{"id":"openreview:wUU-7XTL5XO","title":"PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Change","date":"2022-06-21","section":"Reasoning and the \"physics\" of language models","quality":-0.296417,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/da39c89a33c7acabf5f152b7d25c596a91b3b44bb2dec90057cd739273338425/","source_url":"https://openreview.net/forum?id=wUU-7XTL5XO","text_available":true,"authors":["Karthik Valmeekam","Matthew Marquez","Alberto Olmo","Sarath Sreedharan"],"outgoing":[],"incoming":[{"source":"arxiv:2402.01817","target":"openreview:wUU-7XTL5XO","evidence":"title","id":"arxiv:2402.01817","title":"LLMs Can't Plan, But Can Help Planning in LLM-Modulo Frameworks","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/d4b5a3d7cb6b8ad1768f1c0a91042bc53b290daaf00e9972dff5b384f5996db3/"}],"text_parts":[{"start":0,"end":14895,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/da39c89a33c7acabf5f152b7d25c596a91b3b44bb2dec90057cd739273338425/part-1.html"},{"start":14895,"end":26756,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/da39c89a33c7acabf5f152b7d25c596a91b3b44bb2dec90057cd739273338425/part-2.html"},{"start":26756,"end":39282,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/da39c89a33c7acabf5f152b7d25c596a91b3b44bb2dec90057cd739273338425/part-3.html"},{"start":39282,"end":53953,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/da39c89a33c7acabf5f152b7d25c596a91b3b44bb2dec90057cd739273338425/part-4.html"},{"start":53953,"end":65882,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/da39c89a33c7acabf5f152b7d25c596a91b3b44bb2dec90057cd739273338425/part-5.html"}],"contents":[],"text_code_points":65882,"source_markdown":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/da39c89a33c7acabf5f152b7d25c596a91b3b44bb2dec90057cd739273338425/source.md"}