PPL
Shengyuan Ding
Papers (4)
Beyond Mode Collapse: Distribution Matching for Diverse ReasoningWildClawBench: A Benchmark for Real-World, Long-Horizon Agent EvaluationForge: Quality-Aware Reinforcement Learning for NP-Hard Optimization in LLMsOPT-BENCH: Evaluating the Iterative Self-Optimization of LLM Agents in Large-Scale Search Spaces