{"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/process-ob","entry":"process_ob","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":8,"n_papers_ran":1,"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":2,"n_samples_ran":1,"n_samples_fingerprinted":1,"n_places":8,"n_places_pointer_only":3,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":0,"unverified":1},"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":"2609.00455","paper":"/paper/arxiv-2609-00455","title":"Towards a Belief-Based World Model for LLM Agents","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"WeiminXiong/MPO","path":"envs/alfworld_env.py","file_url":"https://github.com/WeiminXiong/MPO/blob/HEAD/envs/alfworld_env.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":"dfb17eb3e6eaed35","mcp_get_code":{"code_sha256":"dfb17eb3e6eaed35"}},{"arxiv_id":"2505.20732","paper":"/paper/spa-rl-reinforcing-llm-agents-via-stepwise","title":"SPA-RL: Reinforcing LLM Agents via Stepwise Progress Attribution","date":"2025-05-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wanghanlinhenry/spa-rl-agent","path":"eval_agent/envs/alfworld_env.py","file_url":"https://github.com/wanghanlinhenry/spa-rl-agent/blob/HEAD/eval_agent/envs/alfworld_env.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"dfb17eb3e6eaed35","mcp_get_code":{"code_sha256":"dfb17eb3e6eaed35"}},{"arxiv_id":"2410.20749","paper":"/paper/matryoshka-learning-to-drive-black-box-llms","title":"Matryoshka: Learning to Drive Black-Box LLMs with LLMs","date":"2024-10-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lichangh20/Matryoshka","path":"alfworld_generate_data.py","file_url":"https://github.com/lichangh20/Matryoshka/blob/HEAD/alfworld_generate_data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"dfb17eb3e6eaed35","mcp_get_code":{"code_sha256":"dfb17eb3e6eaed35"}},{"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/alfworld_run/run_alfworld.py","file_url":"https://github.com/zjunlp/knowagent/blob/HEAD/Path_Generation/alfworld_run/run_alfworld.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":"dfb17eb3e6eaed35","mcp_get_code":{"code_sha256":"dfb17eb3e6eaed35"}},{"arxiv_id":"2402.16181","paper":"/paper/how-can-llm-guide-rl-a-value-based-approach","title":"How Can LLM Guide RL? A Value-Based Approach","date":"2024-02-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"agentification/language-integrated-vi","path":"alfworld/alfworld_trial_wv.py","file_url":"https://github.com/agentification/language-integrated-vi/blob/HEAD/alfworld/alfworld_trial_wv.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"dfb17eb3e6eaed35","mcp_get_code":{"code_sha256":"dfb17eb3e6eaed35"}},{"arxiv_id":"2311.16714","paper":"/paper/embodied-multi-modal-agent-trained-by-an-llm","title":"Embodied Multi-Modal Agent trained by an LLM from a Parallel TextWorld","date":"2023-11-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"stevenyangyj/emma-alfworld","path":"LAVIS/post_processing.py","file_url":"https://github.com/stevenyangyj/emma-alfworld/blob/HEAD/LAVIS/post_processing.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"dfb17eb3e6eaed35","mcp_get_code":{"code_sha256":"dfb17eb3e6eaed35"}},{"arxiv_id":"2311.05772","paper":"/paper/adapt-as-needed-decomposition-and-planning","title":"ADaPT: As-Needed Decomposition and Planning with Language Models","date":"2023-11-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"archiki/ADaPT","path":"run_alfworld.py","file_url":"https://github.com/archiki/ADaPT/blob/HEAD/run_alfworld.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f2c02b01b0700cef","mcp_get_code":{"code_sha256":"f2c02b01b0700cef"}},{"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":"alfworld_runs/alfworld_trial.py","file_url":"https://github.com/noahshinn/reflexion/blob/HEAD/alfworld_runs/alfworld_trial.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"dfb17eb3e6eaed35","mcp_get_code":{"code_sha256":"dfb17eb3e6eaed35"}}]}