activity
20242026
collaborators

18 papers

cs.CV2026

MIRA: Medical Image Reflection for Agentic Diagnosis

Shengzhi Wang, Jun Yang, Kai Wu +11

Medical visual agents can use tools to inspect images and retrieve external knowledge, but indiscriminate tool use may introduce noisy or misleading evidence. Reliable diagnosis th…

cs.RO2026

Action from Adjacent Set in Physical Space Outperforms the Best Prediction in World Models

Liangyu Li, Qingwen Liu, Mingqing Liu

Controllers based on sampling and latent world models assign a predicted terminal cost to each candidate action sequence, choose the minimum, execute its first action block, and re…

cs.LG2026

Beyond Euclidean Proximity: Repairing Latent World Models with Horizon-Matched Trajectory Reachability Metrics

Liangyu Li, Shengzhi Wang, Qingwen Liu

Latent world models can contain the state needed for control, yet their terminal-cost interface can expose the planner to the wrong decision-relevant information. In common latent…

cs.AI2026

Beyond Mode Collapse: Distribution Matching for Diverse Reasoning

Xiaozhe Li, Yang Li, Xinyu Fang +10

On-policy reinforcement learning methods like GRPO suffer from mode collapse: they exhibit reduced solution diversity, concentrating probability mass on a single solution once disc…

cs.AI2026

Forge: Quality-Aware Reinforcement Learning for NP-Hard Optimization in LLMs

Xiaozhe Li, Xinyu Fang, Shengyuan Ding +5

Large Language Models (LLMs) have achieved remarkable success on reasoning benchmarks through Reinforcement Learning with Verifiable Rewards (RLVR), excelling at tasks such as math…

cs.AI2026

OPT-BENCH: Evaluating the Iterative Self-Optimization of LLM Agents in Large-Scale Search Spaces

Xiaozhe Li, Jixuan Chen, Xinyu Fang +4

Large Language Models (LLMs) have demonstrated remarkable capabilities in reasoning and tool use. However, the fundamental cognitive faculties essential for problem solving, includ…