activity
20242026
collaborators

24 papers

cs.AI2026

AgentHPOBench: A Benchmark For Evaluating LLM Agents as Sequential Hyperparameter Optimizers

Tianyu Huai, Tingshuo Fan, Xinchi Chen +5

As LLMs evolve from code completion systems into autonomous scientific agents, evaluating their ability to conduct experiments has become increasingly important. Existing benchmark…

cs.RO2026

Two Bridges, One Pathway: From VLMs to Generalizable VLAs with Embodied Trajectory-Coupled Data

Linqi Yin, Shiduo Zhang, Shenling Qiu +11

Vision-language models (VLMs) are powerful general-purpose reasoners, yet converting them into robot control policies (VLAs) is surprisingly difficult. The root cause is a two-fold…

cs.CL2026

SciAgentGym: Benchmarking Multi-Step Scientific Tool-use in LLM Agents

Yujiong Shen, Yajie Yang, Zhiheng Xi +17

Scientific reasoning inherently demands integrating sophisticated toolkits to navigate domain-specific knowledge. Yet, current benchmarks largely overlook agents' ability to orches…

cs.CL2026

AdaptR1: Reinforcement Learning Based Adaptive Interleaved Thinking in Multi-hop Question Answering

Yuxin Wang, Jiahao Lu, Qifeng Wu +5

Large Language Models (LLMs) have achieved remarkable performance in complex reasoning tasks through Chain-of-Thought (CoT) prompting. However, this approach often leads to ``over-…

cs.CV2026

Thinking with Video: Video Generation as a Promising Multimodal Reasoning Paradigm

Jingqi Tong, Yurong Mou, Hangcheng Li +11

The "Thinking with Text" and "Thinking with Images" paradigms significantly improve the reasoning abilities of large language models (LLMs) and Vision-Language Models (VLMs). Howev…

cs.CV2026

Beyond Attention Magnitude: Leveraging Inter-layer Rank Consistency for Efficient Vision-Language-Action Models

Peiju Liu, Jinming Liu, Xipeng Qiu +1

Vision-Language-Action (VLA) models excel in robotic manipulation but suffer from significant inference latency due to processing dense visual tokens. Existing token reduction meth…