PPL
Xiaozhe Li
Papers (4)
Beyond Mode Collapse: Distribution Matching for Diverse ReasoningWhat and When to Distill: Selective Hindsight Distillation for Multi-Turn AgentsForge: Quality-Aware Reinforcement Learning for NP-Hard Optimization in LLMsOPT-BENCH: Evaluating the Iterative Self-Optimization of LLM Agents in Large-Scale Search Spaces