{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T03:44:02Z","timestamp":1758080642498,"version":"3.44.0"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["ICAPS"],"abstract":"<jats:p>The capability of Large Language Models (LLMs) to plan remains a topic of debate. Some critics argue that strategies to boost LLMs' reasoning skills are ineffective in planning tasks, while others report strong outcomes merely from training models on a planning corpus. This paper revisits these claims by developing an end-to-end LLM-based planner and evaluating a range of reasoning-enhancement strategies --- including fine-tuning, Chain-of-Thought (CoT) prompting, and reinforcement learning (RL) --- across multiple dimensions of plan quality: validity, executability, goal satisfiability, and more. Our findings reveal fine-tuning alone is insufficient, especially on out-of-distribution tasks. Strategies like CoT prompting primarily enhance local coherence, yielding higher executability rates --- a necessary prerequisite for validity --- but provide only incremental gains and struggle to ensure global plan validity. Notably, RL guided by a novel Longest Contiguous Common Subsequence reward significantly enhances both executability and validity, particularly on longer-horizon problems. Overall, our research addresses key misconceptions in the LLM-planning literature and underscores reward-driven RL optimization as a promising direction for advancing robust LLM-based planning by jointly improving executability and validity.<\/jats:p>","DOI":"10.1609\/icaps.v35i1.36119","type":"journal-article","created":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T22:28:00Z","timestamp":1758061680000},"page":"204-212","source":"Crossref","is-referenced-by-count":0,"title":["Chasing Progress, Not Perfection: Revisiting Strategies for End-to-End LLM Plan Generation"],"prefix":"10.1609","volume":"35","author":[{"given":"Sukai","family":"Huang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Trevor","family":"Cohn","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nir","family":"Lipovetzky","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"9382","published-online":{"date-parts":[[2025,9,16]]},"container-title":["Proceedings of the International Conference on Automated Planning and Scheduling"],"original-title":[],"link":[{"URL":"https:\/\/ojs.aaai.org\/index.php\/ICAPS\/article\/download\/36119\/38273","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/ICAPS\/article\/download\/36119\/38273","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T22:28:01Z","timestamp":1758061681000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/ICAPS\/article\/view\/36119"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,16]]},"references-count":0,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,9,16]]}},"URL":"https:\/\/doi.org\/10.1609\/icaps.v35i1.36119","relation":{},"ISSN":["2334-0843","2334-0835"],"issn-type":[{"value":"2334-0843","type":"electronic"},{"value":"2334-0835","type":"print"}],"subject":[],"published":{"date-parts":[[2025,9,16]]}}}