collaborators

5 papers

cs.LG2026

Policy-Conditioned Counterfactual Credit for Verifiable Reinforcement Learning of Long-Horizon Language Agents

Renwei Meng

Reinforcement learning with verifiable rewards improves reasoning and tool use, yet long-horizon language agents still learn unsupported evidence chains, belief drift, and shortcut…

cs.SE2026

VulnAgent-R2: Evidence-Calibrated Multi-Agent Auditing for Repository-Level Vulnerability Detection

Renwei Meng, Haoyi Wu, Jingming Wang

Software vulnerabilities often depend on cross-file data flow, build options, framework conventions, and runtime guards, so isolated function classifiers produce fragile and poorly…

cs.CL2026

Know2Guess: A Contamination-Aware Multi-Zone Benchmark for Knowledge-Boundary Evaluation in Large Language Models

Renwei Meng, Bowen Zhang, Jian Wang +4

Reliable evaluation of large language models should separate supported answering from unsupported guessing without conflating either with data contamination, prompt idiosyncrasy, o…

cs.LG2026

Group Resonance Network: Learnable Prototypes and Multi-Subject Resonance for EEG Emotion Recognition

Renwei Meng

Electroencephalography(EEG)-basedemotionrecognitionre- mains challenging in cross-subject settings due to severe inter-subject variability. Existing methods mainly learn subject-in…

cs.AI2026

Explainable Innovation Engine: Dual-Tree Agent-RAG with Methods-as-Nodes and Verifiable Write-Back

Renwei Meng

Retrieval-augmented generation (RAG) improves factual grounding, yet most systems rely on flat chunk retrieval and provide limited control over multi-step synthesis. We propose an…