13 papers
Who Improves the Robot? Toward Physical Recursive Self-Improvement
Hai Zhou, Fan Yang, Zeyi Chen +27
Robots are increasingly autonomous in task execution, yet their improvement remains largely human-driven. This study investigates Physical Recursive Self-Improvement (Physical RSI)…
AdaStep: Adaptive Step Credit Weighting for Agentic Reinforcement Learning
Xin Wang, Wenhao Wu, Menghao Zhang +3
Long-horizon LLM agents are typically trained with sparse outcome rewards, making trajectory-level objectives too coarse to distinguish the contribution of individual decisions. St…
HarnessPAI: An Evolving Harness for Physical AI
Xin Wang, Wenhao Wu, Menghao Zhang +20
Physical AI aims to build embodied agents that perceive the world, understand and reason about it, and decide how to act. Yet the field has focused primarily on the last component:…
TRACE: A Self-Evolving Skill Bank for Consistent, Limit-Aware LLM Agents
Wenhao Wu, Menghao Zhang, Xin Wang +3
Reliable deployment of LLM agents in user-facing products depends not on raw task-solving ability but on consistency and limit-awareness: behaving the same way across repeated tria…
MemFuse: Multi-Source Memory Fusion from Fragmented Observations
Chao Li, Yuanfa Li, Wenhao Wu +3
Long-term memory is essential for agents that operate across extended interactions, yet existing memory systems and benchmarks predominantly focus on single-source textual historie…
G-ReAct: Graph-Guided Deep Search via Structure-State Co-Evolution
Shaoxiong Yang, Mengyuan Zhang, Shaojun Lin +4
Deep search has become a fundamental capability of large language models (LLMs) for solving open-domain complex tasks. However, existing approaches typically rely on linear sequent…
Topological collapse of higher-order interactions bottlenecks collective intelligence in AI agent societies
Shuo Lu, Weicheng Meng, Aijing Yu +4
Current paradigms in artificial intelligence concentrate on scaling the capabilities of individual models, yet the collective behaviour of interacting agents is shaped by the topol…
HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry
Tingyang Chen, Shuo Lu, Kang Zhao +11
AI agent performance depends critically on the runtime harness, comprising the prompts, tools, memory, and control flow that mediate how a model observes, reasons, and acts. Yet to…
Mi-Memory: A Lifecycle Memory Framework for Personal AI
Xule Liu, Hanlin Teng, Chao Li +15
Personal AI is moving beyond chat-only interaction toward continuous services that span phones, cars, homes, wearables, cameras, and tools. In this setting, memory cannot remain a…
ProMMSearchAgent: A Generalizable Multimodal Search Agent Trained with Process-Oriented Rewards
Wentao Yan, Shengqin Wang, Huichi Zhou +4
Training multimodal agents via reinforcement learning for knowledge-intensive visual reasoning is fundamentally hindered by the extreme sparsity of outcome-based supervision and th…
K^2-Agent: Co-Evolving Know-What and Know-How for Hierarchical Mobile Device Control
Zhe Wu, Donglin Mo, Hongjin Lu +7
Existing mobile device control agents often perform poorly when solving complex tasks requiring long-horizon planning and precise operations, typically due to a lack of relevant ta…
ViMo: A Generative Visual GUI World Model for App Agents
Dezhao Luo, Bohan Tang, Kang Li +6
App agents, which autonomously operate mobile Apps through Graphical User Interfaces (GUIs), have gained significant interest in real-world applications. Yet, they often struggle w…
Learning Precise Affordances from Egocentric Videos for Robotic Manipulation
Gen Li, Nikolaos Tsagkas, Jifei Song +4
Affordance, defined as the potential actions that an object offers, is crucial for embodied AI agents. For example, such knowledge directs an agent to grasp a knife by the handle f…