papers

Publications (21)

cs.LG2026

MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wild

Peng Xia, Jianwen Chen, Xinyu Yang +10

Large language model (LLM) agents are increasingly used for complex tasks, yet deployed agents often remain static, failing to adapt as user needs evolve. This creates a tension be…

cs.AI2026

Omni-SimpleMem: Autoresearch-Guided Discovery of Lifelong Multimodal Agent Memory

Jiaqi Liu, Zipeng Ling, Shi Qiu +9

AI agents increasingly operate over extended time horizons, yet their ability to retain, organize, and recall multimodal experiences remains a critical bottleneck. Building effecti…

cs.CV2025

MJ-VIDEO: Fine-Grained Benchmarking and Rewarding Video Preferences in Video Generation

Haibo Tong, Zhaoyang Wang, Zhaorun Chen +11

Recent advancements in video generation have significantly improved the ability to synthesize videos from text instructions. However, existing models still struggle with key challe…

cs.AI2026

Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning

Zhaoyang Wang, Canwen Xu, Boyi Liu +5

Recent advances in large language model (LLM) have empowered autonomous agents to perform multi-turn interactions with tools and environments. However, scaling such agent training…

cs.AI2026

AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration

Jiaqi Liu, Shi Qiu, Mairui Li +33

Automating scientific discovery requires more than generating papers from ideas. Real research is iterative: hypotheses are challenged from multiple perspectives, experiments fail…

cs.CV2026

VisualClaw: A Real-Time, Personalized Agent for the Physical World

Haoqin Tu, Jianwen Chen, Zijun Wang +14

Vision language models are serving as general-purpose interfaces for complex multimodal tasks. However, deployment still faces three gaps: VLMs typically incur high latency and cos…

cs.LG2024

Generating Chain-of-Thoughts with a Pairwise-Comparison Approach to Searching for the Most Promising Intermediate Thought

Zhen-Yu Zhang, Siwei Han, Huaxiu Yao +2

To improve the ability of the large language model (LLMs) to tackle complex reasoning problems, chain-of-thoughts (CoT) methods were proposed to guide LLMs to reason step-by-step,…

cs.LG2025

MDocAgent: A Multi-Modal Multi-Agent Framework for Document Understanding

Siwei Han, Peng Xia, Ruiyi Zhang +4

Document Question Answering (DocQA) is a very common task. Existing methods using Large Language Models (LLMs) or Large Vision Language Models (LVLMs) and Retrieval Augmented Gener…

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

SynthAgent: Adapting Web Agents with Synthetic Supervision

Zhaoyang Wang, Yiming Liang, Xuchao Zhang +9

Web agents struggle to adapt to new websites due to the scarcity of environment specific tasks and demonstrations. Recent works have explored synthetic data generation to address t…

cs.AI2025

From EduVisBench to EduVisAgent: A Benchmark and Multi-Agent Framework for Reasoning-Driven Pedagogical Visualization

Haonian Ji, Shi Qiu, Siyang Xin +5

While foundation models (FMs), such as diffusion models and large vision-language models (LVLMs), have been widely applied in educational contexts, their ability to generate pedago…

cs.CL2026

Strategic Navigation or Stochastic Search? How Agents and Humans Reason Over Document Collections

Łukasz Borchmann, Jordy Van Landeghem, Michał Turski +12

Multimodal agents offer a promising path to automating complex document-intensive workflows. Yet, a critical question remains: do these agents demonstrate genuine strategic reasoni…

cs.CV2025

Agent0-VL: Exploring Self-Evolving Agent for Tool-Integrated Vision-Language Reasoning

Jiaqi Liu, Kaiwen Xiong, Peng Xia +6

Vision-language agents have achieved remarkable progress in a variety of multimodal reasoning tasks; however, their learning remains constrained by the limitations of human-annotat…

cs.CV2025

GLIMPSE: Do Large Vision-Language Models Truly Think With Videos or Just Glimpse at Them?

Yiyang Zhou, Linjie Li, Shi Qiu +10

Existing video benchmarks often resemble image-based benchmarks, with question types like "What actions does the person perform throughout the video?" or "What color is the woman's…

cs.RO2025

GRAPE: Generalizing Robot Policy via Preference Alignment

Zijian Zhang, Kaiyuan Zheng, Zhaorun Chen +7

Despite the recent advancements of vision-language-action (VLA) models on a variety of robotics tasks, they suffer from critical issues such as poor generalizability to unseen task…

cs.CV2025

MMIE: Massive Multimodal Interleaved Comprehension Benchmark for Large Vision-Language Models

Peng Xia, Siwei Han, Shi Qiu +9

Interleaved multimodal comprehension and generation, enabling models to produce and interpret both images and text in arbitrary sequences, have become a pivotal area in multimodal…

cs.LG2026

Alignment Tipping Process: How Self-Evolution Pushes LLM Agents Off the Rails

Siwei Han, Kaiwen Xiong, Jiaqi Liu +9

As Large Language Model (LLM) agents increasingly gain self-evolutionary capabilities to adapt and refine their strategies through real-world interaction, their long-term reliabili…

cs.LG2026

SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning

Peng Xia, Jianwen Chen, Hanyang Wang +10

Large Language Model (LLM) agents have shown stunning results in complex tasks, yet they often operate in isolation, failing to learn from past experiences. Existing memory-based m…

cs.CV2025

ReAgent-V: A Reward-Driven Multi-Agent Framework for Video Understanding

Yiyang Zhou, Yangfan He, Yaofeng Su +5

Video understanding is fundamental to tasks such as action recognition, video reasoning, and robotic control. Early video understanding methods based on large vision-language model…

cs.AI2026

SimpleMem: Efficient Lifelong Memory for LLM Agents

Jiaqi Liu, Yaofeng Su, Peng Xia +5

To support long-term interaction in complex environments, LLM agents require memory systems that manage historical experiences. Existing approaches either retain full interaction h…

cs.CV2026

SimpleOCR: Rendering Visualized Questions to Teach MLLMs to Read

Yibo Peng, Peng Xia, Ding Zhong +6

Despite the rapid advancements in Multimodal Large Language Models (MLLMs), a critical question regarding their visual grounding mechanism remains unanswered: do these models genui…