32 citations · 48 across the 47 of their papers we have counts for
30 papers · 1 filter
Self-Evolving Embodied Agents via Skill-Harness Evolution
Peidong Wang, Zhiming Ma, Ying Chang +7
Embodied agents are increasingly built as systems around foundation models, where performance depends not only on model weights but also on the skills, context, action interfaces,…
Do AI Personas Grow? Analyzing and Benchmarking Personality Evolution in LLM Agents After Life Events
Ming Wang, Peidong Wang, Xiaocui Yang +4
Personality-conditioned LLM agents (PC-Agents) are increasingly used in emotional support, social simulation, and role-playing, motivating the development of lifelong agents that r…
Boosting Deepresearch and LongContext Ability with Self-Generated Deepresearch Rollouts Traces
Zihan Wang, Hao Wang, Boyuan Jiang +8
Deepresearch (DR) agents interact with real-world web environments through multi-turn search and visit, causing their contexts to grow rapidly over time. We observe that, even afte…
TRAM: Enhancing Multimodal Reasoning with Trajectory-Derived Auxiliary Memory
Kang Liu, Zijing Wang, Yongkang Liu +5
Multimodal Large Reasoning Models (MLRMs) have achieved strong performance on tasks requiring visual understanding and multi-step inference. However, as reasoning trajectories grow…
CrossLex: A Source-Grounded Benchmark for Cross-Jurisdictional Legal Reasoning in Large Language Models
Xiaocui Yang, Xican Tan, Shoujie Chen +3
Legal reasoning is inherently jurisdiction-dependent: the same facts can call for different legal rules and yield different conclusions across legal systems. Yet existing benchmark…
What are Key Factors for Updates in RL for LLM Reasoning?
Peidong Wang, Demi Wang, Xufang Luo +5
Reinforcement Learning from Verifiable Rewards (RLVR) has emerged as a promising framework for enhancing the reasoning ability of large language models. However, much of the existi…
PRISM: Prosody-Integrated Multi-Agent Reasoning Framework for Empathetic Spoken Dialogue
Wen Zhang, Xiaocui Yang, Zhuoyue Gao +3
Empathetic spoken dialogue systems require not only semantically appropriate responses but also emotionally aligned prosodic expression. However, cascade pipelines often discard ac…
DiM\textsuperscript{3}: Bridging Multilingual and Multimodal Models via Direction- and Magnitude-Aware Merging
Zijing Wang, Mingyang Wang, Ercong Nie +6
Towards more general and human-like intelligence, large language models should seamlessly integrate both multilingual and multimodal capabilities; however, extending an existing mu…
MTRouter: Cost-Aware Multi-Turn LLM Routing with History-Model Joint Embeddings
Yiqun Zhang, Hao Li, Zihan Wang +6
Multi-turn, long-horizon tasks are increasingly common for large language models (LLMs), but solving them typically requires many sequential model invocations, accumulating substan…
GRASP: Grounded CoT Reasoning with Dual-Stage Optimization for Multimodal Sarcasm Target Identification
Faxian Wan, Xiaocui Yang, Yifan Cao +3
Moving beyond the traditional binary classification paradigm of Multimodal Sarcasm Detection, Multimodal Sarcasm Target Identification (MSTI) presents a more formidable challenge,…
NEAT: Neuron-Based Early Exit for Large Reasoning Models
Kang Liu, Yongkang Liu, Xiaocui Yang +5
Large Reasoning Models (LRMs) often suffer from \emph{overthinking}, a phenomenon in which redundant reasoning steps are generated after a correct solution has already been reached…
PlaM: Training-Free Plateau-Guided Model Merging for Better Visual Grounding in MLLMs
Zijing Wang, Yongkang Liu, Mingyang Wang +8
Multimodal Large Language Models (MLLMs) rely on strong linguistic reasoning inherited from their base language models. However, multimodal instruction fine-tuning paradoxically de…
CIRAG: Construction-Integration Retrieval and Adaptive Generation for Multi-hop Question Answering
Zili Wei, Xiaocui Yang, Yilin Wang +5
Triple-based Iterative Retrieval-Augmented Generation (iRAG) mitigates document-level noise for multi-hop question answering. However, existing methods still face limitations: (i)…
Resource-Limited Joint Multimodal Sentiment Reasoning and Classification via Chain-of-Thought Enhancement and Distillation
Haonan Shangguan, Xiaocui Yang, Shi Feng +3
Current approaches for Multimodal Sentiment Analysis (MSA) primarily leverage the knowledge and reasoning capabilities of parameter-heavy (Multimodal) LLMs for classification, over…
MEKiT: Multi-source Heterogeneous Knowledge Injection Method via Instruction Tuning for Emotion-Cause Pair Extraction
Shiyi Mu, Yongkang Liu, Shi Feng +3
Although large language models (LLMs) excel in text comprehension and generation, their performance on the Emotion-Cause Pair Extraction (ECPE) task, which requires reasoning abili…
AnnaAgent: Dynamic Evolution Agent System with Multi-Session Memory for Realistic Seeker Simulation
Ming Wang, Peidong Wang, Lin Wu +6
Constrained by the cost and ethical concerns of involving real seekers in AI-driven mental health, researchers develop LLM-based conversational agents (CAs) with tailored configura…
Nature-Inspired Population-Based Evolution of Large Language Models
Yiqun Zhang, Peng Ye, Xiaocui Yang +5
Evolution, the engine behind the survival and growth of life on Earth, operates through the population-based process of reproduction. Inspired by this principle, this paper formall…
HIPPO: Enhancing the Table Understanding Capability of LLMs through Hybrid-Modal Preference Optimization
Haolan Wang, Zhenghao Liu, Xinze Li +7
Tabular data contains rich structural semantics and plays a crucial role in organizing and manipulating information. Recent methods employ Multi-modal Large Language Models (MLLMs)…
PsyDraw: A Multi-Agent Multimodal System for Mental Health Screening in Left-Behind Children
Yiqun Zhang, Xiaocui Yang, Xiaobai Li +5
Left-behind children (LBCs), numbering over 66 million in China, face severe mental health challenges due to parental migration for work. Early screening and identification of at-r…
TOOL-ED: Enhancing Empathetic Response Generation with the Tool Calling Capability of LLM
Huiying Cao, Yiqun Zhang, Shi Feng +3
Empathetic conversation is a crucial characteristic in daily conversations between individuals. Nowadays, Large Language models (LLMs) have shown outstanding performance in generat…
Language Models as Continuous Self-Evolving Data Engineers
Peidong Wang, Ming Wang, Zhiming Ma +5
Large Language Models (LLMs) have demonstrated remarkable capabilities on various tasks, while the further evolvement is limited to the lack of high-quality training data. In addit…
Generative Emotion Cause Explanation in Multimodal Conversations
Lin Wang, Xiaocui Yang, Shi Feng +3
Multimodal conversation, a crucial form of human communication, carries rich emotional content, making the exploration of the causes of emotions within it a research endeavor of si…
Minstrel: Structural Prompt Generation with Multi-Agents Coordination for Non-AI Experts
Ming Wang, Yuanzhong Liu, Xiaoyu Liang +8
LLMs have demonstrated commendable performance across diverse domains. Nevertheless, formulating high-quality prompts to assist them in their work poses a challenge for non-AI expe…
Hierarchical Retrieval-Augmented Generation Model with Rethink for Multi-hop Question Answering
Xiaoming Zhang, Ming Wang, Xiaocui Yang +3
Multi-hop Question Answering (QA) necessitates complex reasoning by integrating multiple pieces of information to resolve intricate questions. However, existing QA systems encounte…