Reasoning Trajectory

Follow this topic Ask about this topic

Momentum

8 papers in the last four weeks, up 33% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 60

All topics

When Reasoning Helps Action: Monitoring and Steering Chain-of-Thought in Vision-Language-Action Policies
Sep 30, 2026Sathwik Karnik, Joseph JR. Lee, Aryaman Gupta +1Reasoning Trajectory Chain-of-Thought Reasoning
Safe and Intelligent Autonomy Lab, Stanford University
Interpreting Reasoning of Large Language Models via Partial Information Decomposition
Sep 30, 2026Barproda Halder, Qiuyi Zhang, Sanghamitra DuttaLarge Reasoning Models Reasoning Trajectory
University of Maryland, College Park · Elorian AI
TAEC: Trajectory-Aware Evidence Coordination for Multi-Step Visual RAG
Sep 29, 2026Yalun Wu, Bingzhou Wang, Boyang Wang +5Visual Evidence Multimodal Retrieval Augmented Generation
NExT++ Lab, National University of Singapore
Interactive-Policy Distillation with Bidirectional Propose-and-Verify
Sep 29, 2026Shutong Wu, Xiwen Chen, Brendan Rappazzo +4Efficient On-Policy Distillation Teacher
Department of Computer Sciences, University of Wisconsin–Madison · Machine Learning Research, Morgan Stanley · Department of Electrical and Computer Engineering, Rutgers University–New Brunswick
Schema-Anchored Latent Reasoning for Semantic Parsing-Based Knowledge Base Question Answering
Sep 17, 2026Guangze Gao, Zixuan Li, Sikui Zhang +5Efficient Latent Reasoning Sparql
Institute of Automation, Chinese Academy of Sciences China · Institute of Computing Technology, Chinese Academy of Sciences China · University of Chinese Academy of Sciences China
Think Thrice Before Reranking: Multi-perspective Evidence and Reasoning Integration for Text Reranking
Sep 17, 2026Lijun Liu, Zhengzong Chen, Wenyan Li +2Reranking Ranking
Honor Device Co., Ltd
Anchoring What Matters: A Dual-Level Learning Framework for Visually-Grounded Multimodal Reasoning
Sep 16, 2026Xinxin Song, Siyuan Li, Tingxiong Xiao +1Recent Vision-Language Models Reinforcement Learning With Verifiable Reward
Department of Automation, Tsinghua University · Institute for Brain and Cognitive Science, Tsinghua University
Beyond Generation and Accuracy: Diagnosing and Enhancing Visual Chain-of-Thought for Geometry Problem Solving
Sep 11, 2026Zhitong Dong, Jicai Pan, Yingguo Gao +3Visual Reasoning Geogs-Slam
1Key Laboratory of New Generation Artificial Intelligence Technology, Southeast University Group · 2Ant
FlowBalance: Verifier-Grounded Self-Improvement from On-Policy Reasoning Experience
Sep 3, 2026Zixun Huang, Kishan Panaganti, Haitao Mi +1Reinforcement Learning With Verifiable Reward Reasoning Trajectory
Tencent HY LLM Frontier · University of Pennsylvania
Geometry of Divergence: Tracking Hidden-State Trajectories for Adaptive Multi-Turn Reasoning
Aug 31, 2026Jie Liang, Zhengxin Yu, Hamid Nasiri +1Reasoning Trajectory Multi-Turn Interactions
School of Computing and Communications, Lancaster University, UK · School of Computing and Engineering, University of Huddersfield, UK
Learning to Reason and Use Tools through Unsupervised Fine-Tuning in Task-Oriented Dialog Systems
Aug 31, 2026Markel Ferro, Oier Lopez de LacalleLLM Reasoning Strategies Supervised Finetuning
HiTZ Center - Ixa, University of the Basque Country UPV/EHU
AutoCRAT: Within-trajectory Joint Control of Stochasticity and Compute for LLM Reasoning
Aug 30, 2026Hanjun Luo, Qiushi Liu, Jingya Zhang +8LLM Reasoning Strategies Autoregressive Language Models
New York University · New York University Abu Dhabi · University of Washington Seattle +4
CRAFT: LLM-Based Iterative Refinement for Temporal Reasoning over Clinical Narratives
Aug 13, 2026Chengyang He, Tahreem Arif, Marko Zivkovic +3Temporal Reasoning Patient Trajectories
Stevens Institute of Technology, Hoboken, NJ, 07030, USA · Genesis Research Group, Hoboken, NJ, 07030,USA · New Jersey Institute of Technology, Newark, NJ, 07102, USA
Tree-of-Ideas: Automated Research Ideation via Cross-Trajectory Reasoning over Scholarly Evolution
Aug 11, 2026Xun Li, Yiying Yang, Pengtao Li +8Scientific Ideation Research Automation
Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ) · University of Melbourne · University of Sydney +4
Branch2Skill: Efficient Skill Evolution Through Reasoning Trees
Aug 9, 2026Yanwei Ren, Haotian Zhang, Likang Xiao +5Skill Evolution Reasoning Trajectory
School of Artificial Intelligence, Beihang University, Beijing, China · Hangzhou International Innovation Institute, Beihang University, Hangzhou, China · The Hong Kong Polytechnic University, Hong Kong SAR, China +3
From Trajectories to Evidence: Auditable Experimental Records for Industrial Research Agents
Aug 5, 2026Zijie Zhuang, Changxin Lao, Pengbo Xu +13Evidence-Grounded Questions Category-Aware Atomic Claims
Kuaishou Technology, Beijing, China
ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning
Aug 4, 2026Jinhe Bi, Chennan Zhou, Zengjie Jin +10Reasoning Trajectory Large Language Model Reinforcement Learning
National University of Singapore · Ludwig Maximilian University of Munich · Huawei Heisenberg Research Center +6
TRAM: Enhancing Multimodal Reasoning with Trajectory-Derived Auxiliary Memory
Aug 3, 2026Kang Liu, Zijing Wang, Yongkang Liu +5Multimodal Reasoning Reasoning Trajectory
Northeastern University, China
OSReward: Instituting Standardized Evaluation for Cross-Platform Computer-Use Reward Models
Jul 30, 2026Qiushi Sun, Kanzhi Cheng, Yian Wang +20Progress Reward Modeling Large Language Model Judges
The University of Hong Kong · Nanjing University · National University of Singapore +4
TRACTA: Benchmarking Temporal Reasoning over Semantic Trajectories
Jul 24, 2026Michael Romei De Socio, Gian Luca Pozzato, Alessio MerloTemporal Reasoning Neuro-Symbolic Framework
Department of Computer Science, University of Turin, Corso Svizzera 185, 10149 Turin, Italy · CASD – School of Advanced Defense Studies, Piazza della Rovere 83, 00165 Rome, Italy
REFACT: Adaptive Fact Restatement for Compact and Faithful Chain-of-Thought Reasoning
Jul 23, 2026Zhensheng Jin, Xin Dai, Zhenghao Liu +5LLM Reasoning Strategies Long-Context Reasoning
Northeastern University · Shenyang, China · Tsinghua University +1
TREK: Distill to Explore, Reinforce to Refine
Jul 6, 2026Yuanda Xu, Zhengze Zhou, Kayhan Behdin +10Repair-Based Group-Relative Policy Optimization Reasoning Trajectory
LinkedIn Corporation · Harvard University · Georgia Institute of Technology
Do Vision-Language-Action Models Mean What They Say? On the Role of Faithfulness in Embodied Reasoning
Jul 6, 2026Matthew Foutter, Matteo Cercola, Lena Wild +4Reasoning Trajectory Faithfulness
Stanford University · Politecnico di Milano · KTH Royal Institute of Technology +2
Invariant Reasoning Directions in Latent Trajectories of Language Models
Jun 28, 2026Arun Vignesh Malarkkan, Manan Roy Choudhury, Utkarsh Byahut +3Reasoning Trajectory Latent Trajectories
Arizona State University, Tempe, Arizona.
Search for Truth from Reasoning: A Dynamic Representation Editing Framework for Steering LLM Trajectories
Jun 26, 2026Tianlong Wang, Yuhang Wang, Weibin Liao +5LLM Reasoning Strategies Reasoning Trajectory
National Engineering Research Center of Software Engineering, Peking University · School of Computer Science, Peking University · Key Laboratory of High Confidence Software Technologies, Ministry of Education +1
OPERA: Aligning Open-Ended Reasoning via Objective Perplexity-based Reinforcement Learning
Jun 24, 2026Wenxuan Jiang, Zining Fan, Zijian Zhang +6LLM Reasoning Strategies Large Language Model Reinforcement Learning
The Hong Kong Polytechnic University · Peking University · Meituan Longcat Team +2
AIR: Adaptive Interleaved Reasoning with Code in MLLMs
Jun 22, 2026Cong Han, Xiaohan Lan, Haibo Qiu +1LLM Reasoning Strategies Multimodal Large Language Models
1Independent Researcher.
Only Ask What You Don't Know: Grounded Delta Planning for Efficient Multi-step RAG
Jun 21, 2026Wei-Chieh Chou, Xuanjun Chen, Jian-Ren Lin +3Action-Conditioned Planning Reasoning Trajectory
Dept. of Computer Science and Information Engineering, National Taiwan University · Graduate Institute of Communication Engineering, National Taiwan University · Department of Economics, National Taiwan University +2
STRIDE: Strategic Trajectory Reasoning via Discriminative Estimation for Verifiable Reinforcement Learning
Jun 14, 2026Qinjian Zhao, Zhihao Dou, Dinggen Zhang +10Reinforcement Learning With Verifiable Reward Verifiable Rewards
Kean University · Case Western Reserve University · University of Texas at Austin +4
Forecasting Future Behavior as a Learning Task
Jun 9, 2026Mosh Levy, Yoav Goldberg, Asa Cooper SticklandLarge Language Model Forecasting Reasoning Trajectory
Bar-Ilan University · Constellation · UK AI Security Institute +1
StepPRM-RTL: Stepwise Process-Reward Guided LLM Fine-Tuning for Enhanced RTL Synthesis
Jun 2, 2026Prashanth Vijayaraghavan, Apoorva Nitsure, Luyao Shi +2High-Level Synthesis Hierarchical Register Transfer Level Generation
IBM Research San Jose, CA, USA
Geometric Latent Reasoning Induces Shorter Generations in LLMs
Jun 1, 2026Shashi Kumar, Yacouba Kaloga, Petr Motlicek +2Efficient Latent Reasoning Reasoning Trajectory
Idiap Research Institute, Switzerland · EPFL, Switzerland · BUT, Czech Republic
LARK: Learnability-Grounded Trajectory Selection for Efficient Reasoning Distillation
May 28, 2026Tianrun Yu, Kaixiang Zhao, Chih-Chun Chen +5Reasoning Trajectory Learnability
Brigham Young University · The Pennsylvania State University · University of North Carolina at Chapel Hill
ProSR: Process-Shaped Spatial Reasoning for Reliable Chain-of-Thought in VLMs
May 25, 2026Jiangyang Li, Cong Wan, Changjie Wu +8Spatial Reasoning Reasoning Trajectory
1Xi’an Jiaotong University · 2Amap, Alibaba Group · 4Shenzhen University +1
Boosting Inference with Guided Reasoning: Stochastic Exploration for Recursive Models
May 24, 2026Andrew Corbett, Archit Sood, Anna Tzatzopoulou +2Recursive Models Reasoning Trajectory
digiLab, UK · University of Bristol, UK
Better, Faster: Harnessing Self-Improvement in Large Reasoning Models
May 24, 2026Qihuang Zhong, Liang Ding, Juhua Liu +3Large Reasoning Models Reasoning Trajectory
1Nanyang Technological University, Singapore · 2Alibaba Group · School of Computer Science, Wuhan University, China +1
Test-Time Deep Thinking to Explore Implicit Rules
May 24, 2026Wentong Chen, Xin Cong, Zhong Zhang +8Agentic Reasoning Reasoning Trajectory
Renmin University of China Beijing, China · Department of Statistics and Data Science, Tsinghua University Beijing, China · School of Computer Science and Engineering, UESTC Chengdu, China +4
PathCal: State-Aware Reflection-Marker Calibration for Efficient Reasoning
May 21, 2026Lingyu Jiang, Zirui Li, Shuo Xing +6Reasoning Trajectory Chain-of-Thought Reasoning
1Tohoku University · 2Texas A&M University · 3Worcester Polytechnic Institute
On the Cost and Benefit of Chain of Thought: A Learning-Theoretic Perspective
May 20, 2026Yue Zhang, Zhiyi Dong, Tommaso Cesari +1Reasoning Trajectory Thoughts
University of Ottawa, Ottawa, Canada
TIER: Trajectory-Invariant Execution Rewards for Multi-Step Tool Composition
May 16, 2026Anay Kulkarni, ChiaEn Lu, Dheeraj Mekala +3Multi-Turn Reinforcement Learning Reasoning Trajectory
UC San Diego · Cisco Research
How to Interpret Agent Behavior
May 13, 2026Jie Gao, Kaiser Sun, Jen-tse Huang +8Agent Behavior Modeling Runtime
1Johns Hopkins University · 2California Institute of Technology · 3Northeastern University +1
Retrieval is Cheap, Show Me the Code: Executable Multi-Hop Reasoning for Retrieval-Augmented Generation
May 13, 2026Jiashuo Sun, Jimeng Shi, Yixuan Xie +10Multi-Hop Reasoning Reasoning Trajectory
University of Illinois Urbana-Champaign · Hong Kong University of Science and Technology · Texas A&M University +1
Latency Analysis and Optimization of Alpamayo 1 via Efficient Trajectory Generation
May 9, 2026Yunseong Jeon, Namcheol Lee, Yoonsu Lee +4Reasoning Trajectory Inference Latency
Graduate School of Automobile and Mobility, Kookmin University, Seoul, Republic of Korea · Department of Electrical and Computer Engineering, Seoul National University, Seoul, Republic of Korea
Self-ReSET: Learning to Self-Recover from Unsafe Reasoning Trajectories
May 9, 2026Dongcheng Zhang, Yi Zhang, Yuxin Chen +3Reasoning Trajectory
University of Science and Technology of China · Shanghai Artificial Intelligence Laboratory · National University of Singapore
Internalizing Safety Understanding in Large Reasoning Models via Verification
May 9, 2026Yi Zhang, Yuxin Chen, Leheng Sheng +4Safety Claims Large Reasoning Models
University of Science and Technology of China · National University of Singapore · Shanghai Artificial Intelligence Laboratory
How You Begin is How You Reason: Driving Exploration in RLVR via Prefix-Tuned Priors
May 9, 2026Yifan Xu, Junren Chen, Yifan ChenReinforcement Learning With Verifiable Reward Verifiable Rewards
Hong Kong Baptist University · University of Maryland, College Park
AgentPSO: Evolving Agent Reasoning Skill via Multi-agent Particle Swarm Optimization
May 9, 2026Hyunmin Hwang, Jaemin Kim, Choonghan Kim +2Multi-Agent Reasoning Reasoning Benchmark
Graduate School of Artificial Intelligence, Korea Advanced Institute of Science and Technology, Seoul, South Korea.
Measuring Black-Box Confidence via Reasoning Trajectories: Geometry, Coverage, and Verbalization
May 7, 2026Marc Boubnovski Martell, Josefa Lia Stoisser, Kaspar Märtens +4Reasoning Benchmark Reasoning Trajectory
1Novo Nordisk · University of Oxford
RAG over Thinking Traces Can Improve Reasoning Tasks
May 5, 2026Negar Arabzadeh, Wenjie Ma, Sewon Min +1Reasoning Traces Reasoning Trajectory
University of California, Berkeley
Verifiable Counterfactual Supervision for Process Reward Models
May 4, 2026Yinghui Chi, Yuanhong WangProcess Reward Model Counterfactual Learning
Jilin University
Distilling Long-CoT Reasoning through Collaborative Step-wise Multi-Teacher Decoding
May 4, 2026Taewon Yun, Jisu Shin, Jeonghwan Choi +2Reasoning Trajectory Teacher-Student Distillation
KAIST · UNIST
Kernelized Advantage Estimation: From Nonparametric Statistics to LLM Reasoning
Apr 30, 2026Shijin Gong, Kai Ye, Jin Zhu +3Large Language Model Reinforcement Learning LLM Reasoning Strategies
School of Management, University of Science and Technology of China · Department of Statistics, London School of Economics and Political Science · School of Mathematics, University of Birmingham +2
Omni-o3: Deep Nested Omnimodal Deduction for Deliberative Audio-Visual Reasoning
Apr 27, 2026Zhicheng Zhang, Wentao Gu, Weicheng Wang +5Audio-Visual Reasoning Omni-Modal
Nankai University · Kuaishou Technology · Pengcheng Laboratory +1
MultiDx: A Multi-Source Knowledge Integration Framework towards Diagnostic Reasoning
Apr 27, 2026Yimin Deng, Zhenxi Lin, Yejing Wang +9Clinical Reasoning Training Diagnosis
Xi’an Jiaotong University · City University of Hong Kong · Tencent Jarvis Lab +1
LegalDrill: Diagnosis-Driven Synthesis for Legal Reasoning in Small Language Models
Apr 26, 2026Tianchun Li, Haochen Liu, Vishwa Pardeshi +5Legal Reasoning Tasks LLM Reasoning Strategies
Purdue University, West Lafayette, IN, USA · Fidelity Investments, Boston, MA, USA
GRPO-VPS: Enhancing Group Relative Policy Optimization with Verifiable Process Supervision for Effective Reasoning
Apr 22, 2026Jingyi Wang, Lei Zhu, Tengjin Weng +8Reinforcement Learning With Verifiable Reward Better Call Group Relative Policy Optimization
Tsinghua University · Huawei Noah’s Ark Lab · Shenzhen University
AI scientists produce results without reasoning scientifically
Apr 20, 2026Martiño Ríos-García, Nawaf Alampara, Chandan Gupta +5Artificial Intelligence Scientists LLM Reasoning Strategies
Laboratory of Organic and Macromolecular Chemistry (IOMC), Friedrich Schiller University Jena, Humboldstr. 10, 07743 Jena, Germany · Department of Civil Engineering, Indian Institute of Technology Delhi, Hauz Khas, New Delhi 110016, India · School of Interdisciplinary Research, Indian Institute of Technology Delhi, Hauz Khas, New Delhi 110016, India +3
Targeted Exploration via Unified Entropy Control for Reinforcement Learning
Apr 16, 2026Chen Wang, Lai Wei, Yanzhi Zhang +5Large Language Model Reinforcement Learning Reasoning Trajectory
College of Software, Nankai University · Zhongguancun Academy · Shanghai Jiao Tong University +3
Watch the Model Think: On-Policy Extraction of Activation Steering Vectors
Feb 15, 2026Xuanbo Su, Yingfang Zhang, Hao Luo +3Linear Activation Steering Reasoning Trajectory
Bairong Inc., Beijing, China · School of Mathematics, Harbin Institute of Technology, Harbin, China
What If We Allocate Test-Time Compute Adaptively?
Feb 1, 2026Ahsan Bilal, Ahmed Mohsin, Muhammad Umer +4Test-Time Scaling Efficient Inference
University of Oklahoma, OK, USA · Stanford University, CA, USA · Universitat Pompeu Fabra, Barcelona, Spain +2

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

When Reasoning Helps Action: Monitoring and Steering Chain-of-Thought in Vision-Language-Action Policies

Sathwik Karnik, Joseph JR. Lee, Aryaman Gupta, Somil Bansal

Safe and Intelligent Autonomy Lab, Stanford University

Reasoning Trajectory Chain-of-Thought Reasoning Closed Loop Behavioral Divergence

Open paper AskPDF arXiv

Reasoning-enabled VLA policies expose chain-of-thought (CoT) traces that appear to explain and guide their actions, creating a potential interface for runtime safety through reasoning monitoring and correction. In this work, we define and operationalize two evaluation axes for assessing when this interface can improve embodied behavior: correctability, which measures whether unreliable reasoning can be detected and improved during generation, and actionability, which measures whether reasoning corrections produce behaviorally meaningful changes in the intended direction. To enable correctability, we introduce Token-level Reward for Utility-Steered Chain-of-Thought (TRUST), an offline-trained value model that predicts eventual reasoning correctness from partial prefixes and uses these estimates to monitor and selectively steer reasoning generation in frozen VLA policies. On the Alpamayo 1.5 driving VLA, TRUST monitors correctness with 88.9% accuracy and improves reasoning correctness from 75.9% to 90.0%. On a baseline-defined challenging subset in AlpaSim, TRUST reduces collision rate by 30.4% and maximum trajectory error by 11.5% relative to the unsteered policy, outperforming a compute-matched Best-of-4 baseline. On the DeepThinkVLA manipulation VLA, TRUST improves the correctness of grasp-state claims from 69.3% to 90.2% and action-choice claims from 68.8% to 85.9%, yet closed-loop task performance on LIBERO-Plus remains largely unchanged. Empirical analysis reveals intent-consistent behavioral effects in Alpamayo 1.5 but limited effects in DeepThinkVLA, helping interpret these different task-level outcomes. Together, our results show that gains in reasoning correctness do not automatically imply gains in embodied performance, motivating evaluation of correctability and actionability when using CoT as a runtime safety interface.

Momentum

Related topics

Latest papers 60