121 citations · 316 across the 60 of their papers we have counts for
14 papers · 1 filter
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…
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…
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…
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…
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…
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…
From "Aha Moments" to Controllable Thinking: Toward Meta-Cognitive Reasoning in Large Reasoning Models via Decoupled Reasoning and Control
Rui Ha, Rui Pu, Chaozhuo Li +2
Large Reasoning Models (LRMs) can exhibit step-by-step reasoning, reflection, and backtracking, but these behaviors are often unregulated, leading to overthinking. As a result, LRM…
LLMs are Introvert
Litian Zhang, Xiaoming Zhang, Bingyu Yan +5
The exponential growth of social media and generative AI has transformed information dissemination, fostering connectivity but also accelerating the spread of misinformation. Under…
Navigating the Black Box: Leveraging LLMs for Effective Text-Level Graph Injection Attacks
Yuefei Lyu, Chaozhuo Li, Xi Zhang +1
Text-attributed graphs (TAGs) integrate textual data with graph structures, providing valuable insights in applications such as social network analysis and recommendation systems.…
Fact in Fragments: Deconstructing Complex Claims via LLM-based Atomic Fact Extraction and Verification
Liwen Zheng, Chaozhuo Li, Zheng Liu +4
Fact verification plays a vital role in combating misinformation by assessing the veracity of claims through evidence retrieval and reasoning. However, traditional methods struggle…
Reasoning Paths as Signals: Augmenting Multi-hop Fact Verification through Structural Reasoning Progression
Liwen Zheng, Chaozhuo Li, Haoran Jia +1
The growing complexity of factual claims in real-world scenarios presents significant challenges for automated fact verification systems, particularly in accurately aggregating and…
ConvFormer: Revisiting Transformer for Sequential User Modeling
Hao Wang, Jianxun Lian, Mingqi Wu +5
Sequential user modeling, a critical task in personalized recommender systems, focuses on predicting the next item a user would prefer, requiring a deep understanding of user behav…
HousE: Knowledge Graph Embedding with Householder Parameterization
Rui Li, Jianan Zhao, Chaozhuo Li +9
The effectiveness of knowledge graph embedding (KGE) largely depends on the ability to model intrinsic relation patterns and mapping properties. However, existing approaches can on…