{"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":"/paper/don-t-get-lost-in-the-trees-streamlining-llm","title":"Don't Get Lost in the Trees: Streamlining LLM Reasoning by Overcoming Tree Search Exploration Pitfalls","arxiv_id":"2502.11183","date":"2025-02-16","proceeding":null,"authors":["Ante Wang","Linfeng Song","Ye Tian","Dian Yu","Haitao Mi","Xiangyu Duan","Zhaopeng Tu","Jinsong Su","Dong Yu"],"abstract":"Recent advancements in tree search algorithms guided by verifiers have significantly enhanced the reasoning capabilities of large language models (LLMs), but at the cost of increased computational resources. In this work, we identify two key challenges contributing to this inefficiency: $\\textit{over-exploration}$ due to redundant states with semantically equivalent content, and $\\textit{under-exploration}$ caused by high variance in verifier scoring leading to frequent trajectory switching. To address these issues, we propose FETCH, an e$\\textbf{f}$fici$\\textbf{e}$nt $\\textbf{t}$ree sear$\\textbf{ch}$ framework, which is a flexible, plug-and-play system compatible with various tree search algorithms. Our framework mitigates over-exploration by merging semantically similar states using agglomerative clustering of text embeddings obtained from a fine-tuned SimCSE model. To tackle under-exploration, we enhance verifiers by incorporating temporal difference learning with adjusted $\\lambda$-returns during training to reduce variance, and employing a verifier ensemble to aggregate scores during inference. Experiments on GSM8K, GSM-Plus, and MATH datasets demonstrate that our methods significantly improve reasoning accuracy and computational efficiency across four different tree search algorithms, paving the way for more practical applications of LLM-based reasoning. The code is available at https://github.com/Soistesimmer/Fetch.","url_abs":"https://arxiv.org/abs/2502.11183v2","url_pdf":"https://arxiv.org/pdf/2502.11183v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"don-t-get-lost-in-the-trees-streamlining-llm","repo_url":"https://github.com/soistesimmer/fetch","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"gsm8k","task_name":"GSM8K"},{"task_slug":"math","task_name":"Math"}],"methods":[{"method_slug":"simcse","method_name":"SimCSE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2502.11183","atlas_url":"https://app.syntology.ai/?focus=2502.11183","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.11183"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/DeepLearnXMU/Fetch","reach":null}],"summary":{"ran":1},"by_repo_kind":{"found_in_text":{"samples":1,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"79b461376800c855","entry":"VirtualMCTSNode","repo":"DeepLearnXMU/Fetch","repo_kind":"found_in_text","path":"search/mcts/mcts_tree_merge.py","file_url":"https://github.com/DeepLearnXMU/Fetch/blob/HEAD/search/mcts/mcts_tree_merge.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"79b461376800c855"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}