11 papers
RSIPO: Recursive Self-Improving Policy Optimization for Agentic Reinforcement Learning via Skill-Policy Co-Evolution
Fan Zhang, Hao Wu, Jinyang Wu +7
Recent focus in agentic reinforcement learning (RL) seeks to improve credit assignment in long-horizon tasks. One promising direction combines reinforcement learning with verifiabl…
UniMem: Complementary Episodic-to-Parametric Memory for Boundary-Agnostic Task Streams
Siyu Xia, Chenheng Zhang, Yanting Wu +8
Memory is essential for LLM agents to accumulate task experience and reuse task-specific execution strategies. However, real-world deployment over boundary-agnostic and evolving ta…
BrainPilot: Automating Brain Discovery with Agentic Research
Haoxuan Li, Tianci Gao, Jianhe Li +13
Understanding the brain increasingly depends on integrating evidence across scales, modalities, and disciplines. Addressing a single research question therefore requires a coordina…
ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research
Wanghan Xu, Shuo Li, Tianlin Ye +48
AI coding agents are increasingly used for scientific work, but their end-to-end autonomous research capability remains difficult to verify. We present ResearchClawBench, a benchma…
Graph of Trace: Visualizing Execution Traces of Scientific Agent
Tianci Gao, Haoxuan Li, Jianhe Li +5
Scientific AI agents can autonomously carry out complex research workflows, yet these unfolded workflows often remain difficult for humans to inspect and review, limiting interpret…
Orchestra-o1: Omnimodal Agent Orchestration
Fan Zhang, Vireo Zhang, Shengju Qian +8
The recent success of agent swarms has shifted the paradigm of large language model (LLM)-based agents from single-agent workflows to multi-agent systems, highlighting the importan…
PAFO: Pareto Fairness Optimization for Personalized Reward Modeling
Xiaoyan Zhao, Haoting Ni, Yang Zhang +3
Large language models (LLMs) increasingly rely on reward models to align their outputs with diverse user preferences. While personalized reward models aim to capture such heterogen…
Rosetta Memory: Adaptive Memory for Cross-LLM Agents
Hao Yang, Shiqi Shen, Haoxuan Li +3
Memory is the key component for transforming a stateless LLM into a persistent, evolving agent through experience accumulation, long-horizon planning, and continual self-improvemen…
Struct-Searcher: Agentic Structural Thinking Advances Multimodal Deep Information Seeking
Fan Zhang, Vireo Zhang, Shengju Qian +7
Deep research agents have attracted increasing attention for their ability to collect large-scale online information to acquire target knowledge, with recent efforts shifting from…
Rethinking Facial Expression Recognition in the Era of Multimodal Large Language Models: Benchmark, Datasets, and Beyond
Fan Zhang, Haoxuan Li, Shengju Qian +9
Multimodal Large Language Models (MLLMs) have revolutionized numerous research fields, including computer vision and affective computing. As a pivotal challenge in this interdiscip…
MME-Emotion: A Holistic Evaluation Benchmark for Emotional Intelligence in Multimodal Large Language Models
Fan Zhang, Zebang Cheng, Chong Deng +18
Recent advances in multimodal large language models (MLLMs) have catalyzed transformative progress in affective computing, enabling models to exhibit emergent emotional intelligenc…