collaborators

9 papers

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

OPT-BENCH: Evaluating the Iterative Self-Optimization of LLM Agents in Large-Scale Search Spaces

Xiaozhe Li, Jixuan Chen, Xinyu Fang +4

Large Language Models (LLMs) have demonstrated remarkable capabilities in reasoning and tool use. However, the fundamental cognitive faculties essential for problem solving, includ…

cs.CL2026

Timely Machine: Awareness of Time Makes Test-Time Scaling Agentic

Yichuan Ma, Linyang Li, Yongkang chen +5

As large language models (LLMs) increasingly tackle complex reasoning tasks, test-time scaling has become critical for enhancing capabilities. However, in agentic scenarios with fr…

cs.CL2026

TL-GRPO: Turn-Level RL for Reasoning-Guided Iterative Optimization

Peiji Li, Linyang Li, Handa Sun +15

Large language models have demonstrated strong reasoning capabilities in complex tasks through tool integration, which is typically framed as a Markov Decision Process and optimize…