{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/code/parse-action","entry":"parse_action","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":33,"n_papers_ran":22,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":27,"n_samples_ran":17,"n_samples_fingerprinted":11,"n_places":38,"n_places_pointer_only":8,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":3,"ran_fixture":0,"ran":14,"unverified":10},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2605.05802","paper":"/paper/arxiv-2605-05802","title":"Selective Rollout: Mid-Trajectory Termination for Multi-Sample Agent RL","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"zhiyuanZhai20/selective-rollout","path":"src/prompts.py","file_url":"https://github.com/zhiyuanZhai20/selective-rollout/blob/HEAD/src/prompts.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"17942fd27330ceb9","mcp_get_code":{"code_sha256":"17942fd27330ceb9"}},{"arxiv_id":"2604.06182","paper":"/paper/arxiv-2604-06182","title":"VenusBench-Mobile: A Challenging and User-Centric Benchmark for Mobile GUI Agents with Capability Diagnostics","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"inclusionAI/UI-Venus","path":"models/browser/venus_browser.py","file_url":"https://github.com/inclusionAI/UI-Venus/blob/HEAD/models/browser/venus_browser.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"df341ba22d2a7a95","mcp_get_code":{"code_sha256":"df341ba22d2a7a95"}},{"arxiv_id":"2510.00307","paper":"/paper/arxiv-2510-00307","title":"BiasBusters: Uncovering and Mitigating Tool Selection Bias in Large Language Models","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"thierry123454/tool-selection-bias","path":"5_bias_investigation/continued_pretraining/plot_compare_base_vs_adapted.py","file_url":"https://github.com/thierry123454/tool-selection-bias/blob/HEAD/5_bias_investigation/continued_pretraining/plot_compare_base_vs_adapted.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"98bbe08b08d7a02b","mcp_get_code":{"code_sha256":"98bbe08b08d7a02b"}},{"arxiv_id":"2505.21936","paper":"/paper/redteamcua-realistic-adversarial-testing-of","title":"RedTeamCUA: Realistic Adversarial Testing of Computer-Use Agents in Hybrid Web-OS Environments","date":"2025-05-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"osu-nlp-group/redteamcua","path":"mm_agents/uitars_agent.py","file_url":"https://github.com/osu-nlp-group/redteamcua/blob/HEAD/mm_agents/uitars_agent.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"c242cf8145d74b19","mcp_get_code":{"code_sha256":"c242cf8145d74b19"}},{"arxiv_id":"2505.16421","paper":"/paper/webagent-r1-training-web-agents-via-end-to","title":"WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning","date":"2025-05-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"weizhepei/webagent-r1","path":"WebAgent-R1/Eval/browser_env/envs.py","file_url":"https://github.com/weizhepei/webagent-r1/blob/HEAD/WebAgent-R1/Eval/browser_env/envs.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"1829c408a278c974","mcp_get_code":{"code_sha256":"1829c408a278c974"}},{"arxiv_id":"2505.16282","paper":"/paper/arpo-end-to-end-policy-optimization-for-gui","title":"ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay","date":"2025-05-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dvlab-research/arpo","path":"verl/trainer/gui_agent.py","file_url":"https://github.com/dvlab-research/arpo/blob/HEAD/verl/trainer/gui_agent.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"c242cf8145d74b19","mcp_get_code":{"code_sha256":"c242cf8145d74b19"}},{"arxiv_id":"2505.03792","paper":null,"title":"arXiv:2505.03792","date":null,"month_inferred_from_arxiv_id":"2025-05","title_source":null,"repo":"langfengQ/CoSo","path":"digirl/algorithms/causal_digirl/trainer.py","file_url":"https://github.com/langfengQ/CoSo/blob/HEAD/digirl/algorithms/causal_digirl/trainer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"fcc406534c37c490","mcp_get_code":{"code_sha256":"fcc406534c37c490"}},{"arxiv_id":"2501.12326","paper":"/paper/ui-tars-pioneering-automated-gui-interaction","title":"UI-TARS: Pioneering Automated GUI Interaction with Native Agents","date":"2025-01-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bytedance/ui-tars","path":"codes/ui_tars/action_parser.py","file_url":"https://github.com/bytedance/ui-tars/blob/HEAD/codes/ui_tars/action_parser.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"c242cf8145d74b19","mcp_get_code":{"code_sha256":"c242cf8145d74b19"}},{"arxiv_id":"2411.05990","paper":"/paper/game-theoretic-llm-agent-workflow-for","title":"Game-theoretic LLM: Agent Workflow for Negotiation Games","date":"2024-11-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wenyueh/game_theory","path":"src/sequential_game_agent.py","file_url":"https://github.com/wenyueh/game_theory/blob/HEAD/src/sequential_game_agent.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"24b0c7cadb707386","mcp_get_code":{"code_sha256":"24b0c7cadb707386"}},{"arxiv_id":"2410.06617","paper":"/paper/learning-evolving-tools-for-large-language","title":"Learning Evolving Tools for Large Language Models","date":"2024-10-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Chen-GX/ToolEVO","path":"MCTS/src/toolqa.py","file_url":"https://github.com/Chen-GX/ToolEVO/blob/HEAD/MCTS/src/toolqa.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"53f099b3ef83420f","mcp_get_code":{"code_sha256":"53f099b3ef83420f"}},{"arxiv_id":"2410.02907","paper":"/paper/nnetscape-navigator-complex-demonstrations","title":"NNetscape Navigator: Complex Demonstrations for Web Agents Without a Demonstrator","date":"2024-10-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MurtyShikhar/NNetnav","path":"src/postprocess_trajectories_agentlab.py","file_url":"https://github.com/MurtyShikhar/NNetnav/blob/HEAD/src/postprocess_trajectories_agentlab.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"1e0ac88be6fda037","mcp_get_code":{"code_sha256":"1e0ac88be6fda037"}},{"arxiv_id":"2410.02730","paper":"/paper/divscene-benchmarking-lvlms-for-object","title":"DivScene: Benchmarking LVLMs for Object Navigation with Diverse Scenes and Objects","date":"2024-10-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhaowei-wang-nlp/divscene","path":"agent_inference/hf_idefics2_gpt4o.py","file_url":"https://github.com/zhaowei-wang-nlp/divscene/blob/HEAD/agent_inference/hf_idefics2_gpt4o.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b6552010f6d8a287","mcp_get_code":{"code_sha256":"b6552010f6d8a287"}},{"arxiv_id":"2410.02730","paper":"/paper/divscene-benchmarking-lvlms-for-object","title":"DivScene: Benchmarking LVLMs for Object Navigation with Diverse Scenes and Objects","date":"2024-10-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhaowei-wang-nlp/divscene","path":"agent_inference/hf_idefics2_online_client.py","file_url":"https://github.com/zhaowei-wang-nlp/divscene/blob/HEAD/agent_inference/hf_idefics2_online_client.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7a16f1f9f950f857","mcp_get_code":{"code_sha256":"7a16f1f9f950f857"}},{"arxiv_id":"2410.02730","paper":"/paper/divscene-benchmarking-lvlms-for-object","title":"DivScene: Benchmarking LVLMs for Object Navigation with Diverse Scenes and Objects","date":"2024-10-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhaowei-wang-nlp/divscene","path":"agent_inference/hf_idefics2_server.py","file_url":"https://github.com/zhaowei-wang-nlp/divscene/blob/HEAD/agent_inference/hf_idefics2_server.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a24d87222eb1a622","mcp_get_code":{"code_sha256":"a24d87222eb1a622"}},{"arxiv_id":"2409.18073","paper":"/paper/infer-human-s-intentions-before-following","title":"Infer Human's Intentions Before Following Natural Language Instructions","date":"2024-09-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"simon-wan/fiser","path":"dataloaders/data_utils.py","file_url":"https://github.com/simon-wan/fiser/blob/HEAD/dataloaders/data_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"7a7525f5ae8ab255","mcp_get_code":{"code_sha256":"7a7525f5ae8ab255"}},{"arxiv_id":"2407.01476","paper":"/paper/tree-search-for-language-model-agents","title":"Tree Search for Language Model Agents","date":"2024-07-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kohjingyu/search-agents","path":"browser_env/envs.py","file_url":"https://github.com/kohjingyu/search-agents/blob/HEAD/browser_env/envs.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1829c408a278c974","mcp_get_code":{"code_sha256":"1829c408a278c974"}},{"arxiv_id":"2406.12639","paper":"/paper/ask-before-plan-proactive-language-agents-for","title":"Ask-before-Plan: Proactive Language Agents for Real-World Planning","date":"2024-06-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"magicgh/ask-before-plan","path":"common/chat.py","file_url":"https://github.com/magicgh/ask-before-plan/blob/HEAD/common/chat.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4be69b5d38ffb46e","mcp_get_code":{"code_sha256":"4be69b5d38ffb46e"}},{"arxiv_id":"2405.19793","paper":"/paper/pddlego-iterative-planning-in-textual","title":"PDDLEGO: Iterative Planning in Textual Environments","date":"2024-05-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zharry29/nl-to-pddl","path":"source/pddl_evaluation/src/compare_plan.py","file_url":"https://github.com/zharry29/nl-to-pddl/blob/HEAD/source/pddl_evaluation/src/compare_plan.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9fc0305b3d6abb02","mcp_get_code":{"code_sha256":"9fc0305b3d6abb02"}},{"arxiv_id":"2405.00823","paper":"/paper/workbench-a-benchmark-dataset-for-agents-in-a","title":"WorkBench: a Benchmark Dataset for Agents in a Realistic Workplace Setting","date":"2024-05-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"olly-styles/workbench","path":"src/evals/agent.py","file_url":"https://github.com/olly-styles/workbench/blob/HEAD/src/evals/agent.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a3db7ab2f37601d6","mcp_get_code":{"code_sha256":"a3db7ab2f37601d6"}},{"arxiv_id":"2403.03101","paper":"/paper/knowagent-knowledge-augmented-planning-for","title":"KnowAgent: Knowledge-Augmented Planning for LLM-Based Agents","date":"2024-03-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zjunlp/knowagent","path":"Path_Generation/hotpotqa_run/agent_arch.py","file_url":"https://github.com/zjunlp/knowagent/blob/HEAD/Path_Generation/hotpotqa_run/agent_arch.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9f8148d447f9ea0c","mcp_get_code":{"code_sha256":"9f8148d447f9ea0c"}},{"arxiv_id":"2403.00843","paper":"/paper/enhancing-long-term-recommendation-with-bi","title":"Large Language Models are Learnable Planners for Long-Term Recommendation","date":"2024-02-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jizhi-zhang/billp","path":"Agents/agent_base.py","file_url":"https://github.com/jizhi-zhang/billp/blob/HEAD/Agents/agent_base.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"215250417118aa19","mcp_get_code":{"code_sha256":"215250417118aa19"}},{"arxiv_id":"2402.15538","paper":"/paper/agentlite-a-lightweight-library-for-building","title":"AgentLite: A Lightweight Library for Building and Advancing Task-Oriented LLM Agent System","date":"2024-02-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"salesforceairesearch/agentlite","path":"agentlite/agents/agent_utils.py","file_url":"https://github.com/salesforceairesearch/agentlite/blob/HEAD/agentlite/agents/agent_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8cbdbfe07b3e0678","mcp_get_code":{"code_sha256":"8cbdbfe07b3e0678"}},{"arxiv_id":"2402.14963","paper":"/paper/mirror-a-multiple-perspective-self-reflection","title":"Mirror: A Multiple-perspective Self-Reflection Method for Knowledge-rich Reasoning","date":"2024-02-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hanqi-qi/mirror","path":"agents_module.py","file_url":"https://github.com/hanqi-qi/mirror/blob/HEAD/agents_module.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a236bd96b70f98f1","mcp_get_code":{"code_sha256":"a236bd96b70f98f1"}},{"arxiv_id":"2402.11208","paper":"/paper/watch-out-for-your-agents-investigating","title":"Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents","date":"2024-02-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lancopku/agent-backdoor-attacks","path":"AgentTuning/AgentTuning/AgentBench.old/src/tasks/webshop/web_agent_site/engine/engine.py","file_url":"https://github.com/lancopku/agent-backdoor-attacks/blob/HEAD/AgentTuning/AgentTuning/AgentBench.old/src/tasks/webshop/web_agent_site/engine/engine.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f482598cf447f335","mcp_get_code":{"code_sha256":"f482598cf447f335"}},{"arxiv_id":"2402.01622","paper":"/paper/travelplanner-a-benchmark-for-real-world","title":"TravelPlanner: A Benchmark for Real-World Planning with Language Agents","date":"2024-02-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"llv22/travelplanner_forward","path":"agents/tool_agents.py","file_url":"https://github.com/llv22/travelplanner_forward/blob/HEAD/agents/tool_agents.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"744db5623472fa82","mcp_get_code":{"code_sha256":"744db5623472fa82"}},{"arxiv_id":"2401.13649","paper":"/paper/visualwebarena-evaluating-multimodal-agents","title":"VisualWebArena: Evaluating Multimodal Agents on Realistic Visual Web Tasks","date":"2024-01-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"web-arena-x/visualwebarena","path":"browser_env/envs.py","file_url":"https://github.com/web-arena-x/visualwebarena/blob/HEAD/browser_env/envs.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1829c408a278c974","mcp_get_code":{"code_sha256":"1829c408a278c974"}},{"arxiv_id":"2401.05268","paper":"/paper/autoact-automatic-agent-learning-from-scratch","title":"AutoAct: Automatic Agent Learning from Scratch for QA via Self-Planning","date":"2024-01-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zjunlp/autoact","path":"Self_Plan/Group_Planning/benchmark_run/Meta_agent_arch.py","file_url":"https://github.com/zjunlp/autoact/blob/HEAD/Self_Plan/Group_Planning/benchmark_run/Meta_agent_arch.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9f8148d447f9ea0c","mcp_get_code":{"code_sha256":"9f8148d447f9ea0c"}},{"arxiv_id":"2309.08172","paper":"/paper/laser-llm-agent-with-state-space-exploration","title":"LASER: LLM Agent with State-Space Exploration for Web Navigation","date":"2023-09-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mayer123/laser","path":"web_agent_site/engine/engine.py","file_url":"https://github.com/mayer123/laser/blob/HEAD/web_agent_site/engine/engine.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"f482598cf447f335","mcp_get_code":{"code_sha256":"f482598cf447f335"}},{"arxiv_id":"2308.05960","paper":"/paper/bolaa-benchmarking-and-orchestrating-llm","title":"BOLAA: Benchmarking and Orchestrating LLM-augmented Autonomous Agents","date":"2023-08-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"salesforce/bolaa","path":"hotpotqa_run/agent_arch.py","file_url":"https://github.com/salesforce/bolaa/blob/HEAD/hotpotqa_run/agent_arch.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9f8148d447f9ea0c","mcp_get_code":{"code_sha256":"9f8148d447f9ea0c"}},{"arxiv_id":"2307.13854","paper":"/paper/webarena-a-realistic-web-environment-for","title":"WebArena: A Realistic Web Environment for Building Autonomous Agents","date":"2023-07-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"web-arena-x/webarena","path":"browser_env/envs.py","file_url":"https://github.com/web-arena-x/webarena/blob/HEAD/browser_env/envs.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"1829c408a278c974","mcp_get_code":{"code_sha256":"1829c408a278c974"}},{"arxiv_id":"2306.13304","paper":"/paper/toolqa-a-dataset-for-llm-question-answering-1","title":"ToolQA: A Dataset for LLM Question Answering with External Tools","date":"2023-06-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"night-chen/toolqa","path":"benchmark/chameleon/run_toolqa/run-v2.py","file_url":"https://github.com/night-chen/toolqa/blob/HEAD/benchmark/chameleon/run_toolqa/run-v2.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"f71b690030237706","mcp_get_code":{"code_sha256":"f71b690030237706"}},{"arxiv_id":"2306.13304","paper":"/paper/toolqa-a-dataset-for-llm-question-answering-1","title":"ToolQA: A Dataset for LLM Question Answering with External Tools","date":"2023-06-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"night-chen/toolqa","path":"benchmark/ReAct/code/agents.py","file_url":"https://github.com/night-chen/toolqa/blob/HEAD/benchmark/ReAct/code/agents.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"0cd0094dec049291","mcp_get_code":{"code_sha256":"0cd0094dec049291"}},{"arxiv_id":"2306.13304","paper":"/paper/toolqa-a-dataset-for-llm-question-answering-1","title":"ToolQA: A Dataset for LLM Question Answering with External Tools","date":"2023-06-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"night-chen/toolqa","path":"benchmark/ReAct/code/environment.py","file_url":"https://github.com/night-chen/toolqa/blob/HEAD/benchmark/ReAct/code/environment.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"23aab7577a21a4cf","mcp_get_code":{"code_sha256":"23aab7577a21a4cf"}},{"arxiv_id":"2305.14257","paper":"/paper/hierarchical-prompting-assists-large-language","title":"Hierarchical Prompting Assists Large Language Model on Web Navigation","date":"2023-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"oootttyyy/webarena","path":"browser_env/envs.py","file_url":"https://github.com/oootttyyy/webarena/blob/HEAD/browser_env/envs.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"1829c408a278c974","mcp_get_code":{"code_sha256":"1829c408a278c974"}},{"arxiv_id":"2303.11366","paper":"/paper/reflexion-language-agents-with-verbal","title":"Reflexion: Language Agents with Verbal Reinforcement Learning","date":"2023-03-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"noahshinn/reflexion","path":"hotpotqa_runs/agents.py","file_url":"https://github.com/noahshinn/reflexion/blob/HEAD/hotpotqa_runs/agents.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0cd0094dec049291","mcp_get_code":{"code_sha256":"0cd0094dec049291"}},{"arxiv_id":"2303.11366","paper":"/paper/reflexion-language-agents-with-verbal","title":"Reflexion: Language Agents with Verbal Reinforcement Learning","date":"2023-03-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"noahshinn/reflexion","path":"hotpotqa_runs/environment.py","file_url":"https://github.com/noahshinn/reflexion/blob/HEAD/hotpotqa_runs/environment.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"23aab7577a21a4cf","mcp_get_code":{"code_sha256":"23aab7577a21a4cf"}},{"arxiv_id":"openreview_krRRnq3E1w","paper":null,"title":"arXiv:openreview_krRRnq3E1w","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"zhangSchnee/BoG","path":"bog/actions.py","file_url":"https://github.com/zhangSchnee/BoG/blob/HEAD/bog/actions.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"5383ad4e44568f23","mcp_get_code":{"code_sha256":"5383ad4e44568f23"}},{"arxiv_id":"openreview_9aU4vrHPKD","paper":null,"title":"arXiv:openreview_9aU4vrHPKD","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"Octobrist/CoPE","path":"src/world/extract_plan_from_golden.py","file_url":"https://github.com/Octobrist/CoPE/blob/HEAD/src/world/extract_plan_from_golden.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"cea54f4f2666afeb","mcp_get_code":{"code_sha256":"cea54f4f2666afeb"}}]}