5 papers
ExpThink: Experience-Guided Reinforcement Learning for Adaptive Chain-of-Thought Compression
Tingcheng Bian, Yuzhe Zhang, Jing Jin +5
Large reasoning models (LRMs) achieve strong performance via extended chain-of-thought (CoT) reasoning, yet suffer from excessive token consumption and high inference latency. Exis…
Graph-Based Chain-of-Thought Pruning for Reducing Redundant Reflections in Reasoning LLMs
Hongyuan Yuan, Xinran He, Run Shao +6
Extending CoT through RL has been widely used to enhance the reasoning capabilities of LLMs. However, due to the sparsity of reward signals, it can also induce undesirable thinking…
Don't Act Blindly: Robust GUI Automation via Action-Effect Verification and Self-Correction
Yuzhe Zhang, Xianwei Xue, Xingyong Wu +8
Autonomous GUI agents based on vision-language models (VLMs) often assume deterministic environment responses, generating actions without verifying whether previous operations succ…
TRiMS: Real-Time Tracking of Minimal Sufficient Length for Efficient Reasoning via RL
Tingcheng Bian, Jinchang Luo, Mingquan Cheng +5
Large language models achieve breakthroughs in complex reasoning via long chain-of-thought sequences. However, this often leads to severe reasoning inflation, causing substantial c…
GlobalRAG: Enhancing Global Reasoning in Multi-hop Question Answering via Reinforcement Learning
Jinchang Luo, Mingquan Cheng, Fan Wan +7
Reinforcement learning has recently shown promise in improving retrieval-augmented generation (RAG). Despite these advances, its effectiveness in multi-hop question answering (QA)…