When LLM Meets Tree Search: A Systematic View of Inference as Search in Large Language Models
cs.CL
Submitted: 2026-08-31
Updated: 2026-08-31
Terminology
Sources
- AutoDiscovery: Open-ended Scientific Discovery via Bayesian Surprise
- SWE-Search: Enhancing Software Agents with Monte Carlo Tree Search and Iterative Refinement
- Bilevel MCTS for Amortized O(1) Node Selection in Classical Planning
- VerMCTS: Synthesizing Multi-Step Programs using a Verifier, a Large Language Model, and Tree Search
- Multi-Relational Structural Entropy
- PPL-MCTS: Constrained Textual Generation Through Discriminator-Guided MCTS Decoding
- When is Tree Search Useful for LLM Planning? It Depends on the Discriminator
- Think More, Hallucinate Less: Mitigating Hallucinations via Dual Process of Fast and Slow Thinking
- SELA: Tree-Search Enhanced LLM Agents for Automated Machine Learning
- Step-level Value Preference Optimization for Mathematical Reasoning
- KCTS: Knowledge-Constrained Tree Search Decoding with Token-Level Hallucination Detection
- Generating Code World Models with Large Language Models Guided by Monte Carlo Tree Search
- Make Every Move Count: LLM-based High-Quality RTL Code Generation Using MCTS
- Self-supervised Dialogue Learning for Spoken Conversational Question Answering
- ProMed: Shapley Information Gain Guided Reinforcement Learning for Proactive Medical LLMs
- Everything of Thoughts: Defying the Law of Penrose Triangle for Thought Generation
- Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs
- When Images Look Right and Retrieve Wrong: Coverage-Guided Cross-Scale Re-Indexing for Knowledge-Faithful Generative Perception
- Progressive Multimodal Reasoning via Active Retrieval
- Enhancing Test-Time Scaling of Large Language Models with Hierarchical Retrieval-Augmented MCTS
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering