Skip to content

Author

Chengyu Wang

We have 7 of 159 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

See it, Say it, Sorted: Mechanistic Diagnosis and Parameter-Space Mitigation of Emergent Misalignment in LLMs

A dynamic, second-order geometric study of EM is presented, which introduces a parameter-level Geometric Mitigation Framework that orthogonally projects empirical harmful gradient subspace out of parameter updates and unmask the illusion of behavioral safety.

Wei-Qiao Que, Rui-Zhe Li, Cheng-Yu Wang et al. · 0 citations
#artificial intelligence Preprint Sep 2026

Not All Prompts Are Equal: Exploration-Guided Prompt Scaffolding for Multimodal Reinforcement Post-Training

Training prompts in online reinforcement learning (RL) differ substantially in how informative they are for the current policy: some are already saturated while others are too difficult to yield reliable learning signals, yet both receive equal rollout budget under standard training. We propose an exploration-guided pr...

Yuan-Hao Yue, Qianli Ma, Cheng-Yu Wang et al. · 0 citations
Preprint Aug 2026

Beyond Solution-Centric Search: Adaptive Inquiry and Knowledge Revision for Autonomous ML Engineering

Long-horizon autonomous research tasks such as machine learning engineering require systems to make interdependent decisions under a limited budget. Existing LLM-based agents typically organize candidate-solution improvement through tree, graph, or chain structures, meaning that the search process determines how inform...

Shaokang Fu, Yulong Tao, Linbo Jin et al. · 1 citation
Book Open access Aug 2026

Self-Evolutionary Reinforced Knowledge Distillation for Multi-Modal Tool-Use Agents

A two-stage self-evolutionary knowledge distillation framework that equips small MLLMs with robust and adaptive tool-use behaviors and introduces weighted semantic objectives and iteratively expand competence through error-driven optimization, hybrid experience replay, and group-relative policy refinement with multi-di...

Lei Shen, Cheng-Yu Wang, Yuanjie Lyu et al. · 0 citations
Book Open access Aug 2026

Self-Evolutionary Reinforced Knowledge Distillation for Multi-Modal Tool-Use Agents

Autonomous multi-modal agents are increasingly important in real-world applications due to their ability to reason about complex environments and orchestrate tool use. However, deploying multi-modal large language models (MLLMs) for tool use is often constrained by computational cost and inference latency, creating a p...

Lei Shen, Chengyu Wang, Yuanjie Lyu et al. · 0 citations
Jul 2026

MerchantBench: Benchmarking LLM Agents for Long-Term Coherence in E-Commerce Operations

Large language model agents are increasingly evaluated as autonomous tool users, yet most benchmarks focus on bounded tasks with immediate success criteria. Real-world deployments often require Long-Term Coherence, the capacity to preserve purposeful behavior across extended horizons while adapting decisions to accumul...

Qi-Ming Shi, Yulong Tao, Linbo Jin et al. · 2 citations
Preprint Aug 2026

Bidirectional Context Self-Distillation for Reinforcement Learning of Skill-Based LLM Agents

This work proposes BCSD (Bidirectional Context Self-Distillation), a framework that combines self-distillation with reinforcement learning to train LLM agents to use external skills more effectively, enabling agents to utilize external skills more effectively.

Tian Pan, Yuan Li, Hong-Da Wang et al. · 1 citation

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.