25 papers
InfoPO: Information-Driven Policy Optimization for User-Centric Agents
Fanqi Kong, Jiayi Zhang, Mingyi Deng +3
Real-world user requests to LLM agents are often underspecified. Agents must interact to acquire missing information and make correct downstream decisions. However, current multi-t…
MedicalAgentsBench for Complex Medical Reasoning: Comparing Internalized Reasoning Models versus Externalized Agent-based Frameworks
Yanjun Shao, Xiangru Tang, Jiwoong Sohn +10
Complex medical reasoning requires integrating heterogeneous clinical evidence across multiple inference steps. Large language models (LLMs) now approach this through two routes: i…
The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook
Xinlei Yu, Zhangquan Chen, Yongbo He +36
Latent space is rapidly emerging as a native substrate for language-based models. While modern systems are still commonly understood through explicit token-level generation, an inc…
Multi-Rollout On-Policy Distillation via Peer Successes and Failures
Weichen Yu, Xiaomin Li, Yizhou Zhao +8
Large language models are often post-trained with sparse verifier rewards, which indicate whether a sampled trajectory succeeds but provide limited guidance about where reasoning s…
Self-Trained Verification for Training- and Test-Time Self-Improvement
Chen Henry Wu, Aditi Raghunathan
Self-improvement at scale has been a longstanding goal for reasoning models, and there are two natural places to do it: at test time, through verification-refinement (V-R) loops; a…
StepOPSD: Step-Aware Online Preference Distillation for Agent Reinforcement Learning
Yanfei Zhang, Xu Lin, Chenglin Wu
Reinforcement learning for multi-turn agents suffers from a credit-assignment mismatch: rewards are sparse and trajectory-level, while success often hinges on a few local decisions…