76 citations · 139 across the 25 of their papers we have counts for
30 papers
Seeing, Maintaining, and Learning: The Evolution of Multimodal Agent Memory
Minghao Guo, Qingyue Jiao, Xiujin Liu +77
Multimodal models and agents have emerged to enable AI systems to learn from and interact with the real world more like humans by integrating information across multiple modalities…
CLIMB: Confidence-Guided Complementary Evidence for Multimodal Retrieval-Augmented Generation
Hang Gao, Wujiang Xu, Zhixing Zhang +3
Multimodal large language models (MLLMs) have shown strong visual reasoning abilities, but knowledge-intensive visual question answering often requires external textual evidence be…
Opera: A Verbal Critic Framework for Long-horizon Coding Agents
Kai Mei, Zhiyuan Hu, Yutong Dai +7
Long-horizon coding agents need timely corrections, yet feedback can be ineffective or even harmful when it misjudges ongoing work or fails to address the underlying problem. Exist…
Beyond Solo and Consistency: Vindicating Multi-Agent Debate via Conditional Progressive Pruning
Ruosong Ye, Caiqi Zhang, Jiahao Li +9
Large Language Model (LLM) based Multi-Agent Debate (MAD) is one of the most effective test time scaling techniques. Through multi-round communication, agents complement each other…
MemGym: a Long-Horizon Memory Environment for LLM Agents
Wujiang Xu, Yu Wang, Kai Mei +8
Memory is a central capability for LLM agents operating across long-horizon tasks. Existing memory benchmarks predominantly evaluate retention of personalized information in multi-…
Trust or Abstain? A Self-Aware RAG Approach
Xi Zhu, Ziqi Wang, Kai Mei +5
Retrieval-augmented generation (RAG) improves large language models (LLMs) by incorporating external evidence, but it also introduces knowledge conflicts when retrieved contextual…
ClawSafety: "Safe" LLMs, Unsafe Agents
Bowen Wei, Yunbei Zhang, Jinhao Pan +5
Personal AI agents like OpenClaw run with elevated privileges on users' local machines, where a single successful prompt injection can leak credentials, redirect financial transact…
AEL: Evolving Agent Harness in Open-Ended Environments
Wujiang Xu, Jiaojiao Han, Minghao Guo +4
LLM Agents Harnesses are hand-designed and stay fixed, so agents accumulate experience but never learn how to use it: which memories to retrieve, when retrieved evidence is mislead…
Improving Visual Reasoning with Iterative Evidence Refinement
Zeru Shi, Kai Mei, Yihao Quan +2
Vision language models (VLMs) are increasingly capable of reasoning over images, but robust visual reasoning often requires re-grounding intermediate steps in the underlying visual…
Pooling and Semantic Shift: The Fundamental Challenges in Long Text Embedding and Retrieval
Hang Gao, Wujiang Xu, Kai Mei +1
Transformer-based embedding models frequently exhibit geometric pathologies, such as anisotropy and length-induced representation collapse, which can degrade downstream retrieval p…
Agents in the Wild: Safety, Society, and the Illusion of Sociality on Moltbook
Yunbei Zhang, Kai Mei, Ming Liu +5
We present the first large-scale empirical study of Moltbook, an AI-only social platform where 27,269 agents produced 137,485 posts and 345,580 comments over 9 days. We report thre…
R-WoM: Retrieval-augmented World Model For Computer-use Agents
Kai Mei, Jiang Guo, Shuaichen Chang +4
Large Language Models (LLMs) can serve as world models to enhance agent decision-making in digital environments by simulating future states and predicting action outcomes, potentia…
EPO: Entropy-regularized Policy Optimization for LLM Agents Reinforcement Learning
Wujiang Xu, Wentian Zhao, Zhenting Wang +6
Training LLM agents in multi-turn environments with sparse rewards, where completing a single task requires 30+ turns of interaction within an episode, presents a fundamental chall…
LiteCUA: Computer as MCP Server for Computer-Use Agent on AIOS
Kai Mei, Xi Zhu, Hang Gao +2
We present AIOS 1.0, a novel platform designed to advance computer-use agent (CUA) capabilities through environmental contextualization. While existing approaches primarily focus o…
Cerebrum (AIOS SDK): A Platform for Agent Development, Deployment, Distribution, and Discovery
Balaji Rama, Kai Mei, Yongfeng Zhang
Autonomous LLM-based agents have emerged as a powerful paradigm for complex task execution, yet the field lacks standardized tools for development, deployment, distribution and dis…
OmniRouter: Budget and Performance Controllable Multi-LLM Routing
Kai Mei, Wujiang Xu, Minghao Guo +2
Large language models (LLMs) deliver superior performance but require substantial computational resources and operate with relatively low efficiency, while smaller models can effic…
iAgent: LLM Agent as a Shield between User and Recommender Systems
Wujiang Xu, Yunxiao Shi, Zujie Liang +6
Traditional recommender systems usually take the user-platform paradigm, where users are directly exposed under the control of the platform's recommendation algorithms. However, th…
A-MEM: Agentic Memory for LLM Agents
Wujiang Xu, Zujie Liang, Kai Mei +3
While large language model (LLM) agents can effectively use external tools for complex real-world tasks, they require memory systems to leverage historical experiences. Current mem…
Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding
Mingyu Jin, Kai Mei, Wujiang Xu +5
Large language models (LLMs) have achieved remarkable success in contextual knowledge understanding. In this paper, we show that these concentrated massive values consistently emer…
From Commands to Prompts: LLM-based Semantic File System for AIOS
Zeru Shi, Kai Mei, Mingyu Jin +9
Large language models (LLMs) have demonstrated significant potential in the development of intelligent applications and systems such as LLM-based agents and agent operating systems…
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Hanrong Zhang, Jingyuan Huang, Kai Mei +5
Although LLM-based agents, powered by Large Language Models (LLMs), can use external tools and memory mechanisms to solve complex real-world tasks, they may also introduce critical…
AutoFlow: Automated Workflow Generation for Large Language Model Agents
Zelong Li, Shuyuan Xu, Kai Mei +6
Recent advancements in Large Language Models (LLMs) have shown significant progress in understanding complex natural language. One important application of LLM is LLM-based AI Agen…
AIOS Compiler: LLM as Interpreter for Natural Language Programming and Flow Programming of AI Agents
Shuyuan Xu, Zelong Li, Kai Mei +1
Since their inception, programming languages have trended towards greater readability and lower barriers for programmers. Following this trend, natural language can be a promising…
Exploring Concept Depth: How Large Language Models Acquire Knowledge and Concept at Different Layers?
Mingyu Jin, Qinkai Yu, Jingyuan Huang +10
Large language models (LLMs) have shown remarkable performances across a wide range of tasks. However, the mechanisms by which these models encode tasks of varying complexities rem…