paper-with-me

홈 › Papers

Chain-in-Tree: Back to Sequential Reasoning in LLM Tree Search

2025-09-30 · Xinzhe Li arxiv

Test-time scaling improves large language models (LLMs) on long-horizon reasoning tasks by allocating more compute at inference. LLM inference via tree search (LITS) achieves strong performance but is highly inefficient. We propose Chain-in-Tree (CiT), a plug-in framework that decides when to branch during search instead of expanding at every step. CiT introduces lightweight Branching Necessity (BN) evaluations, including BN-DP (direct prompting) and BN-SC (self-consistency). Integrated into Tree of Thoughts, ReST-MCTS, and RAP, BN-DP reduces token generation, model calls, and runtime by 75-85% on GSM8K and Math500, with often negligible or no accuracy loss. BN-SC typically yields substantial savings (up to 80%) generally but shows instability in 1-4 out of 14 settings, caused by a small subset of examples that produce extremely long reasoning steps. We theoretically prove that BN-DP never increases policy invocations and release unified implementations applicable across LITS frameworks. The full codebase is publicly available at https://github.com/xinzhel/chain_in_tree.

📄 PDF Abstract BibTeX arXiv:2509.25835

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Probabilistic Tree-of-thought Reasoning for Answering Knowledge-intensive Complex Questions

2023-11-23 · Shulin Cao, Jiajie Zhang, Jiaxin Shi, Xin Lv 외

Large language models (LLMs) are capable of answering knowledge-intensive complex questions with chain-of-thought (CoT) reasoning. However, they tend to generate factually incorrect reasoning steps when the required know…

Retrieval

Reason in Chains, Learn in Trees: Self-Rectification and Grafting for Multi-turn Agent Policy Optimization

2026-04-08 · Yu Li, Sizhe Tang, Tian Lan arxiv

Reinforcement learning for Large Language Model agents is often hindered by sparse rewards in multi-step reasoning tasks. Existing approaches like Group Relative Policy Optimization treat sampled trajectories as independ…

Reinforcement Learning

From Chain to Tree: Refining Chain-like Rules into Tree-like Rules on Knowledge Graphs

2024-03-08 · Wangtao Sun, Shizhu He, Jun Zhao, Kang Liu

With good explanatory power and controllability, rule-based methods play an important role in many tasks such as knowledge reasoning and decision support. However, existing studies primarily focused on learning chain-lik…

Knowledge GraphsLink Prediction

Breaking Chains with Trees: Model-Parallel Deep Learning with $\mathcal{O}(\log N)$ Time Complexity

2026-06-19 · Neeraj Mohan Sushma, Aditya Nagarsekar, Cabrel Teguemne Fokam, Robin Schiewer 외 arxiv

Modern deep neural networks are trained using error backpropagation, which requires sequential forward and backward computations across network layers. As these networks become deeper, this introduces limitations, since …

Chow-Liu Ordering for Long-Context Reasoning in Chain-of-Agents

2026-03-10 · Naman Gupta, Vaibhav Singh, Arun Iyer, Kirankumar Shiragur 외 arxiv

Sequential multi-agent reasoning frameworks such as Chain-of-Agents (CoA) handle long-context queries by decomposing inputs into chunks and processing them sequentially using LLM-based worker agents that read from and up…