collaborators
Showing cs.AIShow all

5 papers · 1 filter

cs.AI2026

Beyond Mode Collapse: Distribution Matching for Diverse Reasoning

Xiaozhe Li, Yang Li, Xinyu Fang +10

On-policy reinforcement learning methods like GRPO suffer from mode collapse: they exhibit reduced solution diversity, concentrating probability mass on a single solution once disc…

cs.AI2026

What and When to Distill: Selective Hindsight Distillation for Multi-Turn Agents

Xiaozhe Li, Tianyi Lyu, Yang Li +6

Reinforcement learning can train LLM agents from sparse task rewards, but long-horizon credit assignment remains challenging: a single success-or-failure signal must be distributed…

cs.AI2026

Forge: Quality-Aware Reinforcement Learning for NP-Hard Optimization in LLMs

Xiaozhe Li, Xinyu Fang, Shengyuan Ding +5

Large Language Models (LLMs) have achieved remarkable success on reasoning benchmarks through Reinforcement Learning with Verifiable Rewards (RLVR), excelling at tasks such as math…

cs.AI2026

COSMO-Agent: Tool-Augmented Agent for Closed-loop Optimization,Simulation,and Modeling Orchestration

Liyuan Deng, Shujian Deng, Yongkang Chen +6

Iterative industrial design-simulation optimization is bottlenecked by the CAD-CAE semantic gap: translating simulation feedback into valid geometric edits under diverse, coupled c…

cs.AI2026

Tool-Augmented Agent for Closed-loop Optimization,Simulation,and Modeling Orchestration

Liyuan Deng, Shujian Deng, Yongkang Chen +6

Iterative industrial design-simulation optimization is bottlenecked by the CAD-CAE semantic gap: translating simulation feedback into valid geometric edits under diverse, coupled c…