121 citations · 316 across the 60 of their papers we have counts for
66 papers
Information-Gain Calibrated On-Policy Distillation for Deep Search Agents
Chenxi Li, Xueyang Feng, Songyang Liu +4
On-policy distillation (OPD) has recently emerged as a promising approach for transferring the capabilities of large agents to compact students. In deep search, where agents iterat…
AREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks
Hongjin Qian, Chaofan Li, Kun Luo +11
We present AREX-2, an effort to advance the self-improving capability of LLM agents, which we define as the ability to iteratively refine a solution at test time. This ability rest…
Just-In-Time Agent Memory with Runtime Agentic Research
Bingyu Yan, Chaofan Li, Hongjin Qian +3
Memory is critical for AI agents. Many existing agent-memory systems follow an Ahead-of-Time (AOT) design, constructing memory before a specific request arrives. While this reduces…
CIBuzzBench: A Benchmark for Cross-Lingual Understanding of Chinese Internet Buzzwords
Yifan Wang, Junyu Lu, Qifan Wang +6
Chinese social media has generated a vast and continually evolving lexicon of internet buzzwords whose meanings are often non-literal and deeply rooted in local cultural and pragma…
Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills
Jianlyu Chen, Yuyang Hu, Hongjin Qian +8
Autonomous agents are beginning to carry out machine-learning (ML) research end to end. These agents combine a model backbone with a harness for planning, execution, memory, and ve…
AREX: Towards a Recursively Self-Improving Agent for Deep Research
Shuqi Lu, Chaofan Li, Kun Luo +21
Deep research requires agents to find answers that jointly satisfy multiple constraints. Discovering such answers is costly, whereas verifying a candidate can often be decomposed i…
Auditing Privacy Risks in LLM-Enhanced Graph Neural Networks
Longzhu He, Zelang Wen, Chaozhuo Li +1
Large language models (LLMs) have recently advanced graph neural networks (GNNs) by enriching node representations with semantic information, giving rise to LLM-enhanced GNNs that…
Tabular Foundation Models for Multi-View Information Cascade Popularity Prediction
Wenting Zhu, Chenghua Gong, Sanchuan Guo +3
Predicting the future popularity of information cascades is essential for understanding information diffusion on social media. Despite recent advances, existing methods face two ke…
Benign Alone, Harmful Together: Exploiting Experience Composition in Self-Evolving LLM Agents
Bingyu Yan, Xiaoming Zhang, Chaozhuo Li +3
Self-evolving large language model agents improve their capabilities by distilling interaction trajectories into persistent experiences. Yet this mechanism introduces a new safety…
Audio-Zero: Label-Free Self-Evolution for Fine-Grained Audio Reasoning
Siqian Tong, Xuan Li, Chaozhuo Li +5
Large Audio Language models (LALMs) have made rapid progress on acoustic understanding, yet they still struggle with fine-grained audio reasoning (e.g., recognizing event order, re…
MOF-Sleuth: Tool-Grounded Reward Alignment for Explainable Fine-Grained MOF CIF Auditing
Yu Liu, Zhiwei Yang, Diandian Guo +7
Large metal-organic framework (MOF) databases support simulation, screening, and machine learning through crystallographic information files (CIFs). Subtle chemical and structural…
Towards Personalized Differentially Private Learning for Decentralized Local Graphs
Longzhu He, Peng Tang, Chaozhuo Li +5
Graph-structured data is increasingly generated and stored in decentralized environments, such as social platforms, mobile applications, and edge networks, where users maintain con…
OpenEvoShield: Dual Non-Stationary Continual Defense for Open-World Multi-Agent System Attacks
Litian Zhang, Chaozhuo Li, Yuting Zhang +3
LLM-based multi-agent systems (LLM-MAS) are increasingly deployed in safety-critical applications, where adversaries inject malicious instructions through inter-agent communication…
Evo-Attacker: Memory-Augmented Reinforcement Learning for Long-Horizon Tool Attacks on LLM-MAS
Bingyu Yan, Xiaoming Zhang, Jinyu Hou +4
While Large Language Model-based Multi-Agent Systems (LLM-MAS) demonstrate remarkable capabilities in solving complex tasks by orchestrating specialized agents and external tools,…
Conflict-Aware Multi-Agent Reasoning via Signed Graph Modeling
Longgang He, Longzhu He, Daojing He +2
LLM-based multi-agent systems (MAS) seek to improve reasoning by combining diverse perspectives from multiple agents. However, aggregation may overlook supportive, contradictory, a…
Model-Agnostic Lifelong LLM Safety via Externalized Attack-Defense Co-Evolution
Xiaozhe Zhang, Chaozhuo Li, Hui Liu +4
Large language models remain vulnerable to adversarial prompts that elicit harmful outputs. Existing safety paradigms typically couple red-teaming and post-training in a closed, po…
PropGuard: Safeguarding LLM-MAS via Propagation-Aware Exploration and Remediation
Bingyu Yan, Xiaoming Zhang, Jinyu Hou +4
LLM-based multi-agent systems (LLM-MAS) have become a promising paradigm for solving complex tasks through role specialization, tool use, memory, and collaborative reasoning. Howev…
Securing Computer-Use Agents: A Unified Architecture-Lifecycle Framework for Deployment-Grounded Reliability
Zejian Chen, Zhanyuan Liu, Chaozhuo Li +6
Computer-use agents(CUAs)are moving frombounded benchmarks toward real software environments, wherethey operate browsers, desktops, mobile applications, flesystems,terminals, and t…
ClawKeeper: Comprehensive Safety Protection for OpenClaw Agents Through Skills, Plugins, and Watchers
Songyang Liu, Chaozhuo Li, Chenxu Wang +8
OpenClaw has rapidly established itself as a leading open-source autonomous agent runtime, offering powerful capabilities including tool integration, local file access, and shell c…
Jailbreaking LLMs & VLMs: Mechanisms, Evaluation, and Unified Defense
Zejian Chen, Chaozhuo Li, Chao Li +3
This paper provides a systematic survey of jailbreak attacks and defenses on Large Language Models (LLMs) and Vision-Language Models (VLMs), emphasizing that jailbreak vulnerabilit…
How Real is Your Jailbreak? Fine-grained Jailbreak Evaluation with Anchored Reference
Songyang Liu, Chaozhuo Li, Rui Pu +5
Jailbreak attacks present a significant challenge to the safety of Large Language Models (LLMs), yet current automated evaluation methods largely rely on coarse classifications tha…
LANCET: Neural Intervention via Structural Entropy for Mitigating Faithfulness Hallucinations in LLMs
Chenxu Wang, Chaozhuo Li, Pengbo Wang +7
Large Language Models have revolutionized information processing, yet their reliability is severely compromised by faithfulness hallucinations. While current approaches attempt to…
Attack the Messages, Not the Agents: A Multi-round Adaptive Stealthy Tampering Framework for LLM-MAS
Bingyu Yan, Ziyi Zhou, Xiaoming Zhang +5
Large language model-based multi-agent systems (LLM-MAS) effectively accomplish complex and dynamic tasks through inter-agent communication, but this reliance introduces substantia…
Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning
Rui Pu, Chaozhuo Li, Rui Ha +3
Defending large language models (LLMs) against jailbreak attacks is essential for their safe and reliable deployment. Existing defenses often rely on shallow pattern matching, whic…