6 citations · 7 across the 15 of their papers we have counts for
20 papers
Skill++: Towards Lifelong Agents via Routing-Aware Skill Refinement
Hanrong Zhang, Minghao Liang, Jiawei Wu +10
Large language model (LLM) agents extend their capabilities with skills, each with a name, a description, and a body. Under progressive disclosure, an LLM router selects skills by…
SkillNEO: Non-Elitist Evolutionary Optimization of Agent Skills
Enze Ma, Chunyu Miao, Yankai Chen +14
Agent skills turn procedural knowledge into reusable artifacts, allowing LLM agents to accumulate and refine expertise through experience. Building on this, skill evolution iterati…
Open-MMUnlearning: Unifying Methods and Evaluation for MLLM Unlearning
Junkai Chen, Yuhao He, Qianshan Wei +19
As multimodal large language models (MLLMs) become more capable and widely deployed, concerns about privacy and safety have become increasingly pressing. Machine unlearning offers…
Playing social deduction games with reinforcement fine-tuned large language models
Lingzhe Zhang, Yunpeng Zhai, Tong Jia +7
Reinforcement fine-tuning (RFT) is increasingly used in applications where large language models (LLMs) interact with humans and other agents. Here we use social deduction games to…
InterTab: Interleaved Visual-Structure Alignment for Multi-Modal Table Reasoning
Hanqian Li, Sirui Huang, Chen Ling +12
Table images preserve structural information that are often lost in text serialization, and reasoning over them requires locating relevant rows, columns, and cells step by step. Cu…
EAVer: Long-Form Factuality Verification as an End-to-End Agentic Policy
Kening Zheng, Aoying Zheng, Zhigang Chang +21
Long-form factuality verification is commonly implemented as a static decompose-search-verify pipeline, with separately prompted modules processing claims and invoking external sea…
Consistency as Inductive Bias: Learning Cross-View Invariance for Robust Multimodal Reasoning
Xin Zou, Haolin Deng, Yibo Yan +6
Inductive biases steer learning toward generalizable solutions by encoding task structure. In this work, we identify a crucial missing bias in MLLMs: cross-view consistency, \texti…
ARC-STAR: Auditable Post-Hoc Correction for PDE Foundation Models
Chengze Li, Lingwei Wei, Li Sun +7
Partial differential equation (PDE) foundation models are pretrained networks that forecast how physical fields like velocity and pressure evolve from a single reusable solver. On…
Towards Robust LLM Post-Training: Automatic Failure Management for Reinforcement Fine-Tuning
Lingzhe Zhang, Tong Jia, Yunpeng Zhai +6
Reinforcement fine-tuning (RFT) has become a core paradigm for post-training large language models, yet its training process remains highly fragile. Existing efforts mainly improve…
SAMark: A Self-Anchored Text Watermarking with Paragraph-Level Paraphrase Robustness
Jiahao Huo, Wenjie Qu, Yibo Yan +5
Semantic-level watermarking (SWM) improves robustness against text modifications by treating sentences as the basic unit. However, robustness to paragraph-level paraphrasing remain…
Unveiling Language Routing Isolation in Multilingual MoE Models for Interpretable Subnetwork Adaptation
Kening Zheng, Wei-Chieh Huang, Jiahao Huo +9
Mixture-of-Experts (MoE) models exhibit striking performance disparities across languages, yet the internal mechanisms driving these gaps remain poorly understood. In this work, we…
CoEvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verification
Hanrong Zhang, Shicheng Fan, Henry Peng Zou +11
Anthropic proposes the concept of skills for LLM agents to tackle multi-step professional tasks that simple tool invocations cannot address. A tool is a single, self-contained func…
When Users Change Their Mind: Evaluating Interruptible Agents in Long-Horizon Web Navigation
Henry Peng Zou, Chunyu Miao, Wei-Chieh Huang +16
As LLM agents transition from short, static problem solving to executing complex, long-horizon tasks in dynamic environments, the ability to handle user interruptions, such as addi…
Unlocking Multimodal Document Intelligence: From Current Triumphs to Future Frontiers of Visual Document Retrieval
Yibo Yan, Jiahao Huo, Guanbo Feng +12
With the rapid proliferation of multimodal information, Visual Document Retrieval (VDR) has emerged as a critical frontier in bridging the gap between unstructured visually rich da…
GM-PRM: A Generative Multimodal Process Reward Model for Multimodal Mathematical Reasoning
Jianghangfan Zhang, Yibo Yan, Kening Zheng +3
Multimodal Large Language Models (MLLMs) demonstrate remarkable capabilities but often struggle with complex, multi-step mathematical reasoning, where minor errors in visual percep…
OMEGA: Can LLMs Reason Outside the Box in Math? Evaluating Exploratory, Compositional, and Transformative Generalization
Yiyou Sun, Shawn Hu, Georgia Zhou +4
Recent large-scale language models (LLMs) with long Chain-of-Thought reasoning-such as DeepSeek-R1-have achieved impressive results on Olympiad-level mathematics benchmarks. Howeve…
SafeEraser: Enhancing Safety in Multimodal Large Language Models through Multimodal Machine Unlearning
Junkai Chen, Zhijie Deng, Kening Zheng +6
As Multimodal Large Language Models (MLLMs) develop, their potential security issues have become increasingly prominent. Machine Unlearning (MU), as an effective strategy for forge…
Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in Multimodal Large Language Models
Xin Zou, Yizhou Wang, Yibo Yan +8
Despite their impressive capabilities, multimodal large language models (MLLMs) are prone to hallucinations, i.e., the generated content that is nonsensical or unfaithful to input…
Reefknot: A Comprehensive Benchmark for Relation Hallucination Evaluation, Analysis and Mitigation in Multimodal Large Language Models
Kening Zheng, Junkai Chen, Yibo Yan +2
Hallucination issues continue to affect multimodal large language models (MLLMs), with existing research mainly addressing object-level or attribute-level hallucinations, neglectin…
Refiner: Restructure Retrieval Content Efficiently to Advance Question-Answering Capabilities
Zhonghao Li, Xuming Hu, Aiwei Liu +3
Large Language Models (LLMs) are limited by their parametric knowledge, leading to hallucinations in knowledge-extensive tasks. To address this, Retrieval-Augmented Generation (RAG…