10 papers
RLCSD: Reinforcement Learning with Contrastive On-Policy Self-Distillation
Leyi Pan, Shuchang Tao, Yunpeng Zhai +5
On-policy self-distillation (OPSD) provides dense, token-level supervision for reasoning models by aligning a model's own distribution with the distribution it produces under privi…
How Much Parallelism Is "Free"? A Principle of Near-Free Parallelism for Parallel Decoding
Minghua He, Lingzhe Zhang, Yuan Liu +2
Parallel decoding improves generation efficiency by processing multiple decode positions within a single decode forward, but reported speedups conflate algorithmic token utilizatio…
d-TreeRPO: Towards More Reliable Policy Optimization for Diffusion Language Models
Leyi Pan, Shuchang Tao, Yunpeng Zhai +8
Reinforcement learning (RL) is pivotal for enhancing the reasoning capabilities of diffusion large language models (dLLMs). However, existing dLLM policy optimization methods suffe…
E2E-REME: Towards End-to-End Microservices Auto-Remediation via Experience-Simulation Reinforcement Fine-Tuning
Lingzhe Zhang, Yunpeng Zhai, Tong Jia +5
Contemporary microservice systems continue to grow in scale and complexity, leading to increasingly frequent and costly failures. While recent LLM-based auto-remediation approaches…
Efficient Failure Management for Multi-Agent Systems with Reasoning Trace Representation
Lingzhe Zhang, Tong Jia, Mingyu Wang +9
Large Language Models (LLM)-based Multi-Agent Systems (MASs) have emerged as a new paradigm in software system design, increasingly demonstrating strong reasoning and collaboration…
RuntimeSlicer: Towards Generalizable Unified Runtime State Representation for Failure Management
Lingzhe Zhang, Tong Jia, Weijie Hong +9
Modern software systems operate at unprecedented scale and complexity, where effective failure management is critical yet increasingly challenging. Metrics, traces, and logs provid…