8 papers
InterTab: Interleaved Visual-Structure Alignment for Multi-Modal Table Reasoning
Hanqian Li, Sirui Huang, Chen Ling +12
Table images preserve structural information that are often lost in text serialization, and reasoning over them requires locating relevant rows, columns, and cells step by step. Cu…
Design the Feedback, Not Just the Reward: Environments for Open-Ended Reinforcement Learning
Rui Jin, Jikai Chen, Yihan Chen +7
Reinforcement learning has advanced large language models on tasks with reliable verifiers, where checking an outcome provides a clear basis for reward. Extending this approach to…
Last Step Matters: Early Uncertainty Cannot Predict Failure in Long-Horizon Agents
Zongyue Li, Chengyue Yu, Lei Zang +3
Early failure prediction is important for long-horizon agents, as it enables timely intervention and can reduce inference and tool-use costs. Uncertainty quantification, such as ve…
MetaRAG: Belief-Action Aligned Policy Optimization for Agentic RAG
Qiuyi Qi, Tian Liang, Jiamu Wang +7
Agentic retrieval-augmented generation (RAG) requires language models to decide when to continue searching and when to answer. Existing RL-based methods rely on external supervisio…
Teach the Magnitude, Not the Direction: Verifier-Anchored Credit Assignment for Multi-Turn Multi-Step LLM Agents
Zechuan Wang, Siyuan Lu, Hongxuan Zhang +3
Reinforcement learning with verifiable rewards (RLVR) directly optimizes verifier-defined outcomes for multi-turn tool-use agents, yet its trajectory-level credit assignment confla…
Debias in Text, Believe Your Eyes: Text-Anchored Cross-Modal Transfer for Visual Counter-Commonsense Reasoning
Chen Ling, Hanqian Li, Dongnan Liu +9
The visual reasoning ability of multimodal large language models (MLLMs) is crucial for downstream applications, particularly counter-commonsense reasoning, which requires models t…
STAPO: Selective Trajectory-Aware Policy Optimization for LLM Agent Training
Qiuyi Qi, Tian Liang, Mutian Bao +8
Reinforcement Learning (RL) is the dominant paradigm for training Large Language Model (LLM) agents on long-horizon tasks. However, sparse and delayed rewards often lead to traject…
CARL: Constraint-Aware Reinforcement Learning for Planning with LLMs
Qiuyi Qi, Jinjian Zhang, Mutian Bao +9
Despite their strong reasoning capabilities and extensive world knowledge, Large Language Models (LLMs) frequently generate plans that violate task constraints, undermining their r…