{"work":{"id":"810dbb8b-e954-4797-bf0d-5d8cad94e524","openalex_id":null,"doi":null,"arxiv_id":"2310.04406","raw_key":null,"title":"Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models","authors":null,"authors_text":"Andy Zhou, Kai Yan, Michal Shlapentokh-Rothman, Haohan Wang, Yu-Xiong Wang","year":2023,"venue":"cs.AI","abstract":"While language models (LMs) have shown potential across a range of decision-making tasks, their reliance on simple acting processes limits their broad deployment as autonomous agents. In this paper, we introduce Language Agent Tree Search (LATS) -- the first general framework that synergizes the capabilities of LMs in reasoning, acting, and planning. By leveraging the in-context learning ability of LMs, we integrate Monte Carlo Tree Search into LATS to enable LMs as agents, along with LM-powered value functions and self-reflections for proficient exploration and enhanced decision-making. A key feature of our approach is the incorporation of an environment for external feedback, which offers a more deliberate and adaptive problem-solving mechanism that surpasses the constraints of existing techniques. Our experimental evaluation across diverse domains, including programming, interactive question-answering (QA), web navigation, and math, validates the effectiveness and generality of LATS in decision-making while maintaining competitive or improved reasoning performance. Notably, LATS achieves state-of-the-art pass@1 accuracy (92.7%) for programming on HumanEval with GPT-4 and demonstrates gradient-free performance (average score of 75.9) comparable to gradient-based fine-tuning for web navigation on WebShop with GPT-3.5. Code can be found at https://github.com/lapisrocks/LanguageAgentTreeSearch","external_url":"https://arxiv.org/abs/2310.04406","cited_by_count":null,"metadata_source":"pith","metadata_fetched_at":"2026-05-22T21:42:10.703513+00:00","pith_arxiv_id":"2310.04406","created_at":"2026-05-11T05:15:57.733446+00:00","updated_at":"2026-05-22T21:42:10.703513+00:00","title_quality_ok":true,"display_title":"Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models","render_title":"Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models"},"hub":{"state":{"work_id":"810dbb8b-e954-4797-bf0d-5d8cad94e524","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":28,"external_cited_by_count":null,"distinct_field_count":5,"first_pith_cited_at":"2023-10-03T16:05:48+00:00","last_pith_cited_at":"2026-05-21T14:45:40+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-06-03T22:36:32.501167+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":8},{"context_role":"method","n":1}],"polarity_counts":[{"context_polarity":"background","n":6},{"context_polarity":"support","n":2},{"context_polarity":"use_method","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}