11 papers
: Discrete Diffusion with Regulation Reinforcement for Single-Cell Perturbation Prediction
Ninghan Fan, Qi Liu, Xunuo Zhu +9
Predicting single-cell transcriptomic responses to genetic perturbations is central to functional genomics and virtual-cell modeling. Existing approaches, however, typically predic…
CARE: Confidence-Aware Reasoning for Reliable Medical VQA
Yuetian Du, Yucheng Wang, Zhenyuan Chen +9
Reinforcement Fine-Tuning (RFT) has enabled medical Multimodal Large Language Models (MLLMs) to produce Chain-of-Thought (CoT) reasoning for visual question answering, yet these mo…
Living-Harness Is an Interactive-Agent Evolver
Yuetian Du, Yucheng Wang, He Xu +9
The paper introduces Living-Harness, a self‑evolving harness for large language model agents that updates procedural knowledge from episode feedback, enabling the agent to avoid re…
LOTAPO: Leave-One-Turn Attribution for Self-Generated Process Rewards in Multi-Turn Search Reasoning
Qiang Zhu, Jiajun Wu, Longyi Wang
Reinforcement learning for multi-turn search reasoning typically relies on terminal outcome rewards, which cannot distinguish useful, redundant, and harmful intermediate interactio…
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…