbcad53548af8724, +ThibaultLSDC,GenericAgent-meta-llama_llama-3.1-70b-instruct,workarena_l1,0.4.1,2024-10-23_22-30-06,2024-10-23_14-17-40,0.279,0.025,0,330/330,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,4cd1e2d4189ddfbeb94129f7b0c9a00c3400ebac,,0.9.0,f25bdcd6b946fc4a79cdbee5fbcad53548af8724, +ThibaultLSDC,GenericAgent-openai_o1-mini-2024-09-12,workarena_l1,0.4.1,2024-10-23_22-30-06,2024-10-23_14-17-40,0.567,0.027,4,330/330,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,4cd1e2d4189ddfbeb94129f7b0c9a00c3400ebac,,0.9.0,f25bdcd6b946fc4a79cdbee5fbcad53548af8724, +recursix,GenericAgent-anthropic_claude-3.5-sonnet:beta,webarena,0.11.3,2024-11-02_23-50-17,22a9d3f5-9d86-455e-b451-3ea17690ce8a,0.329,0.016,0,812/812,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.6,1.39.0,0.2.3,418a05d90c74800cd66371b7846ef861185b8c47,,0.11.3,160167ff0d2631826f0131e8e30b92ef448d6881, +ThibaultLSDC,GenericAgent-gpt-4o-mini,workarena_l2_agent_curriculum_eval,0.4.1,2024-10-24_17-08-53,2024-10-23_17-10-46,0.013,0.007,2,235/235,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,827d847995f19dc337f3899427340bdddbd81cd5,,0.10.0,None, +ThibaultLSDC,GenericAgent-gpt-4o,workarena_l2_agent_curriculum_eval,0.4.1,2024-10-24_17-08-53,2024-10-23_17-10-46,0.085,0.018,3,233/235,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,827d847995f19dc337f3899427340bdddbd81cd5,,0.10.0,None, +ThibaultLSDC,GenericAgent-anthropic_claude-3.5-sonnet:beta,workarena_l2_agent_curriculum_eval,0.4.1,2024-10-24_17-08-53,2024-10-23_17-10-46,0.391,0.032,3,235/235,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,827d847995f19dc337f3899427340bdddbd81cd5,,0.10.0,None, +ThibaultLSDC,GenericAgent-meta-llama_llama-3.1-70b-instruct,workarena_l2_agent_curriculum_eval,0.4.1,2024-10-24_17-08-53,2024-10-23_17-10-46,0.021,0.009,2,235/235,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,827d847995f19dc337f3899427340bdddbd81cd5,,0.10.0,None, +ThibaultLSDC,GenericAgent-openai_o1-mini-2024-09-12,workarena_l2_agent_curriculum_eval,0.4.1,2024-10-24_17-08-53,2024-10-23_17-10-46,0.149,0.023,1,235/235,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,827d847995f19dc337f3899427340bdddbd81cd5,,0.10.0,None, +ThibaultLSDC,GenericAgent-anthropic_claude-3.5-sonnet:beta,workarena_l3_agent_curriculum_eval,0.4.1,2024-10-24_23-03-30,2024-10-24_18-06-57,0.004,0.004,1,235/235,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,de67ed8ad4321740ff05cf26ab889978be706460,,0.10.2,a9e44a88139798543ba53fc8c45d44997665ccca, +ThibaultLSDC,GenericAgent-gpt-4o-mini,miniwob,0.10.2,2024-10-25_17-16-23,2024-10-25_06-08-16,0.566,0.02,0,625/625,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,f12887f776525bcad6a0c42cb49651ff4f65af43,,0.10.2,a9e44a88139798543ba53fc8c45d44997665ccca, +ThibaultLSDC,GenericAgent-gpt-4o,miniwob,0.10.2,2024-10-25_17-16-23,2024-10-25_06-08-16,0.638,0.019,0,625/625,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,f12887f776525bcad6a0c42cb49651ff4f65af43,,0.10.2,a9e44a88139798543ba53fc8c45d44997665ccca, +ThibaultLSDC,GenericAgent-anthropic_claude-3.5-sonnet:beta,miniwob,0.10.2,2024-10-25_17-16-23,2024-10-25_06-08-16,0.698,0.018,0,625/625,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,f12887f776525bcad6a0c42cb49651ff4f65af43,,0.10.2,a9e44a88139798543ba53fc8c45d44997665ccca, +ThibaultLSDC,GenericAgent-meta-llama_llama-3.1-70b-instruct,miniwob,0.10.2,2024-10-25_17-16-23,2024-10-25_06-08-16,0.576,0.02,0,625/625,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,f12887f776525bcad6a0c42cb49651ff4f65af43,,0.10.2,a9e44a88139798543ba53fc8c45d44997665ccca, +ThibaultLSDC,GenericAgent-openai_o1-mini-2024-09-12,miniwob,0.10.2,2024-10-25_17-16-23,2024-10-25_06-08-16,0.678,0.019,0,625/625,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,f12887f776525bcad6a0c42cb49651ff4f65af43,,0.10.2,a9e44a88139798543ba53fc8c45d44997665ccca, +ThibaultLSDC,GenericAgent-meta-llama_llama-3.1-405b-instruct,workarena_l1,0.4.1,2024-10-25_20-32-26,2024-10-25_17-34-45,0.433,0.027,1,330/330,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,177ba72a7469e5610e6b615adf1bdcde58cb0298,,0.10.2,a9e44a88139798543ba53fc8c45d44997665ccca, +Maxime Gasse,GenericAgent-gpt-4o-2024-05-13,weblinx_test,0.0.1.dev13,2024-11-04_16-01-14,2024-11-04_15-59-12,0.123,0.006,0,2650/2650,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.0,1.39.0,0.2.3,6e18fb818a64ec1e3f379c1a6480411d2fd0628b,,0.11.3,3ab1843edb14bfce7d39485f0106d0dc0c2d7486, +ThibaultLSDC,GenericAgent-gpt-4o-mini,weblinx_test,0.0.1.dev13,2024-11-07_21-42-30,b9451759-4f0e-492c-a3c8-fa5109d2d9b1,0.116,0.006,0,2650/2650,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,7a5b91e62056fa8fb26efdd2f64f5b25a92b817c,,0.12.0,8633c30c31e6a5a1d5122835c035aa56d18f3f0a, +ThibaultLSDC,GenericAgent-gpt-4o,weblinx_test,0.0.1.dev13,2024-11-07_21-42-30,b9451759-4f0e-492c-a3c8-fa5109d2d9b1,0.125,0.006,0,2650/2650,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,7a5b91e62056fa8fb26efdd2f64f5b25a92b817c,,0.12.0,8633c30c31e6a5a1d5122835c035aa56d18f3f0a, +ThibaultLSDC,GenericAgent-anthropic_claude-3.5-sonnet:beta,weblinx_test,0.0.1.dev13,2024-11-07_21-42-30,b9451759-4f0e-492c-a3c8-fa5109d2d9b1,0.137,0.006,0,2650/2650,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,7a5b91e62056fa8fb26efdd2f64f5b25a92b817c,,0.12.0,8633c30c31e6a5a1d5122835c035aa56d18f3f0a, +ThibaultLSDC,GenericAgent-meta-llama_llama-3.1-70b-instruct,weblinx_test,0.0.1.dev13,2024-11-07_21-42-30,b9451759-4f0e-492c-a3c8-fa5109d2d9b1,0.089,0.005,0,2650/2650,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,7a5b91e62056fa8fb26efdd2f64f5b25a92b817c,,0.12.0,8633c30c31e6a5a1d5122835c035aa56d18f3f0a, +ThibaultLSDC,GenericAgent-openai_o1-mini-2024-09-12,weblinx_test,0.0.1.dev13,2024-11-07_21-42-30,b9451759-4f0e-492c-a3c8-fa5109d2d9b1,0.125,0.006,0,2650/2650,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,7a5b91e62056fa8fb26efdd2f64f5b25a92b817c,,0.12.0,8633c30c31e6a5a1d5122835c035aa56d18f3f0a, +ThibaultLSDC,GenericAgent-meta-llama_llama-3.1-405b-instruct,weblinx_test,0.0.1.dev13,2024-11-07_21-42-30,b9451759-4f0e-492c-a3c8-fa5109d2d9b1,0.079,0.005,0,2650/2650,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,7a5b91e62056fa8fb26efdd2f64f5b25a92b817c,,0.12.0,8633c30c31e6a5a1d5122835c035aa56d18f3f0a, +ThibaultLSDC,GenericAgent-meta-llama_llama-3.1-405b-instruct,workarena_l2_agent_curriculum_eval,0.4.1,2024-11-29_14-28-47,528da1f2-1949-41dc-b988-85f19f435af2,0.072,0.017,2,235/235,None,Linux (#68-Ubuntu SMP Mon Oct 7 14:34:20 UTC 2024),3.12.7,1.39.0,0.3.1,b115b2716d8a6328824684a692ed642297f0b1dc,,0.13.3,70dac253628c476aff1af6a975f27f8563453ad2, +ThibaultLSDC,GenericAgent-meta-llama_llama-3.1-405b-instruct,miniwob,0.13.3,2024-11-29_16-14-00,4d748972-6d35-4489-a197-138b656a7db3,0.646,0.019,0,625/625,None,Linux (#68-Ubuntu SMP Mon Oct 7 14:34:20 UTC 2024),3.12.7,1.39.0,0.3.1,becb4856fb1612f44010fe74ef8155d367ca17fc,,0.13.3,70dac253628c476aff1af6a975f27f8563453ad2, +ThibaultLSDC,GenericAgent-gpt-4o,assistantbench,0.13.1,2024-11-28_19-34-58,d93a2398-2b70-41ce-b989-364fed988d73,0.005,0.003,2,213/214,None,Linux (#68-Ubuntu SMP Mon Oct 7 14:34:20 UTC 2024),3.12.7,1.39.0,0.3.0,32865050045c8c71df35c34ff30a6b420a4e258c, M: src/agentlab/experiments/study.py,0.13.1,None, +ThibaultLSDC,GenericAgent-gpt-4o-mini,assistantbench,0.13.1,2024-11-28_19-34-58,d93a2398-2b70-41ce-b989-364fed988d73,0.002,0.002,1,214/214,None,Linux (#68-Ubuntu SMP Mon Oct 7 14:34:20 UTC 2024),3.12.7,1.39.0,0.3.0,32865050045c8c71df35c34ff30a6b420a4e258c, M: src/agentlab/experiments/study.py,0.13.1,None, +ThibaultLSDC,GenericAgent-meta-llama_llama-3.1-405b-instruct,assistantbench,0.13.1,2024-11-28_19-34-58,d93a2398-2b70-41ce-b989-364fed988d73,0.008,0.003,1,212/214,None,Linux (#68-Ubuntu SMP Mon Oct 7 14:34:20 UTC 2024),3.12.7,1.39.0,0.3.0,32865050045c8c71df35c34ff30a6b420a4e258c, M: src/agentlab/experiments/study.py,0.13.1,None, +ThibaultLSDC,GenericAgent-meta-llama_llama-3.1-70b-instruct,assistantbench,0.13.1,2024-11-28_19-34-58,d93a2398-2b70-41ce-b989-364fed988d73,0.007,0.005,8,206/214,None,Linux (#68-Ubuntu SMP Mon Oct 7 14:34:20 UTC 2024),3.12.7,1.39.0,0.3.0,32865050045c8c71df35c34ff30a6b420a4e258c, M: src/agentlab/experiments/study.py,0.13.1,None, +ThibaultLSDC,GenericAgent-meta-llama_llama-3.1-8b-instruct,assistantbench,0.13.1,2024-11-28_19-34-58,d93a2398-2b70-41ce-b989-364fed988d73,0.001,0.001,15,214/214,None,Linux (#68-Ubuntu SMP Mon Oct 7 14:34:20 UTC 2024),3.12.7,1.39.0,0.3.0,32865050045c8c71df35c34ff30a6b420a4e258c, M: src/agentlab/experiments/study.py,0.13.1,None, +ThibaultLSDC,GenericAgent-anthropic_claude-3.5-sonnet:beta,assistantbench,0.13.1,2024-11-28_19-34-58,d93a2398-2b70-41ce-b989-364fed988d73,0.007,0.003,1,212/214,None,Linux (#68-Ubuntu SMP Mon Oct 7 14:34:20 UTC 2024),3.12.7,1.39.0,0.3.0,32865050045c8c71df35c34ff30a6b420a4e258c, M: src/agentlab/experiments/study.py,0.13.1,None, +ThibaultLSDC,GenericAgent-openai_o1-mini-2024-09-12,assistantbench,0.13.1,2024-11-28_19-34-58,d93a2398-2b70-41ce-b989-364fed988d73,0.009,0.005,1,214/214,None,Linux (#68-Ubuntu SMP Mon Oct 7 14:34:20 UTC 2024),3.12.7,1.39.0,0.3.0,32865050045c8c71df35c34ff30a6b420a4e258c, M: src/agentlab/experiments/study.py,0.13.1,None, +ThibaultLSDC,GenericAgent-gpt-4o-mini,webarena,0.13.3,2024-11-29_19-25-49,c6bdeb87-9879-4c06-aa70-00d895001156,0.174,0.013,1,812/812,None,Linux (#68-Ubuntu SMP Mon Oct 7 14:34:20 UTC 2024),3.12.7,1.39.0,0.3.1,b115b2716d8a6328824684a692ed642297f0b1dc,,0.13.3,None, +ThibaultLSDC,GenericAgent-gpt-4o,webarena,0.13.3,2024-11-29_22-28-32,d2eed215-91bb-4603-b69c-8ef8f9d57f34,0.314,0.016,3,812/812,None,Linux (#68-Ubuntu SMP Mon Oct 7 14:34:20 UTC 2024),3.12.7,1.39.0,0.3.1,430fe9456ba766398380454a6335f094004607af,,0.13.3,None, +ThibaultLSDC,GenericAgent-anthropic_claude-3.5-sonnet:beta,webarena,0.13.3,2024-11-29_22-37-46,b5fc5be7-54cc-4fc1-a9ee-73447b9c3eae,0.362,0.017,0,812/812,None,Linux (#68-Ubuntu SMP Mon Oct 7 14:34:20 UTC 2024),3.12.7,1.39.0,0.3.1,7b224971fb7a90fb76924ca9386a1e8bf609dd2a,,0.13.3,None, +ThibaultLSDC,GenericAgent-openai_o1-mini-2024-09-12,webarena,0.13.3,2024-11-30_00-22-44,1827983d-5e84-4b63-ad49-bf45ec2a6348,0.286,0.016,0,812/812,None,Linux (#68-Ubuntu SMP Mon Oct 7 14:34:20 UTC 2024),3.12.7,1.39.0,0.3.1,3f54ef13b778e69a1706c732f776147e9523ad3d,,0.13.3,None, +ThibaultLSDC,GenericAgent-meta-llama_llama-3.1-405b-instruct,webarena,0.13.3,2024-12-01_00-04-43,aaeca13d-0cf5-444f-8445-590350b54746,0.24,0.015,9,812/812,None,Linux (#68-Ubuntu SMP Mon Oct 7 14:34:20 UTC 2024),3.12.7,1.39.0,0.3.1,5a5b94d544424517cdd11602b27100b82e35eac0,,0.13.3,None, +ThibaultLSDC,GenericAgent-gpt-4o-mini_vision,visualwebarena,0.13.3,2024-12-02_02-54-33,8d8642d3-757a-4346-ba45-01398f85b1f4,0.169,0.012,37,909/910,None,Linux (#68-Ubuntu SMP Mon Oct 7 14:34:20 UTC 2024),3.12.7,1.39.0,0.3.1,df7bc706f3793f47a456d1bda0485b306b8cf612,,0.13.3,None, +ThibaultLSDC,GenericAgent-gpt-4o_vision,visualwebarena,0.13.3,2024-12-02_07-17-28,7fb7eac8-4bbd-4ebe-be32-15901a7678f2,0.267,0.015,65,910/910,None,Linux (#68-Ubuntu SMP Mon Oct 7 14:34:20 UTC 2024),3.12.7,1.39.0,0.3.1,df7bc706f3793f47a456d1bda0485b306b8cf612,,0.13.3,None, +ThibaultLSDC,GenericAgent-anthropic_claude-3.5-sonnet:beta_vision,visualwebarena,0.13.3,2024-12-02_09-11-35,22f0611d-aeea-4ee9-a533-b45442b5e080,0.21,0.013,178,910/910,None,Linux (#68-Ubuntu SMP Mon Oct 7 14:34:20 UTC 2024),3.12.7,1.39.0,0.3.1,df7bc706f3793f47a456d1bda0485b306b8cf612,,0.13.3,None, +ThibaultLSDC,GenericAgent-meta-llama_llama-3.1-70b-instruct,webarena,0.13.3,2024-12-02_23-18-38,fc5747bc-d998-4942-a0eb-e55a3ccc1cb3,0.184,0.014,213,811/812,None,Linux (#68-Ubuntu SMP Mon Oct 7 14:34:20 UTC 2024),3.12.7,1.39.0,0.3.1,df7bc706f3793f47a456d1bda0485b306b8cf612,,0.13.3,None, +Leo Boisvert,GenericAgent-o3-mini-2025-01-31,workarena_l1,0.4.1,2025-01-31_22-08-33,a74cc00f-f743-43a1-9cab-59af8bffa3a2,0.482,0.028,3,330/330,None,Linux (#68-Ubuntu SMP Mon Oct 7 14:34:20 UTC 2024),3.12.3,1.44.0,v0.3.2,73baabee6d7ac37a5b8677c80baf83914a4f4dc4," M: src/agentlab/agents/generic_agent/__init__.py + M: src/agentlab/agents/generic_agent/agent_configs.py + M: src/agentlab/analyze/agent_xray.py + M: src/agentlab/llm/chat_api.py + M: src/agentlab/llm/llm_configs.py",0.13.3,1d2d7160e5b7ec9954ecb48988f71eb56288dd29, +Leo Boisvert,GenericAgent-openai_o1-mini-2024-09-12,workarena_l1,0.4.1,2025-02-02_01-55-04,f3e1fcb8-5fc5-4115-9e00-27251508e2c7,0.518,0.028,5,330/330,None,Linux (#68-Ubuntu SMP Mon Oct 7 14:34:20 UTC 2024),3.12.3,1.44.0,v0.3.2,73baabee6d7ac37a5b8677c80baf83914a4f4dc4," M: src/agentlab/agents/generic_agent/__init__.py + M: src/agentlab/agents/generic_agent/agent_configs.py + M: src/agentlab/analyze/agent_xray.py + M: src/agentlab/llm/llm_configs.py",0.13.3,1d2d7160e5b7ec9954ecb48988f71eb56288dd29, +Leo Boisvert,GenericAgent-anthropic_claude-3.7-sonnet,workarena_l1,0.4.1,2025-02-25_02-32-09,d4f900c2-1de1-4e4b-a3ab-495ff2675fff,0.515,0.028,0,330/330,None,Linux (#68-Ubuntu SMP Mon Oct 7 14:34:20 UTC 2024),3.12.3,1.44.0,v0.4.0,c9d2ef9648435ef1119950ecb1a0734497ccc33b,,0.13.3,1d2d7160e5b7ec9954ecb48988f71eb56288dd29, +agentlabtraces,GenericAgent-meta-llama_llama-4-maverick,workarena_l1,0.4.1,2025-04-14_17-15-56,a6dc4022-2bb7-4b46-8b37-f62c010defc1,0.27,0.024,0,330/330,None,Linux (#135-Ubuntu SMP Fri Sep 27 13:53:58 UTC 2024),3.12.7,1.39.0,v0.4.0,5eb2ecb5e5b293170230bcbed8b17fe192af214a,,0.13.3,70dac253628c476aff1af6a975f27f8563453ad2, +agentlabtraces,GenericAgent-meta-llama_llama-4-maverick,workarena_l2_agent_curriculum_eval,0.4.1,2025-04-22_15-38-44,d62fed39-caac-4ef3-92ac-b29897c69f88,0.085,0.018,1,235/235,None,Linux (#68-Ubuntu SMP Mon Oct 7 14:34:20 UTC 2024),3.12.7,1.39.0,v0.4.0,43bafbcfbe398fca39e4ffdc57b2f226d2c6d3e1,,0.13.3,70dac253628c476aff1af6a975f27f8563453ad2, +amanjaiswal73892,VisualAgent-qwen_qwen2.5-vl-32b-instruct,miniwob,0.13.4,2025-05-09_23-26-28,06f85422-d89a-4b72-83e7-db53419de107,0.376,0.019,0,625/625,None,Linux (#68-Ubuntu SMP Mon Oct 7 14:34:20 UTC 2024),3.12.8,1.44.0,v0.4.0,bfc68dbfd1a77555b727a7f1816ed393446db59b,,0.13.4,bfc68dbfd1a77555b727a7f1816ed393446db59b, +amanjaiswal73892,GenericAgent-qwen_qwen2.5-vl-32b-instruct,miniwob,0.13.4,2025-05-09_23-26-28,06f85422-d89a-4b72-83e7-db53419de107,0.61,0.02,0,625/625,None,Linux (#68-Ubuntu SMP Mon Oct 7 14:34:20 UTC 2024),3.12.8,1.44.0,v0.4.0,bfc68dbfd1a77555b727a7f1816ed393446db59b,,0.13.4,bfc68dbfd1a77555b727a7f1816ed393446db59b, +amanjaiswal73892,GenericAgent-meta-llama_llama-4-maverick,miniwob,0.13.4,2025-05-09_23-26-28,06f85422-d89a-4b72-83e7-db53419de107,0.613,0.019,0,625/625,None,Linux (#68-Ubuntu SMP Mon Oct 7 14:34:20 UTC 2024),3.12.8,1.44.0,v0.4.0,bfc68dbfd1a77555b727a7f1816ed393446db59b,,0.13.4,bfc68dbfd1a77555b727a7f1816ed393446db59b, +amanjaiswal73892,VisualAgent-som-meta-llama_llama-4-maverick,miniwob,0.13.4,2025-05-08_10-27-21,91f14b21-d32e-467d-a65e-eda0a17dc274,0.29,0.018,0,625/625,None,Darwin (Darwin Kernel Version 24.4.0: Fri Apr 11 18:28:23 PDT 2025; root:xnu-11417.101.15~117/RELEASE_X86_64),3.12.9,1.44.0,v0.4.0,f041e6487ced733149d293dba8afd9f84ceb28df,,0.13.4,f041e6487ced733149d293dba8afd9f84ceb28df, +amanjaiswal73892,VisualAgent-qwen_qwen2.5-vl-32b-instruct,workarena_l1,0.4.1,2025-05-12_14-13-30,d393e506-9b16-4827-8779-09199ca7d9c3,0.061,0.013,6,330/330,None,Linux (#68-Ubuntu SMP Mon Oct 7 14:34:20 UTC 2024),3.12.8,1.44.0,v0.4.0,9a84b804db236e711489e1d137c87540e19d221b,,0.13.4,9a84b804db236e711489e1d137c87540e19d221b, +amanjaiswal73892,GenericAgent-qwen_qwen2.5-vl-32b-instruct,workarena_l1,0.4.1,2025-05-12_18-55-20,eae2f2e6-eff7-434a-a4ae-34eb200f32f6,0.339,0.026,6,330/330,None,Linux (#68-Ubuntu SMP Mon Oct 7 14:34:20 UTC 2024),3.12.8,1.44.0,v0.4.0,9a84b804db236e711489e1d137c87540e19d221b,,0.13.4,9a84b804db236e711489e1d137c87540e19d221b, +amanjaiswal73892,VisualAgent-som-meta-llama_llama-4-maverick,workarena_l1,0.4.1,2025-05-12_23-19-24,7df7f868-7eca-469d-b201-0be4010b263f,0.024,0.008,6,330/330,None,Linux (#68-Ubuntu SMP Mon Oct 7 14:34:20 UTC 2024),3.12.8,1.44.0,v0.4.0,9a84b804db236e711489e1d137c87540e19d221b,,0.13.4,9a84b804db236e711489e1d137c87540e19d221b, diff --git a/src/agentlab/agents/__init__.py b/src/agentlab/agents/__init__.py index 75249df3..4af478eb 100644 --- a/src/agentlab/agents/__init__.py +++ b/src/agentlab/agents/__init__.py @@ -9,5 +9,7 @@ - TapeAgent: An agent that uses the Tape data structure to perform actions +- VisualAgent: An agent that uses visual observations to to perform actions + - VisualWebArenaAgent: An implementation of the agent used in WebArena and VisualWebArena """ diff --git a/src/agentlab/agents/generic_agent/agent_configs.py b/src/agentlab/agents/generic_agent/agent_configs.py index 914e3249..50f4abb0 100644 --- a/src/agentlab/agents/generic_agent/agent_configs.py +++ b/src/agentlab/agents/generic_agent/agent_configs.py @@ -10,7 +10,7 @@ from .generic_agent import GenericAgentArgs from .generic_agent_prompt import GenericPromptFlags -from .tmlr_config import BASE_FLAGS +from .tmlr_config import BASE_FLAGS, get_base_agent FLAGS_CUSTOM = GenericPromptFlags( obs=dp.ObsFlags( @@ -302,6 +302,9 @@ flags=BASE_FLAGS, ) +AGENT_QWEN_2_5_VL_32B = get_base_agent("openrouter/qwen/qwen2.5-vl-32b-instruct") +AGENT_QWEN_3_32B = get_base_agent("openrouter/qwen/qwen3-32b") + DEFAULT_RS_FLAGS = GenericPromptFlags( flag_group="default_rs", obs=dp.ObsFlags( diff --git a/src/agentlab/agents/generic_agent/tmlr_config.py b/src/agentlab/agents/generic_agent/tmlr_config.py index 5a749721..b102a006 100644 --- a/src/agentlab/agents/generic_agent/tmlr_config.py +++ b/src/agentlab/agents/generic_agent/tmlr_config.py @@ -51,6 +51,7 @@ def get_base_agent(llm_config: str): + assert llm_config in CHAT_MODEL_ARGS_DICT, f"Unsupported LLM config: {llm_config}" return GenericAgentArgs( chat_model_args=CHAT_MODEL_ARGS_DICT[llm_config], flags=BASE_FLAGS, diff --git a/src/agentlab/agents/visual_agent/agent_configs.py b/src/agentlab/agents/visual_agent/agent_configs.py index 404afaec..faa92e71 100644 --- a/src/agentlab/agents/visual_agent/agent_configs.py +++ b/src/agentlab/agents/visual_agent/agent_configs.py @@ -42,3 +42,46 @@ chat_model_args=CHAT_MODEL_ARGS_DICT["openrouter/anthropic/claude-3.5-sonnet:beta"], flags=DEFAULT_PROMPT_FLAGS, ) + +VISUAL_AGENT_QWEN_2_5_VL_32B = VisualAgentArgs( + chat_model_args=CHAT_MODEL_ARGS_DICT["openrouter/qwen/qwen2.5-vl-32b-instruct"], + flags=DEFAULT_PROMPT_FLAGS, +) + +def get_som_agent(llm_config: str): + """Creates basic 1-step vision SOM agent""" + assert llm_config in CHAT_MODEL_ARGS_DICT, f"Unsupported LLM config: {llm_config}" + obs_flags = dp.ObsFlags( + use_tabs=True, + use_error_logs=True, + use_past_error_logs=False, + use_screenshot=True, + use_som=True, + openai_vision_detail="auto", + ) + action_flags = dp.ActionFlags( + action_set=bgym.HighLevelActionSetArgs(subsets=["bid"]), + long_description=True, + individual_examples=False, + ) + som_prompt_flags = PromptFlags( + obs=obs_flags, + action=action_flags, + use_thinking=True, + use_concrete_example=False, + use_abstract_example=True, + enable_chat=False, + extra_instructions=None, + ) + + agent_args = VisualAgentArgs( + chat_model_args=CHAT_MODEL_ARGS_DICT[llm_config], + flags=som_prompt_flags, + ) + model_name = agent_args.chat_model_args.model_name + agent_args.agent_name = f"VisualAgent-som-{model_name}".replace("/", "_") + + return agent_args + + +VISUAL_SOM_AGENT_LLAMA4_17B_INSTRUCT = get_som_agent("openrouter/meta-llama/llama-4-maverick") diff --git a/src/agentlab/llm/chat_api.py b/src/agentlab/llm/chat_api.py index 371229b5..cdbc810d 100644 --- a/src/agentlab/llm/chat_api.py +++ b/src/agentlab/llm/chat_api.py @@ -322,12 +322,15 @@ def __call__(self, messages: list[dict], n_samples: int = 1, temperature: float tracking.TRACKER.instance(input_tokens, output_tokens, cost) if n_samples == 1: - res = AIMessage(completion.choices[0].message.content) + res = AIMessage(self.extract_content_with_reasoning(completion.choices[0].message)) if self.log_probs: res["log_probs"] = completion.choices[0].log_probs return res else: - return [AIMessage(c.message.content) for c in completion.choices] + return [ + AIMessage(self.extract_content_with_reasoning(c.message)) + for c in completion.choices + ] def get_stats(self): return { @@ -335,6 +338,19 @@ def get_stats(self): # "busted_retry_llm": int(not self.success), # not logged if it occurs anyways } + # Support for models that return reasoning. + def extract_content_with_reasoning(self, message, wrap_tag="think"): + """Extracts the content from the message, including reasoning if available. + It wraps the reasoning around ... for backward compatibility.""" + + reasoning_content = getattr(message, "reasoning", None) + if reasoning_content: + # Wrap reasoning in tags with newlines for clarity + reasoning_content = f"<{wrap_tag}>\n{reasoning_content}\n\n" + else: + reasoning_content = "" + return f"{reasoning_content}{message.content}" + class OpenAIChatModel(ChatModel): def __init__( diff --git a/src/agentlab/llm/llm_configs.py b/src/agentlab/llm/llm_configs.py index 5125801d..3857e716 100644 --- a/src/agentlab/llm/llm_configs.py +++ b/src/agentlab/llm/llm_configs.py @@ -207,4 +207,20 @@ max_new_tokens=64_000, temperature=1e-1, ), + "openrouter/qwen/qwen2.5-vl-32b-instruct": OpenRouterModelArgs( + model_name="qwen/qwen2.5-vl-32b-instruct", + max_total_tokens=128_000, + max_input_tokens=120_000, + max_new_tokens=8_000, + temperature=1e-1, + vision_support=True, + ), + "openrouter/qwen/qwen3-32b": OpenRouterModelArgs( + model_name="qwen/qwen3-32b", + max_total_tokens=128_000, + max_input_tokens=120_000, + max_new_tokens=8_000, + temperature=1e-1, + vision_support=True, + ), }