Tree Search

Follow this topic Ask about this topic

Momentum

7 papers in the last four weeks, against 2 the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 46

All topics

OPTS-TTPO: Enhancing Finite-Sample Policy-Gradient Learning with Tree Search
Sep 30, 2026Junyu Lu, Shichao Weng, Zhiqiang Wang +10Frictive Policy Optimization Policy Gradient
Dobot Robotics · Independent Researcher · Zhejiang University +2
LazySloth: Bounded LLM-based Lazy Tree Search for Fast Long Video Comprehension
Sep 29, 2026Arka Mukherjee, Kaleen Shrestha, Larissa Zhu +1Video Understanding Video Captioning
School of Computer Engineering, Kalinga Institute of Industrial Technology (KIIT) Bhubaneswar · Computer Science Department, Viterbi School of Engineering, University of Southern California
Canopy: Exploiting Piecewise Smooth Tree Priors for Multi-Fidelity Bandits
Sep 24, 2026Michael Jerge, Suman JanaTree Search Multi-Fidelity
Amazon · Columbia University
EvoTreeNAD: Genealogy-Guided Evolution for LLM-Driven Neural Architecture Discovery
Sep 24, 2026Lishan Yu, Derek Jiu, Qizhen Lan +1Neural Architecture Search Evolutionary Search
Department of Health Data Science and AI McWilliams School of Biomedical Informatics University of Texas Health Science Center at Houston
Self Improvement via Fast Tree-search
Sep 17, 2026Xinghong Fu, Aravinth Kulanthaivelu, Yutaro YamadaRecursive Self-Improvement Tree Search
Massachusetts Institute of Technology · Sakana AI
Learning-Guided Planning in Large Dynamic Action Spaces: Budgeted Tree Search for One-to-Many Mobile Charging
Sep 15, 2026Liang-Ching Tao, Pi-Chung WangClassical Planning Learning Policy
Department of Computer Science and Engineering, National Chung Hsing University · Xingda Rd., South District, Taichung 402, Taiwan
VertexCBF: Improving Neural Control Barrier Functions via Vertex-Restricted Control Search
Sep 11, 2026Bojan Derajić, Sebastian Bernhard, Wolfgang HönigControl Barrier Functions Learning-Based Control
Technical University of Berlin, Germany · AUMOVIO, Germany · Technical University of Applied Sciences Augsburg, Germany +1
When LLM Meets Tree Search: A Systematic View of Inference as Search in Large Language Models
Aug 31, 2026Jiaqi Wei, Xiang Zhang, Yuejin Yang +10Tree Search LLM Reasoning Strategies
1Zhejiang University · 2Shanghai AI Laboratory · 4Fudan University +3
Recovering Wasted Compute in Autoresearch Agents
Aug 11, 2026Au Kwok Chun, Abhigyan Acherjee, Amrutha Rao +4Research Automation Search Algorithms
Department of Computer Science, Columbia University · 2AI, Analytics and Future of Work Initiative, Georgetown University · Department of Applied Mathematics, Columbia University +3
Idea Search: Guiding Tree Search with Ideas to Explore Diverse Scientific Methods
Aug 9, 2026Xuefei Julie Wang, Hao Cui, Michael P. Brenner +1Tree Search Tree-Of-Thoughts
California Institute of Technology · *Work done during an internship at Google Research. · Google Research +1
BONSAI: Evolvability-Guided Tree Search over Skills
Aug 7, 2026Yash Priya Shastri, Anand Eswaran, Adnan Qidwai +2Skills Tree Search
IBM Research
CEDAR: Agent-Orchestrated Tree Search for Goal-Directed Optimization of Complex Systems
Aug 7, 2026Yingtao TianMonte Carlo Tree Search Tree Search
Sakana AI, Tokyo, Japan
Monte Carlo Tree Search for Table-to-Multimodal Report Generation
Aug 4, 2026Teng Lin, Zhiyang Zhang, Yuyu Luo +1Report Monte Carlo Tree Search
The Hong Kong University of Science and Technology (Guangzhou)
Mining Verdict Boundaries for Neural Network Verification
Jul 31, 2026Jiawei Ren, Guanqin Zhang, Zhenya Zhang +1Neural Network Verification Upper Bounds
University of New South Wales, Sydney, Australia · Kyushu University, Fukuoka, Japan · National Institute of Informatics, Tokyo, Japan
FARO: Feasibility-Aware Robot Motion Optimization
Jul 20, 2026Michal Ciebielski, Shafeef Omar, Aaron Johnson +1Robot Trajectories Humanoid Loco-Manipulation
Munich Institute of Robotics and Machine Intelligence (MIRMI), Technical University of Munich (TUM), Germany. · Institute for Advanced Study, Technical University of Munich, Garching, Germany. · Department of Mechanical Engineering, Carnegie Mellon University, Pittsburgh, PA, USA.
TreeThink: A Modular Tree Search Library for Mathematical Reasoning with LLMs
Jul 13, 2026Burak S. Akbudak, Zeynel A. Uluşan, Can S. Erer +1Theorem Proving Tree Search
Computer Engineering Department, Bogazici University, Istanbul, Turkey · Computer Engineering Department, Koç University, Istanbul, Turkey · Codeway Studios, Istanbul, Turkey +2
GATS: Graph-Augmented Tree Search with Layered World Models for Efficient Agent Planning
Jul 9, 2026Maureese Williams, Dymitr NowickiLarge Language Model Planning Classical Planning
Institute for Cybernetics of NAS of Ukraine
Offline Nash Solvers Meet Online Tree Search in Multi-Agent Games on Graphs
Jul 9, 2026Mukesh Kumar, Yue Guan, Panagiotis TsiotrasNash Equilibrium Tree Search
School of Aerospace Engineering, Georgia Institute of Technology, Atlanta, GA, USA
DominoTree: Conditional Tree-Structured Drafting with Domino for Speculative Decoding
Jul 9, 2026Saw S. Lin, Jyh-Shing Roger JangBlock-Diffusion Drafter Speculative Decoding
Zhiqi Zhang · Department of Computer Science and Information Engineering, National Taiwan University.
Look Before You Leap: Distilling Tree Search into Action Evaluation for Frozen VLA Models
Jul 4, 2026Xinyi Xie, Zican Hu, Zhanyu Liu +7Frozen Vision-Language Models Action Generation
Nanjing University · Australian National University · Institute of Automation, Chinese Academy of Sciences +1
CONTRA: Red-Teaming Configurations of Personalizable Agents
Jul 3, 2026Jonathan Nöther, Adish Singla, Goran RadanovicRed-Teaming Malicious Agents
Max Planck Institute for Software Systems, Germany
Learning the ARTS of Search for Automated Discovery
Jun 20, 2026Gurusha Juneja, Arnav Kumar Jain, Deepak Nathani +2Tree Search Agentic Reasoning
University of California, Santa Barbara · Université de Montréal and Mila- Quebec AI Institute
SproutRAG: Attention-Guided Tree Search with Progressive Embeddings for Long-Document RAG
Jun 16, 2026Amirhossein Abaskohi, Issam H. Laradji, Peter West +1Agentic Retrieval-Augmented Generation Systems Tree Search
University of British Columbia · ServiceNow Research
StarOR: Synergizing Tree Search and Test-Time Reinforcement Learning for Optimization Modeling
Jun 13, 2026Jiajun Li, Yu Ding, Shisi Guan +2Optimization Modeling Tree Search
School of Computer Science and Engineering, Southeast University · Northwest A&F University
Arbor: Tree Search as a Cognition Layer for Autonomous Agents
Jun 10, 2026Neha Prakriya, Chaojun Hou, Zheng Gong +5Agentic Inference Tree Search
Training and Inference Optimization Team AMD
TreeSeeker: Tree-Structured Trial, Error, and Return in Deep Search
Jun 10, 2026Zhuofan Shi, Mingzhe Ma, Lu Wang +8Tree Search High-Level Subgoal Generation
1Microsoft · 2East China Normal University
Segment-level Tree Search for Long Meeting Document Summarization
Jun 7, 2026Sangwon Ryu, Heejin Do, Jun Seo +4Summarization Document
GSAI, POSTECH · ETH Zurich, ETH AI Center · Agentic AI Lab, KT +2
Automated Proving of Shannon-Type Entropy Inequalities via Fine-Tuned Language Models and Guided Tree Search
Jun 4, 2026Shing Yin Wong, Shaocheng Liu, Linqi Song +2Theorem Proving Small Large Language Models
Department of Computer Science, City University of Hong Kong · Department of Information Engineering, The Chinese University of Hong Kong
S3TS: Stochastic Scenario-Structured Tree Search for Advanced Planning Under Uncertainty
Jun 1, 2026Fabio Pavirani, Bert Claessens, Pierre Pinson +1Demand Response Power Systems
IDLab Ghent university – imec, Technologiepark Zwijnaarde 126, 9052 Gent, Belgium · Beebop.ai, Belgium · Imperial College London, London, UK
Two-Fidelity Best-Action Identification for Stochastic Minimax Tree
Jun 1, 2026Peter Chen, Xi ChenMonte Carlo Tree Search Tree Search
Department of Mathematics Columbia University · Stern School of Business New York University
COMPASS: Cognitive MCTS-Guided Process Alignment for Safe Search Agents
May 29, 2026Wenkai Shen, Pengyang Zhou, Jiahe Xu +5Safety Alignment Search Agents
Zhejiang University
Structure-Induced Information for Rerooting Levin Tree Search
May 28, 2026Jake Tuero, Michael Buro, Laurent Orseau +1Tree Search High-Level Subgoal Generation
Department of Computing Science, University of Alberta, Edmonton, Canada. · Alberta Machine Intelligence Institute (Amii), Edmonton, Canada. · Google DeepMind, London, United Kingdom.
Automating Formal Verification with Agent-Guided Tree Search
May 26, 2026Leo YaoFormal Verification Code Generation
Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology
Protein Thoughts: Interpretable Reasoning with Tree of Thoughts and Embedding-Space Flow Matching for Protein-Protein Interaction Discovery
May 19, 2026Kingsley Yeon, Xuefeng Liu, Promit GhosalBiomedical Knowledge Graph Tree Search
Department of Statistics and CCAM University of Chicago Chicago, IL 60637 · School of Medicine Stanford University Stanford, CA 94305 · Department of Statistics University of Chicago Chicago, IL 60637
Memory-Guided Tree Search with Cross-Branch Knowledge Transfer for LLM Solver Synthesis
May 17, 2026Fatemeh Haji, Javier Delarosa Quiros, Peyman NajafiradFunctional Code Solvers Tree Search
Secure AI and Autonomy Lab · The University of Texas at San Antonio
FML-bench: A Controlled Study of AI Research Agent Strategies from the Perspective of Search Dynamics
May 17, 2026Qiran Zou, Hou Hei Lam, Wenhao Zhao +11Agentic Benchmarks Tree Search
National University of Singapore · Tsinghua University · University of Minnesota +2
Prospective multi-pathogen disease forecasting using autonomous LLM-guided tree search
May 15, 2026Sarah Martinson, Michael P. Brenner, Martyna Plomecka +3Epidemiological Models Tree Search
Google Research · School of Engineering and Applied Sciences, Harvard University · Google Deepmind +1
Optimized Three-Dimensional Photovoltaic Structures with LLM guided Tree Search
May 15, 2026Michael P. Brenner, Lizzie Dorfman, John C. PlattPhotovoltaic Tree Search
Google Research · School of Engineering and Applied Sciences, Harvard University
LEAF-SQL: Level-wise Exploration with Adaptive Fine-graining for Text-to-SQL Skeleton Prediction
May 10, 2026Zhao Tan, Xiping Liu, Qing Shu +3Text-To-Sql Sql
School of Computing and Artificial Intelligence, Jiangxi University of Finance and Economics, Nanchang, China
Extracting Search Trees from LLM Reasoning Traces Reveals Myopic Planning
May 7, 2026Sixing Chen, Ji-An Li, Saner Cakir +3Large Language Model Planning LLM Reasoning Strategies
Department of Psychology New York University · Generality Inc.
Maximizing Rollout Informativeness under a Fixed Budget: A Submodular View of Tree Search for Tool-Use Agentic Reinforcement Learning
May 6, 2026Yuelin Hu, Zhenbo Yu, Zhengxue Cheng +2Group-Based Reinforcement Learning Tree Search
Shanghai Jiao Tong University · Shanghai Maritime University
Understanding Scattered Forest Search: A Version-Space Perspective on Multi-Turn Program Correction
Apr 27, 2026Yuto Tanaka, Issei SatoEfficient Inference Iterative Refinement
Department of Computer Science The University of Tokyo Tokyo, Japan
M2-PALE: A Framework for Explaining Multi-Agent MCTS--Minimax Hybrids via Process Mining and LLMs
Apr 16, 2026Yiyu Qian, Liyuan Zhao, Tim MillerStrategic Reasoning Tree Search
RMIT University, Melbourne, Victoria 3000, Australia · University of California, Irvine, Irvine, CA 92617, USA · University of Queensland, Brisbane, Queensland 4072, Australia
MARS $^2$ : Scaling Multi-Agent Tree Search via Reinforcement Learning for Code Generation
Apr 16, 2026Pengfei Li, Shijie Wang, Fangyuan Li +7Multi-Agent Planning Tree Search
Shanghai Artificial Intelligence Laboratory · Shanghai Innovation Institute · Harbin Institute of Technology +1
Gaussian Process Aggregation for Root-Parallel Monte Carlo Tree Search with Continuous Actions
Dec 10, 2025Junlin Xiao, Victor-Alexandru Darvariu, Bruno Lacerda +1Monte Carlo Tree Search Gaussian Process
School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen · Oxford Robotics Institute, Department of Engineering Science, University of Oxford · Stateful Robotics
Monte Carlo Tree Search with Tensor Factorization for Optimization Problems in Robotics
Jul 7, 2025Teng Xue, Yan Zhang, Amirreza Razmjoo +1Multi-Robot Motion Planning Monte Carlo Tree Search
Idiap Research Institute, Martigny, Switzerland · École Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland

Sep 30, 2026, cs.CLJ/K move · Enter open · S save

OPTS-TTPO: Enhancing Finite-Sample Policy-Gradient Learning with Tree Search

Junyu Lu, Shichao Weng, Zhiqiang Wang, Haojie Luo+9

Dobot Robotics · Independent Researcher · Zhejiang University+2

Frictive Policy Optimization Policy Gradient Tree Search On-Policy

Open paper AskPDF arXiv

The policy-gradient theorem gives the exact gradient under the current policy, but finite on-policy samples may miss rare high-return trajectories. We study whether tree search improves their coverage within a fixed budget while controlling gradient bias. We introduce On-Policy Parallel Tree Search (OPTS) and Tree Trajectory Policy Optimization (TTPO) using on-policy tree trajectories, which sample new suffixes from the current policy at visited states. This needs no action-distribution correction, although branching changes state visitation. Our Branch Aggregation Lemma shows that branch-weighted tree statistics recover chain expectations when branch choices and weights are fixed before outgoing transitions are sampled. OPTS selects expansion states using estimated performance differences. Under deterministic dynamics, exact values, and max-backup advantages, the induced search policy's expected return improves monotonically with the budget. We bound the gradient bias from adaptive expansion and show that max backup assigns prefix credit to actions leading to better discovered suffixes. Against a finite chain reference, TTPG's measured bias stays near its no-branching level, while NaivePG's bias grows from 0.1251 to 0.4884. At matched budgets, reward- and value-guided OPTS improve correct-answer coverage and majority-vote accuracy over independent sampling. At matched branch counts, OPTS + TTPG gains coverage with a modest bias increase relative to Fixed-branch + TTPG. Under matched interaction or rollout budgets, OPTS-TTPO improves MuJoCo tail returns over PPO by up to 28.6%, achieves a 34-22-1 win-loss-tie record against PPO on Atari-57 under the last-100-log mean-return metric, and improves micro-averaged avg@32 and pass@32 over PPO across all four Qwen3 models.

Momentum

Related topics

Latest papers 46