{"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/llm","entry":"LLM","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":11,"n_papers_ran":5,"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":11,"n_samples_ran":5,"n_samples_fingerprinted":0,"n_places":11,"n_places_pointer_only":6,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":5,"unverified":6},"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":"2605.28079","paper":"/paper/arxiv-2605-28079","title":"ATLAS: All-round Testing of Long-context Abilities across Scales","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"princeton-nlp/HELMET","path":"model_utils.py","file_url":"https://github.com/princeton-nlp/HELMET/blob/HEAD/model_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"49c91caa4809ddb1","mcp_get_code":{"code_sha256":"49c91caa4809ddb1"}},{"arxiv_id":"2602.11182","paper":"/paper/arxiv-2602-11182","title":"MetaMem: Evolving Meta-Memory for Knowledge Utilization through Self-Reflective Symbolic Optimization","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"OpenBMB/MetaMem","path":"src/train_metamem.py","file_url":"https://github.com/OpenBMB/MetaMem/blob/HEAD/src/train_metamem.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":"52abd86631ab59aa","mcp_get_code":{"code_sha256":"52abd86631ab59aa"}},{"arxiv_id":"2601.06487","paper":"/paper/arxiv-2601-06487","title":"ArenaRL: Scaling RL for Open-Ended Agents via Tournamentbased Relative Ranking","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"Alibaba-NLP/qqr","path":"qqr/reward_models/arena/double_elimination.py","file_url":"https://github.com/Alibaba-NLP/qqr/blob/HEAD/qqr/reward_models/arena/double_elimination.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":"f6e4a304659ffd5c","mcp_get_code":{"code_sha256":"f6e4a304659ffd5c"}},{"arxiv_id":"2510.08445","paper":"/paper/arxiv-2510-08445","title":"Synthetic Series-Symbol Data Generation for Time Series Foundation Models","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"wwhenxuan/SymTime","path":"models/pretrain_model.py","file_url":"https://github.com/wwhenxuan/SymTime/blob/HEAD/models/pretrain_model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"43a8088d7f81189c","mcp_get_code":{"code_sha256":"43a8088d7f81189c"}},{"arxiv_id":"2507.22606","paper":null,"title":"arXiv:2507.22606","date":null,"month_inferred_from_arxiv_id":"2025-07","title_source":null,"repo":"SaFoLab-WISC/MetaAgent","path":"baseclass/FSM_Gen.py","file_url":"https://github.com/SaFoLab-WISC/MetaAgent/blob/HEAD/baseclass/FSM_Gen.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"57b19d5a35592f8d","mcp_get_code":{"code_sha256":"57b19d5a35592f8d"}},{"arxiv_id":"2501.00830","paper":"/paper/llm-al-bridging-large-language-models-and","title":"LLM+AL: Bridging Large Language Models and Action Languages for Complex Reasoning about Actions","date":"2025-01-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"azreasoners/llm-al","path":"utils.py","file_url":"https://github.com/azreasoners/llm-al/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"15771455409e6f78","mcp_get_code":{"code_sha256":"15771455409e6f78"}},{"arxiv_id":"2411.01796","paper":"/paper/constrained-human-ai-cooperation-an-inclusive","title":"Constrained Human-AI Cooperation: An Inclusive Embodied Social Intelligence Challenge","date":"2024-11-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"umass-foundation-model/chaic","path":"LM_agent/LLM.py","file_url":"https://github.com/umass-foundation-model/chaic/blob/HEAD/LM_agent/LLM.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"62c72be98d3cf53f","mcp_get_code":{"code_sha256":"62c72be98d3cf53f"}},{"arxiv_id":"2406.07232","paper":"/paper/dual-reflect-enhancing-large-language-models","title":"DUAL-REFLECT: Enhancing Large Language Models for Reflective Translation through Dual Learning Feedback Mechanisms","date":"2024-06-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"loulianzhang/dual-reflect","path":"alpaca/dual_reflection.py","file_url":"https://github.com/loulianzhang/dual-reflect/blob/HEAD/alpaca/dual_reflection.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"98dbe9aa9001ea6e","mcp_get_code":{"code_sha256":"98dbe9aa9001ea6e"}},{"arxiv_id":"2402.17574","paper":"/paper/agent-pro-learning-to-evolve-via-policy-level","title":"Agent-Pro: Learning to Evolve via Policy-Level Reflection and Optimization","date":"2024-02-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zwq2018/agent-pro","path":"agentpro/LimitTexasHoldem/LimittexasholdemAgent.py","file_url":"https://github.com/zwq2018/agent-pro/blob/HEAD/agentpro/LimitTexasHoldem/LimittexasholdemAgent.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"86c65468a54e7486","mcp_get_code":{"code_sha256":"86c65468a54e7486"}},{"arxiv_id":"2402.10466","paper":"/paper/large-language-models-as-zero-shot-dialogue","title":"Large Language Models as Zero-shot Dialogue State Tracker through Function Calling","date":"2024-02-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/FnCTOD","path":"chatbots/llm.py","file_url":"https://github.com/facebookresearch/FnCTOD/blob/HEAD/chatbots/llm.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"5ab842ef17be865e","mcp_get_code":{"code_sha256":"5ab842ef17be865e"}},{"arxiv_id":"2306.12509","paper":"/paper/deep-language-networks-joint-prompt-training","title":"Joint Prompt Optimization of Stacked LLMs using Variational Inference","date":"2023-06-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/deep-language-networks","path":"dln/vi/model.py","file_url":"https://github.com/microsoft/deep-language-networks/blob/HEAD/dln/vi/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"58142a168b50bfe8","mcp_get_code":{"code_sha256":"58142a168b50bfe8"}}]}