5 papers
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…
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…
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…
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…
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…