Agentic Reasoning Publications

LAGEN: Are Vision-Language Agents Latency Aware? [Website][PDF][Code][Models][Data]
Talha Chafekar*, Zihan Wang*, Zeju Li*, Xinyuan Li*, Qineng Wang, Jiajun Wu, Yuke Zhu, Yi Dong, Zhiding Yu, Ruohan Zhang, Manling Li

Latency-Aware AgentsVision-Language-Action ModelsReal-Time DeploymentAgent Training

Realtime-Bench: Can Frontier Models Solve Real-time Interactive Problems? [Website][PDF][Code]
Jingyu Tang*, Xu Yang*, Zhehao Zhang*, Zheng Wang, Qi Cheng, Haozhe Zhao, Manling Li, Wenxuan Li, Xide Xia, Jiaxin Pei

Real-Time AgentsInteractive BenchmarkLatency-Aware EvaluationMultimodal ModelsTemporal Awareness

Decoupled Physical Modeling and Execution for Physics Reasoning [PDF]
Ye Zhang, Xuehang Guo, Rui Pan, Pengfei Yu, Denghui Zhang, Manling Li, Qingyun Wang

Physics ReasoningExplicit Physical ModelingReinforcement LearningRubric-Based RewardsVision-Language Models

Consistency-Driven Co-Evolution for Self-Supervised Cross-Representation Learning [PDF]
Xuehang Guo, Pengyuan Li, Tom Hope, Tirthankar Ghosal, Manling Li, Qingyun Wang

Cross-Representation ConsistencyChart-Table-Code UnderstandingSelf-Supervised Co-EvolutionTest-Time OptimizationReinforcement Learning

Agentic Commerce World: An Auditable and Verifiable Environment for Vibe Commerce [PDF][Code]
Shicheng Fan, Mingdai Yang, Duohao Wang, Canyu Chen, Yongfeng Zhang, Hua Wei, Manling Li, Julian McAuley, Kun Zhang, Philip S. Yu, Kejing Yu, Zhiwei Liu

Agentic CommerceMulti-Agent EnvironmentBuyer-Merchant NegotiationAgent BenchmarkAuditable Evaluation

SENTINEL: Failure-Driven Reinforcement Learning for Training Tool-Using Language Model Agents [PDF]
Ziyi Wang, Yuxuan Lu, Yimeng Zhang, Qun Liu, Chen Luo, Jiri Gesi, Hanqing Lu, Yisi Sang, Manling Li, Jing Huang, Dakuo Wang

Failure-Driven Reinforcement LearningTool-Using AgentsTargeted Task GenerationMulti-Turn Tool UseAgent Training

CLORE: Content-Level Optimization for Reasoning Efficiency [PDF]
Yuyang Wu*, Qiyao Xue*, Guanxing Lu*, Weichen Liu, Zihan Wang, Manling Li+, Olexandr Isayev+

Efficient ReasoningReinforcement LearningReasoning Trace EditingDPOMathematical Reasoning

Interactive Evaluation Requires a Design Science [PDF][Code]
Keyang Xuan*, Peiyang Song*, Pan Lu, Pengrui Han, Wenkai Li, Zhenyu Zhang, Zexue He, Wenyue Hua, Manling Li, Jiaxuan You, Adrian Weller, Yizhong Wang+, Jiaxin Pei+

Interactive EvaluationAgent BenchmarksTrajectory-Level AssessmentEvaluation TaxonomyPosition Paper

SkillCraft: Can LLM Agents Learn to Use Tools Skillfully? [Website][PDF][Code][tl;dr]
Shiqi Chen, Jingze Gai, Ruochen Zhou, Jinghan Zhang, Tongyao Zhu, Junlong Li, Kangrui Wang, Zihan Wang, Zhengyu Chen, Klara Kaleb, Ning Miao, Siyang Gao, Cong Lu, Manling Li, Junxian He, Yee Whye Teh

Tool UseSkill LearningLLM AgentsAgent Training

BAGEN: Are LLM Agents Budget-Aware? [Website][PDF][Code][Data][tl;dr]
Yuxiang Lin, Zihan Wang, Mengyang Liu, Yuxuan Shan, Longju Bai, Junyao Zhang, Xing Jin, Boshan Chen, Jinyan Su, Xingyao Wang, Jiaxin Pei, Manling Li

Budget-Aware AgentsLLM AgentsAgentic Reinforcement LearningTest-Time Compute

Trajectory2Task: Training Robust Tool-Calling Agents with Synthesized Yet Verifiable Data for Complex User Intents [PDF]
Ziyi Wang, Yuxuan Lu, Yimeng Zhang, Pei Chen, Ziwei Dong, Jing Huang, Jiri Gesi, Xianfeng Tang, Chen Luo, Qun Liu, Yisi Sang, Hanqing Lu, Manling Li, Jin Lai, Dakuo Wang

Tool-Calling AgentsVerifiable Data SynthesisComplex User IntentsMulti-Turn Tool UseAgent Fine-Tuning

Artificial Entanglement in the Fine-Tuning of Large Language Models [PDF]
Min Chen, Zihan Wang, Canyu Chen, Zeguan Wu, Manling Li, Junyu Liu

Parameter-Efficient Fine-TuningLoRA AnalysisEntanglement EntropyMatrix Product StatesRandom Matrix Theory

Adaptation of Agentic AI: A Survey of Post-Training, Memory, and Skills [PDF][Code]
Pengcheng Jiang*, Jiacheng Lin*, Zhiyi Shi*, Zifeng Wang, Luxi He, Yichen Wu, Ming Zhong, Peiyang Song, Qizheng Zhang, Heng Wang, Xueqiang Xu, Hanwen Xu, Pengrui Han, Dylan Zhang, Jiashuo Sun, Chaoqi Yang, Kun Qian, Tian Wang, Changran Hu, Manling Li, Quanzheng Li, Hao Peng, Sheng Wang, Jingbo Shang, Chao Zhang, Jiaxuan You, Liyuan Liu, Pan Lu, Yu Zhang, Heng Ji, Yejin Choi, Dawn Song, Jimeng Sun, Jiawei Han

Agent AdaptationTool AdaptationAgent MemoryAgent SkillsPost-Training Survey

ROSETTA: Constructing Code-Based Reward from Unconstrained Language Preference [Website][PDF][Data][Code][tl;dr]
Sanjana Srivastava*, Kangrui Wang*, Yung-Chieh Chan*, Tianyuan Dai, Manling Li, Ruohan Zhang, Mengdi Xu, Jiajun Wu, Li Fei-Fei
ICLR 2026
Best Paper Award at RSS 2025 on Continual Robot Learning from Humans

Reward ModelingCode-Based RewardsLanguage PreferencesAgentic Reinforcement Learning

RAGEN-2: Reasoning Collapse in Agentic Reinforcement Learning [Website][PDF][Code][Experimental Logs][tl;dr]
Zenus Wang*, Chi Gui*, Xing Jin*, Qineng Wang*, Licheng Liu*, Kangrui Wang, Shiqi Chen, Linjie Li, Zhengyuan Yang, Pingyue Zhang, Yiping Lu, Jiajun Wu, Li Fei-Fei, Lijuan Wang, Yejin Choi, Manling Li
ICML 2026 (Oral, Top 0.7%)
Best Paper Award at CVPR 2026 Workshop on Multimodal Reasoning for Agentic Intelligence (MMRAgI)
20 Papers That Matter at ICML 2026, selected by Nebius Science
Best Poster Award at MMLS 2025 (Midwest Machine Learning Symposium)
2.7k+ Github Stars, Featured by MIT Tech Review, Lambda Partner Spotlight, VentureBeat, Medium, AI News, MarkTechPost, Business Leaders Review, etc.

Agentic Reinforcement LearningMulti-Turn Reinforcement LearningLLM AgentsReasoning CollapseReinforcement Learning Training Stability

VAGEN: Reinforcing World Model Reasoning for Multi-Turn VLM Agents [Website][PDF][Blog][Code][tl;dr]
Kangrui Wang*, Pingyue Zhang*, Zihan Wang*, Yaning Gao*, Linjie Li*, Qineng Wang, Chi Wan, Hanyang Chen, Yiping Lu, Zhengyuan Yang, Lijuan Wang, Ranjay Krishna, Jiajun Wu, Li Fei-Fei, Yejin Choi, Manling Li
NeurIPS 2025
Featured by MIT Tech Review, Stanford AI Blog

World Model ReasoningWorld Model Reinforcement LearningMulti-Turn Reinforcement LearningRL for VisionVLM AgentsAgentic Reinforcement Learning

Federated Agent Reinforcement Learning [Website][PDF]
Canyu Chen, Kangyu Zhu, Zhaorun Chen, Zhanhui Zhou, Shizhe Diao, Yiping Lu, Tian Li, Manling Li+, Dawn Song+
NeurIPS 2026
Best Paper Award at AAAI 2026 Workshop on Trustworthy Agentic Systems
Outstanding Paper Award at AAAI 2026 Workshop on Personalization in the Era of Large Foundation Models

Federated LearningAgentic Reinforcement LearningLLM AgentsPrivacy-Preserving Training

WorldAgen: Unified State-Action Prediction with Test-Time World Model Training [PDF]
Chi Wan*, Kangrui Wang*, Yuan Si, Pingyue Zhang, Manling Li
AAAI 2026

World ModelsTest-Time TrainingState-Action PredictionEmbodied Agents

SyncMind: Measuring Agent Out-of-Sync Recovery in Collaborative Software Engineering [Website][PDF][Code][Data]
Xuehang Guo, Xingyao Wang, Yangyi Chen, Sha Li, Chi Han, Manling Li, Heng Ji
ICML 2025

Software Engineering AgentsAgent CollaborationLLM AgentsBenchmark

Internalizing World Models via Self-Play Finetuning for Agentic RL [PDF][Code]
Shiqi Chen, Tongyao Zhu, Zian Wang, Jinghan Zhang, Kangrui Wang, Siyang Gao, Teng Xiao, Yee Whye Teh, Junxian He, Manling Li
2025

World ModelsSelf-Play Fine-TuningAgentic Reinforcement LearningLLM Agents

ERA: Transforming VLMs into Embodied Agents via Embodied Prior Learning and Online Reinforcement Learning [Website][PDF][Code][Data]
Hanyang Chen, Mark Zhao, Rui Yang, Qinwei Ma, Ke Yang, Jiarui Yao, Kangrui Wang, Hao Bai, Zhenhailong Wang, Rui Pan, Mengchao Zhang, Jose Barreiros, Aykut Onol, ChengXiang Zhai, Heng Ji, Manling Li, Huan Zhang, Tong Zhang
2025

Embodied ReasoningReinforcement LearningRL for VisionEmbodied AgentsVLM Agents

Chain-of-Action: Faithful and Multimodal Question Answering through Large Language Models [PDF]
Zhenyu Pan, Haozheng Luo, Manling Li, Han Liu
ICLR 2025

Multimodal Question AnsweringFaithful ReasoningLLM AgentsRetrieval-Augmented Generation

Embodied Agent Interface: Benchmarking LLMs for Embodied Decision Making [Website][PDF][Code][Data][Docker][PyPi][Doc]
Manling Li^*, Shiyu Zhao^*, Qineng Wang^*, Kangrui Wang^*, Yu Zhou^*, Sanjana Srivastava, Cem Gokmen, Tony Lee, Li Erran Li, Ruohan Zhang, Weiyu Liu, Percy Liang, Li Fei-Fei, Jiayuan Mao, Jiajun Wu
NeurIPS 2024 Datasets and Benchmarks Track (Oral, Top 0.6%)
Best Paper Award at SoCal NLP 2024, Top 0.4%

Embodied Decision MakingLLM AgentsEmbodied AI BenchmarkReasoning and Planning

Non-Sequential Graph Script Induction via Multimedia Grounding [PDF]
Yu Zhou^†, Sha Li, Manling Li, Xudong Lin, Shih-Fu Chang, Mohit Bansal and Heng Ji
ACL 2023 (^† denotes supervised undergraduate)

Graph Script InductionProcedural KnowledgeMultimedia Grounding

A Language First Approach to Procedure Planning [PDF]
Jiateng Liu^†, Sha Li, Zhenhailong Wang, Manling Li, Heng Ji
ACL 2023 Findings (^† denotes supervised undergraduate)

Procedure PlanningTask PlanningLanguage Priors

Open-Domain Hierarchical Event Schema Induction by Incremental Prompting and Verification [PDF]
Sha Li, Ruining Zhao^†, Manling Li, Heng Ji, Chris Callison-Burch and Jiawei Han
ACL 2023 (^† denotes supervised undergraduate)

Event Schema InductionHierarchical SchemasLLM Prompting

Multimedia Generative Script Learning for Task Planning [PDF]
Qingyun Wang, Manling Li, Hou Pong Chan, Lifu Huang, Julia Hockenmaier, Girish Chowdhary and Heng Ji
ACL 2023 Findings

Script LearningTask PlanningProcedural Knowledge

Event Schema Induction with Double Graph Autoencoders [PDF][Code]
Xiaomeng Jin^†, Manling Li and Heng Ji
NAACL'22

Event Schema InductionGraph AutoencodersEvent Graphs

The Future is not One-dimensional: Complex Event Schema Induction by Graph Modeling for Event Prediction [PDF][Data]
Manling Li, Sha Li, Zhenhailong Wang, Lifu Huang, Kyunghyun Cho, Heng Ji, Jiawei Han and Clare Voss
EMNLP'21

Complex Event SchemasTemporal GraphsEvent Prediction

Connecting the Dots: Event Graph Schema Induction with Path Language Modeling [PDF][Code/Data]
Manling Li, Qi Zeng, Ying Lin, Kyunghyun Cho, Heng Ji, Jonathan May, Nathanael Chambers and Clare Voss
EMNLP'20: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing.

Event Schema InductionPath Language ModelingEvent Graphs