{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T03:05:33Z","timestamp":1773803133878,"version":"3.50.1"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"28","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"<jats:p>Reinforcement learning (RL) has emerged as the predominant paradigm for training large language model (LLM) agents to solve complex, multi-step tasks through environmental interaction. A fundamental challenge in such long-horizon scenarios is credit assignment, as delayed rewards provide inadequate signals for evaluating individual action contributions. \nExisting methods typically neglect trajectory transition dynamics, which leads to coarse-grained or biased credit assignment.\nTo address these limitations, we introduce SHADOW, a novel framework that systematically incorporates transition dynamics for improved credit assignment. Our framework makes two primary contributions: (i) a dynamics-aware state grouping mechanism that mitigates misleading action comparisons between dynamically inconsistent states, and (ii) a local dynamic advantage estimator that leverages Generalized Advantage Estimation (GAE) to precisely quantify individual action contributions through a fine-grained analysis of transition patterns. \nComprehensive experiments conducted with the Qwen2.5-1.5\/7B-Instruct agent model demonstrate that our method achieves success rate improvements of 9.4%\/7.6% on the ALFworld benchmark and a performance gain of over 5% on WebShop.<\/jats:p>","DOI":"10.1609\/aaai.v40i28.39570","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T01:39:01Z","timestamp":1773797941000},"page":"23935-23944","source":"Crossref","is-referenced-by-count":0,"title":["SHADOW: Dynamic-Aware Credit Assignment Against Long-Horizon Tasks"],"prefix":"10.1609","volume":"40","author":[{"given":"Yuze","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chaochao","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chao","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"9382","published-online":{"date-parts":[[2026,3,14]]},"container-title":["Proceedings of the AAAI Conference on Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/39570\/43531","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/39570\/43531","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T01:39:02Z","timestamp":1773797942000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/39570"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,14]]},"references-count":0,"journal-issue":{"issue":"28","published-online":{"date-parts":[[2026,3,17]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v40i28.39570","relation":{},"ISSN":["2374-3468","2159-5399"],"issn-type":[{"value":"2374-3468","type":"electronic"},{"value":"2159-5399","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3,14]]}}}