PRISM-MCTS: Learning from Reasoning Trajectories with Metacognitive Reflection
PRISM-MCTS: Learning from Reasoning Trajectories with Metacognitive Reflection Siyuan Cheng, Bozhong Tian, Yanchao Hao, Zheng Wei Published: 06 Apr 2026, Last Modified: 06 Apr 2026 ACL 2026 Findings Conference, Area Chairs, Reviewers, Publication Chairs, Authors Revisions BibTeX CC BY 4.0 Keywords: Efficient/Low-Resource Methods for NLP, Generation, Question Answering Abstract: The emergence of reasoning models, exemplified by OpenAI o1, signifies a transition from intuitive to deliberative cognition, effectively reorienting the scaling laws from pre-training paradigms toward test-time computation. While Monte Carlo Tree Search (MCTS) has shown promise in this domain, existing approaches typically treat each rollout as an isolated trajectory. This lack of information sharing leads to severe inefficiency and substantial computational redundancy, as the search process fails to leverage insights from prior explorations. To address these limitations, we propose PRISM-MCTS, a novel reasoning framework that draws inspiration from human parallel thinking and reflective processes. PRISM-MCTS integrates a Process Reward Model (PRM) with a dynamic shared memory, capturing both "Heuristics" and "Fallacies". By reinforcing successful strategies and pruning error-prone branches, PRISM-MCTS effectively achieves refinement. Furthermore, we develop a data-efficient training strategy for the PRM, achieving high-fidelity evaluation under a few-shot regime. Empirical evaluations across diverse reasoning benchmarks substantiate the efficacy of PRISM-MCTS. Notably, it halves the trajectory requirements on GPQA while surpassing MCTS-RAG and Search-o1, demonstrating that it scales inference by reasoning judiciously rather than exhaustively.
Code (0)
등록된 구현이 없습니다.
Tasks
Question AnsweringSimilar Papers 제목 키워드 기반
EduFlow: Advancing MLLMs' Problem-Solving Proficiency through Multi-Stage, Multi-Perspective Critique
Multimodal large language models (MLLMs) still perform poorly on scientific tasks, particularly those requiring multi-step and interpretable reasoning. Their limitations include insufficient scientific reasoning patterns…
CoT2-Meta: Budgeted Metacognitive Control for Test-Time Reasoning
Recent test-time reasoning methods improve performance by generating more candidate chains or searching over larger reasoning trees, but they typically lack explicit control over when to expand, what to prune, how to rep…
PRISM: Robust VLM Alignment with Principled Reasoning for Integrated Safety in Multimodality
Safeguarding vision-language models (VLMs) is a critical challenge, as existing methods often suffer from over-defense, which harms utility, or rely on shallow alignment, failing to detect complex threats that require de…
MeEvo: Metacognitive Evolution Combined with Natural Evolution for Automatic Heuristic Design
Large Language Models (LLMs) have advanced Automatic Heuristic Design (AHD) by enabling heuristic generation through reasoning and code synthesis. In LLM-based AHD, the LLM reasons about algorithm design and generates ex…
When Does Memory Help Multi-Trajectory Inference for Tool-Use LLM Agents?
Multi-trajectory inference for tool-use LLM agents - generating multiple reasoning attempts and selecting among them - benefits from transferring knowledge across attempts so that later ones avoid the pitfalls of earlier…