5 citations · 27 across the 50 of their papers we have counts for
13 papers · 1 filter
TraceDance: An Automated System for Building Agent Behavior Benchmarks from Real-World Agent Deployment Traces
Dehai Min, Daoan Zhang, Yiming Zeng +13
An agent can complete a task while exhibiting undesirable behavior during execution. Developers need tests for the specific behaviors encountered in deployment, beyond fixed benchm…
Dr. Claw: An AI Scientist Workspace for Vibe Research
Dingjie Song, Hanrong Zhang, Dawei Liu +10
Command-line coding agents (e.g., Claude Code, Gemini CLI) can already read and write files and sustain long sessions, yet end-to-end research still fragments across chat tools, ID…
HAS-Bench: Evaluating LLM-Based Human-Agent Systems under Configurable Human Participation
Yaozu Wu, Wei-Chieh Huang, Jizhou Guo +11
Large language models increasingly operate in settings where humans are active collaborators rather than passive task providers. We introduce HAS-Framework, a graph-based framework…
GAM: Hierarchical Graph-based Agentic Memory for LLM Agents
Zhaofen Wu, Hanrong Zhang, Fulin Lin +9
To sustain coherent long-term interactions, Large Language Model (LLM) agents must navigate the tension between acquiring new information and retaining prior knowledge. Current uni…
CoEvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verification
Hanrong Zhang, Shicheng Fan, Henry Peng Zou +11
Anthropic proposes the concept of skills for LLM agents to tackle multi-step professional tasks that simple tool invocations cannot address. A tool is a single, self-contained func…
EpochX: Building the Infrastructure for an Emergent Agent Civilization
Huacan Wang, Chaofa Yuan, Xialie Zhuang +15
General-purpose technologies reshape economies less by improving individual tools than by enabling new ways to organize production and coordination. We believe AI agents are approa…
When Only the Final Text Survives: Implicit Execution Tracing for Multi-Agent Auditing
Yi Nian, Haosen Cao, Shenzhe Zhu +4
When a multi-agent system produces an incorrect or harmful answer, who is accountable if execution logs and agent identifiers are unavailable? In practice, generated content is oft…
CM2: Reinforcement Learning with Checklist Rewards for Multi-Turn and Multi-Step Agentic Tool Use
Zhen Zhang, Kaiqiang Song, Xun Wang +11
AI agents are increasingly used to solve real-world tasks by reasoning over multi-turn user interactions and invoking external tools. However, applying reinforcement learning to su…
TodyComm: Task-Oriented Dynamic Communication for Multi-Round LLM-based Multi-Agent System
Wenzhe Fan, Tommaso Tognoli, Henry Peng Zou +3
Multi-round LLM-based multi-agent systems rely on effective communication structures to support collaboration across rounds. However, most existing methods employ a fixed communica…
Embracing Trustworthy Brain-Agent Collaboration as Paradigm Extension for Intelligent Assistive Technologies
Yankai Chen, Xinni Zhang, Yifei Zhang +6
Brain-Computer Interfaces (BCIs) offer a direct communication pathway between the human brain and external devices, holding significant promise for individuals with severe neurolog…
PSG-Agent: Personality-Aware Safety Guardrail for LLM-based Agents
Yaozu Wu, Jizhou Guo, Dongyuan Li +9
Effective guardrails are essential for safely deploying LLM-based agents in critical applications. Despite recent advances, existing guardrails suffer from two fundamental limitati…
A Call for Collaborative Intelligence: Why Human-Agent Systems Should Precede AI Autonomy
Henry Peng Zou, Wei-Chieh Huang, Yaozu Wu +10
Recent improvements in large language models (LLMs) have led many researchers to focus on building fully autonomous AI agents. This position paper questions whether this approach i…
PersonaAgent: Bridging Memory and Action for Personalized LLM Agents
Weizhi Zhang, Xinyang Zhang, Chenwei Zhang +12
Large Language Model (LLM) empowered agents have recently emerged as advanced paradigms that exhibit impressive capabilities in a wide range of domains and tasks. Despite their pot…