Min Zhang
6 papers · Latest:
CoCoReviewBench: A Completeness- and Correctness-Oriented Benchmark for AI Reviewers
CoCoReviewBench is a new benchmark for AI reviewers, focusing on completeness and correctness by curating 3,900 papers with expert annotations.
MASPO: Joint Prompt Optimization for LLM-based Multi-Agent Systems
MASPO optimizes prompts for LLM multi-agent systems by jointly evaluating their impact on successor agents, improving collaborative task performance.
DMGD: Train-Free Dataset Distillation with Semantic-Distribution Matching in Diffusion Models
DMGD introduces a train-free diffusion-based dataset distillation framework using dual semantic and distribution matching, outperforming SOTA methods.
Taming Actor-Observer Asymmetry in Agents via Dialectical Alignment
This paper introduces ReTAS, a new method to mitigate Actor-Observer Asymmetry in LLM agents by enforcing perspective-invariant reasoning.
OGER: A Robust Offline-Guided Exploration Reward for Hybrid Reinforcement Learning
OGER is a new framework that enhances LLM exploration in RLVR by unifying offline guidance and online RL with an entropy-aware reward.
E3-TIR: Enhanced Experience Exploitation for Tool-Integrated Reasoning
E3-TIR enhances LLM tool-integrated reasoning by efficiently exploiting diverse experiences, achieving better performance with less data.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.