4 papers · 1 filter
Latent Thought Credit: Multi-Answer Credit Assignment for Latent Reasoning
Xuyang Zhao, Liting Zhang, Zichen Xu +4
Latent reasoning allows language models to carry out intermediate reasoning in continuous latent representations rather than fully externalizing it as discrete chains of thought. H…
Is More Privileged Information Better? From Solution Traces to Problem-Solving Structure in Self-Distilled Reasoning
Xuyang Zhao, Liting Zhang, Zichen Xu +4
On-policy self-distillation (OPSD) improves reasoning by using a privileged view of a model conditioned on reference solutions to supervise a student view that observes only the qu…
AgentCDM: Enhancing Multi-Agent Collaborative Decision-Making via ACH-Inspired Structured Reasoning
Xuyang Zhao, Shiwan Zhao, Hualong Yu +2
Multi-agent systems (MAS) powered by large language models (LLMs) hold significant promise for solving complex decision-making tasks. However, the core process of collaborative dec…
SDPO: Segment-Level Direct Preference Optimization for Social Agents
Aobo Kong, Wentao Ma, Shiwan Zhao +7
Social agents powered by large language models (LLMs) can simulate human social behaviors but fall short in handling complex social dialogues. Direct Preference Optimization (DPO)…