activity
20242026
collaborators
Showing cs.LGShow all

16 papers · 1 filter

cs.LG2026

Position: The Hidden Costs and Measurement Gaps of Reinforcement Learning with Verifiable Rewards

Fang Wu, Aaron Tu, Weihao Xuan +21

Reinforcement learning with verifiable rewards (RLVR) is a practical, scalable way to improve large language models on math, code, and other structured tasks. However, we argue tha…

cs.LG2026

ClawArena: Benchmarking AI Agents in Evolving Information Environments

Haonian Ji, Kaiwen Xiong, Siwei Han +9

AI agents deployed as persistent assistants must maintain correct beliefs as their information environment evolves. In practice, evidence is scattered across heterogeneous sources…

cs.LG2026

EvolveMem:Self-Evolving Memory Architecture via AutoResearch for LLM Agents

Jiaqi Liu, Xinyu Ye, Peng Xia +4

Long-term memory is essential for LLM agents that operate across multiple sessions, yet existing memory systems treat retrieval infrastructure as fixed: stored content evolves whil…

cs.LG2026

NoiseRater: Meta-Learned Noise Valuation for Diffusion Model Training

Fang Wu, Haokai Zhao, Da Xing +17

Diffusion models have achieved remarkable success across a wide range of generative tasks, yet their training paradigm largely treats injected noise as uniformly informative. In th…

cs.LG2026

Proteo-R1: Reasoning Foundation Models for De Novo Protein Design

Fang Wu, Weihao Xuan, Heli Qi +26

Deep learning in de novo protein design has achieved atomic-level fidelity. However, existing models remain largely non-deliberative: they directly synthesize molecular geometries…

cs.LG2026

MedVerse: Efficient and Reliable Medical Reasoning via DAG-Structured Parallel Execution

Jianwen Chen, Xinyu Yang, Peng Xia +7

Large language models (LLMs) have demonstrated strong performance and rapid progress in a wide range of medical reasoning tasks. However, their sequential autoregressive decoding f…