1 citations · 1 across the 15 of their papers we have counts for
20 papers
TPPO: Tracking-Value PPO For Language Model Reasoning
Futing Wang, Chenxi Li, Jianhao Yan +6
Proximal Policy Optimization (PPO) is widely used in reinforcement learning with verifiable rewards for language-model reasoning. While \emph{value evolution along trajectory} char…
AdaStep: Adaptive Step Credit Weighting for Agentic Reinforcement Learning
Xin Wang, Wenhao Wu, Menghao Zhang +3
Long-horizon LLM agents are typically trained with sparse outcome rewards, making trajectory-level objectives too coarse to distinguish the contribution of individual decisions. St…
TRACE: A Self-Evolving Skill Bank for Consistent, Limit-Aware LLM Agents
Wenhao Wu, Menghao Zhang, Xin Wang +3
Reliable deployment of LLM agents in user-facing products depends not on raw task-solving ability but on consistency and limit-awareness: behaving the same way across repeated tria…
MemFuse: Multi-Source Memory Fusion from Fragmented Observations
Chao Li, Yuanfa Li, Wenhao Wu +3
Long-term memory is essential for agents that operate across extended interactions, yet existing memory systems and benchmarks predominantly focus on single-source textual historie…
OpenVisTool: An Open Recipe for Synthesizing Instructive Visual Tool-Use Trajectories
Changhao Xiang, Shilin Zhang, Zheng Ma +8
Visual tool use has emerged as a fundamental capability for multimodal agents to actively acquire evidence beyond a fixed image encoding. The prevailing recipe learns this capabili…
FailForge: Distilling Procedural Competence from Persistent Failures into Code Agents
Dongyi Lv, Fushun E, Aichen Cai +8
Rejection sampling fine-tuning (RFT) is widely used to train code agents by generating trajectories on verifiable software engineering tasks, retaining those that pass the tests, a…
Look Before You Leap: Distilling Tree Search into Action Evaluation for Frozen VLA Models
Xinyi Xie, Zican Hu, Zhanyu Liu +7
Vision-Language-Action (VLA) models acquire broad embodied capabilities through large-scale pretraining, yet their generalization remains far more fragile than that of LLMs and VLM…
Bridging Interleaved Multi-Modal Reasoning as a Unified Decision Process
Zican Hu, Xuyang Hu, Yiming Liu +10
Unified multi-modal models (UMMs) have shown promising interleaved text-image reasoning capabilities, yet effectively optimizing such multi-turn generation via reinforcement learni…
Beyond Compilation: Evaluating Faithful Natural-Language-to-Lean Statement Formalization
Ke Zhang, Patricio Gallardo Candela, Sudhir Murthy +3
Lean verifies that a generated declaration is well typed, but cannot check whether it states what the user intended. We measure how far compilation overstates faithfulness in state…
FailureMem: A Failure-Aware Multimodal Framework for Autonomous Software Repair
Ruize Ma, Yilei Jiang, Shilin Zhang +7
Multimodal Automated Program Repair (MAPR) extends traditional program repair by requiring models to jointly reason over source code, textual issue descriptions, and visual artifac…
From Conflict to Consensus: Boosting Medical Reasoning via Multi-Round Agentic RAG
Wenhao Wu, Zhentao Tang, Yafu Li +5
Large Language Models (LLMs) exhibit high reasoning capacity in medical question-answering, but their tendency to produce hallucinations and outdated knowledge poses critical risks…
Think Longer to Explore Deeper: Learn to Explore In-Context via Length-Incentivized Reinforcement Learning
Futing Wang, Jianhao Yan, Yun Luo +6
Achieving effective test-time scaling requires models to engage in In-Context Exploration -- the intrinsic ability to generate, verify, and refine multiple reasoning hypotheses wit…
New Skills or Sharper Primitives? A Probabilistic Perspective on the Emergence of Reasoning in RLVR
Zhilin Wang, Yafu Li, Shunkai Zhang +4
Whether Reinforcement Learning with Verifiable Rewards (RLVR) endows Large Language Models (LLMs) with new capabilities or merely elicits latent traces remains a central debate. In…
Characterizing, Evaluating, and Optimizing Complex Reasoning
Haoran Zhang, Yafu Li, Zhi Wang +4
Large Reasoning Models (LRMs) increasingly rely on reasoning traces with complex internal structures. However, existing work lacks a unified answer to three fundamental questions:…
ExGRPO: Learning to Reason from Experience
Runzhe Zhan, Yafu Li, Zhi Wang +5
Reinforcement learning from verifiable rewards (RLVR) is an emerging paradigm for improving the reasoning ability of large language models. However, standard on-policy training dis…
Diversity-Incentivized Exploration for Versatile Reasoning
Zican Hu, Shilin Zhang, Yafu Li +7
Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a crucial paradigm for incentivizing reasoning capabilities in Large Language Models (LLMs). Due to vast state-…
Mixture-of-Experts Meets In-Context Reinforcement Learning
Wenhao Wu, Fuhong Liu, Haoru Li +4
In-context reinforcement learning (ICRL) has emerged as a promising paradigm for adapting RL agents to downstream tasks through prompt conditioning. However, two notable challenges…
The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models
Ganqu Cui, Yuchen Zhang, Jiacheng Chen +14
This paper aims to overcome a major obstacle in scaling RL for reasoning with LLMs, namely the collapse of policy entropy. Such phenomenon is consistently observed across vast RL r…
Text-to-Decision Agent: Offline Meta-Reinforcement Learning from Natural Language Supervision
Shilin Zhang, Zican Hu, Wenhao Wu +7
Offline meta-RL usually tackles generalization by inferring task beliefs from high-quality samples or warmup explorations. The restricted form limits their generality and usability…
Learning to Reason under Off-Policy Guidance
Jianhao Yan, Yafu Li, Zican Hu +5
Recent advances in large reasoning models (LRMs) demonstrate that sophisticated behaviors such as multi-step reasoning and self-reflection can emerge via reinforcement learning wit…