14 citations · 29 across the 44 of their papers we have counts for
53 papers
Agents' Last Doubt: Knowing When to Act and When to Step Back in Tool-Using Agents
Qisai Liu, Qingyue Jiao, Bangwei Guo +7
Tool-using LLM agents repeatedly face decision points under uncertainty, choosing between autonomous action, additional information gathering, and human escalation. These decisions…
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…
ShellElastic: Scalable Elastic Pretraining with Simultaneous Maximal Updates and Hyperparameter Transfer
Can Jin, Yan Kang, Yifan Gong +5
Foundation models need to support diverse inference budgets, yet training a separate model for each budget duplicates pretraining effort. Elastic models train several nested sub-ne…
Knossos and Ariadne: Benchmarking and Learning Complete Diagram Topology Extraction with Vision-Language Models
Bangwei Guo, Xujiang Zhao, Shengyu Chen +6
Structural diagrams are widely used to represent complex systems and relational information across scientific, engineering, procedural, and spatial domains. Recent vision-language…
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…
Act More, Decide Less: Skill-Guided Adaptive Action Chunking for Long-Horizon LLM Agents
Yanting Yang, Can Jin, Jinman Zhao +6
Large language model (LLM) agents for long-horizon interactive tasks typically follow a ReAct-style protocol, issuing one primitive action per LLM round. While this enables frequen…
TopoAgent: A Structure-Aware Perception-to-Reasoning Framework for Diagram-to-Graph Topology Extraction with Large Vision-Language Models
Bangwei Guo, Xujiang Zhao, Yanchi Liu +7
Diagram-to-graph topology extraction aims to extract a graph of entities and their connections from a structural diagram. This task remains challenging for current vision-language…
ES-VP : Energy-Shaped Dynamic Visual Prompting for Efficient Model Adaptation
Can Jin, Ying Li, Jingchen Sun +5
Visual prompting (VP) has emerged as a parameter-efficient method for adapting pre-trained models to downstream tasks. However, existing approaches encounter a trade-off between fl…
OpenPM: Auditable Point-in-Time Evaluation for LLM Portfolio-Management Agents
Xinying Cai, Minghao Guo, Jiahe Liu +7
Large language models are increasingly used to read markets, assess risk, and allocate capital. However, reported results for LLM trading agents can be inflated by look-ahead leaka…
Conformal Path Reasoning: Trustworthy Knowledge Graph Question Answering via Path-Level Calibration
Shuhang Lin, Chuhao Zhou, Xiao Lin +5
Knowledge Graph Question Answering (KGQA) offers grounded, interpretable reasoning, but existing methods often fail to provide reliable coverage guarantees over retrieved answers.…
Agent Skill Evaluation and Evolution: Frameworks and Benchmarks
Kexin Ding, Yang Zhou, Can Jin +3
The growth of agent skills has transformed how agentic systems are built, evaluated, and deployed. As skill libraries continue to scale, rigorous evaluation becomes critical to ens…
Evidence Over Plans: Online Trajectory Verification for Skill Distillation
Yang Zhou, Zihan Dong, Zhenting Wang +7
Agent skills can remarkably improve task success rates by using human-written procedural documents, but their quality is difficult to assess without environment-grounded verificati…
PR2: Predictive Routing Replay for MoE-Based LLM Reinforcement Learning
Daize Dong, Junlin Chen, Haolong Jia +9
Mixture of Experts (MoE) Large Language Models (LLMs) achieve strong performance at scale. However, reinforcement learning (RL) on MoE-based LLMs often suffers from training instab…
Latent Reward Steering: An Adaptive Inference-Time Framework that Implicitly Promotes Cognitive Behaviors in Reasoning LLMs
Jiakang Li, Guanyu Zhu, Can Jin +8
Strong reasoning depends not only on model knowledge but also on how effectively cognitive behaviors are deployed during generation. Existing methods often rely on explicit behavio…
Weak Critics Make Strong Learners: On-Policy Critique Distillation for Scalable Oversight
Can Jin, Jiakang Li, Rui Wu +2
As large language models become stronger, weak supervisors may fail to provide reliable labels, preferences, or final judgments for complex outputs, limiting both weak-to-strong ge…
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-…
MemEye: A Visual-Centric Evaluation Framework for Multimodal Agent Memory
Minghao Guo, Qingyue Jiao, Zeru Shi +14
Long-term agent memory is increasingly multimodal, yet existing evaluations rarely test whether agents preserve the visual evidence needed for later reasoning. In prior work, many…
All Circuits Lead to Rome: Rethinking Functional Anisotropy in Circuit and Sheaf Discovery for LLMs
Xi Chen, Mingyu Jin, Jingcheng Niu +7
In this paper, we present empirical and theoretical evidence against a central but largely implicit assumption in circuit and sheaf discovery (CSD), which we term the Functional An…
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…
DARE: Difficulty-Adaptive Reinforcement Learning with Co-Evolved Difficulty Estimation
Yang Zhou, Can Jin, Zihan Dong +7
Reinforcement learning improves the reasoning ability of large language models but remains costly and sample-inefficient, as many rollouts provide weak learning signals. Difficulty…
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…
Farther the Shift, Sparser the Representation: Analyzing OOD Mechanisms in LLMs
Mingyu Jin, Yutong Yin, Jingcheng Niu +7
In this work, we investigate how Large Language Models (LLMs) adapt their internal representations when encountering inputs of increasing difficulty, quantified as the degree of ou…