2 citations · 4 across the 10 of their papers we have counts for
12 papers
Playing social deduction games with reinforcement fine-tuned large language models
Lingzhe Zhang, Yunpeng Zhai, Tong Jia +7
Reinforcement fine-tuning (RFT) is increasingly used in applications where large language models (LLMs) interact with humans and other agents. Here we use social deduction games to…
EAVer: Long-Form Factuality Verification as an End-to-End Agentic Policy
Kening Zheng, Aoying Zheng, Zhigang Chang +21
Long-form factuality verification is commonly implemented as a static decompose-search-verify pipeline, with separately prompted modules processing claims and invoking external sea…
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 that under privileged context, typically…
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…
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…
Hypothesize-Then-Verify: Speculative Root Cause Analysis for Microservices with Pathwise Parallelism
Lingzhe Zhang, Tong Jia, Yunpeng Zhai +5
Microservice systems have become the backbone of cloud-native enterprise applications due to their resource elasticity, loosely coupled architecture, and lightweight deployment. Ye…
Agentic Memory Enhanced Recursive Reasoning for Root Cause Localization in Microservices
Lingzhe Zhang, Tong Jia, Yunpeng Zhai +5
As contemporary microservice systems become increasingly popular and complex-often comprising hundreds or even thousands of fine-grained, interdependent subsystems-they are experie…
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…
A Survey on Parallel Text Generation: From Parallel Decoding to Diffusion Language Models
Lingzhe Zhang, Liancheng Fang, Chiming Duan +8
As text generation has become a core capability of modern Large Language Models (LLMs), it underpins a wide range of downstream applications. However, most existing LLMs rely on au…
Omni-SafetyBench: A Benchmark for Safety Evaluation of Audio-Visual Large Language Models
Leyi Pan, Zheyu Fu, Yunpeng Zhai +9
Omni-modal Large Language Models (OLLMs) that integrate visual, auditory, and textual processing face severe safety risks. They exhibit fragile defenses against audio-visual joint…