5 citations · 23 across the 53 of their papers we have counts for
54 papers
FPCO-Dialog: A Multi-Turn False-Premise Benchmark for Correction and Cooperation in Vision-Language Models
Jiayuan Ma, Yuqi Lu, Weiyang Guo +5
Vision-language models (VLMs) are increasingly deployed in multi-turn settings where users may describe visual content with incorrect assumptions. Yet existing evaluations rarely i…
Can LLM Agents Stick to the Script? A Benchmark for Long-Horizon Consistency in Interactive Narratives
Yingpeng Ma, Jianhao Yan, Bei Shi +6
The rapid advancement of Large Language Models (LLMs) is revolutionizing AI for Games by enabling open-ended and fluid interactive storytelling. However, existing research has larg…
CRISP: Critical Step Perception for Training Efficient Deep Search Agents
Haosi Mo, Zihao Yan, Ruiqing Zhang +4
Large language models (LLMs) are increasingly extended into deep search agents that solve complex questions through multi-step interaction with external search and browsing tools.…
SuCo: Sufficiency-guided Continuous Adaptive Reasoning
Jiahao Wang, Bingyu Liang, Chenhao Hu +5
Despite remarkable performance on complex tasks, Large Reasoning Models (LRMs) often generate excessively long Chain-of-Thoughts (CoT), inflating computational costs even for simpl…
TGV-KV: Text-Grounded KV Eviction for Vision-Language Models
Jizhihui Liu, Ruizi Han, Miao Zhang +4
Vision-Language Models (VLMs) inherit the auto-regressive generation paradigm and cache the keys and values (KV) of all previous tokens to accelerate inference, resulting in memory…
Loong: A Human-Like Long Document Translation Agent with Observe-and-Act Adaptive Context Selection
Yutong Wang, Xuebo Liu, Derek F. Wong +5
Document-level translation remains one of the most challenging tasks for large language models, which are constrained by limited context windows that impede global cohesion, while…
OGER: A Robust Offline-Guided Exploration Reward for Hybrid Reinforcement Learning
Xinyu Ma, Mingzhou Xu, Xuebo Liu +4
Recent advancements in Reinforcement Learning with Verifiable Rewards (RLVR) have significantly improved Large Language Model (LLM) reasoning, yet models often struggle to explore…
CoCoReviewBench: A Completeness- and Correctness-Oriented Benchmark for AI Reviewers
Hexuan Deng, Xiaopeng Ke, Yichen Li +6
Despite the rapid development of AI reviewers, evaluating such systems remains challenging: metrics favor overlap with human reviews over correctness. However, since human reviews…
Mitigating Context-Memory Conflicts in LLMs through Dynamic Cognitive Reconciliation Decoding
Yigeng Zhou, Wu Li, Yifan Lu +6
Large language models accumulate extensive parametric knowledge through pre-training. However, knowledge conflicts occur when outdated or incorrect parametric knowledge conflicts w…
MASPO: Joint Prompt Optimization for LLM-based Multi-Agent Systems
Zhexuan Wang, Xuebo Liu, Li Wang +4
Large language model (LLM)-based Multi-agent systems (MAS) have shown promise in tackling complex collaborative tasks, where agents are typically orchestrated via role-specific pro…
D-QRELO: Training- and Data-Free Delta Compression for Large Language Models via Quantization and Residual Low-Rank Approximation
Junlin Li, Shuangyong Song, Guodong Du +6
Supervised Fine-Tuning (SFT) accelerates taskspecific large language models (LLMs) development, but the resulting proliferation of finetuned models incurs substantial memory overhe…
RouterKGQA: Specialized--General Model Routing for Constraint-Aware Knowledge Graph Question Answering
Bo Yuan, Hexuan Deng, Xuebo Liu +1
Knowledge graph question answering (KGQA) is a promising approach for mitigating LLM hallucination by grounding reasoning in structured and verifiable knowledge graphs. Existing ap…
MemoNoveltyAgent: A Historical Research Memory-Aware Agent Workflow for Paper Novelty Assessment
Jiajun Hou, Hexuan Deng, Wenxiang Jiao +4
To alleviate the heavy burden of paper screening, researchers increasingly rely on existing AI agents, such as AI reviewers or DeepResearch, for paper evaluation and novelty assess…
Think Dense, Not Long: Dynamic Decoupled Conditional Advantage for Efficient Reasoning
Keqin Peng, Yuanxin Ouyang, Xuebo Liu +4
Reinforcement Learning with Verifiable Rewards (RLVR) can elicit strong multi-step reasoning, yet it often encourages overly verbose traces. Moreover, naive length penalties in gro…
MASRubric: Auditing Information Flow in Multi-Agent Systems with Failure-Distilled Pitfall Rubrics
Yutong Wang, Siyuan Xiong, Xuebo Liu +4
While multi-agent systems (MAS) excel at complex reasoning, they are vulnerable to errors that intermediate agents introduce and downstream agents build upon. Auditing intermediate…
Stop Rewarding Hallucinated Steps: Faithfulness-Aware Step-Level Reinforcement Learning for Small Reasoning Models
Shuo Nie, Hexuan Deng, Chao Wang +6
As large language models become smaller and more efficient, small reasoning models (SRMs) are crucial for enabling chain-of-thought (CoT) reasoning in resource-constrained settings…
Mining or Synthesis? Rethinking Exploration Efficiency in Iterative Alignment of Mathematical Reasoning
Jun Rao, Zixiong Yu, Xuebo Liu +6
Iterative Direct Preference Optimization (DPO) has emerged as a widely used paradigm for aligning Large Language Models on reasoning tasks. Existing approaches typically rely on Be…
CVeDRL: An Efficient Code Verifier via Difficulty-aware Reinforcement Learning
Ji Shi, Peiming Guo, Meishan Zhang +4
Code verifiers play a critical role in post-verification for LLM-based code generation, yet existing supervised fine-tuning methods suffer from data scarcity, high failure rates, a…
Exposing the Cracks: Vulnerabilities of Retrieval-Augmented LLM-based Machine Translation
Yanming Sun, Runzhe Zhan, Chi Seng Cheang +7
\textbf{RE}trieval-\textbf{A}ugmented \textbf{L}LM-based \textbf{M}achine \textbf{T}ranslation (REAL-MT) shows promise for knowledge-intensive tasks like idiomatic translation, but…
SeaPO: Strategic Error Amplification for Robust Preference Optimization of Large Language Models
Jun Rao, Yunjie Liao, Xuebo Liu +6
Existing alignment methods for preference optimization of large language models (LLMs) aim to enhance model performance by utilizing pairs of positive and negative samples. However…
CDT: A Comprehensive Capability Framework for Large Language Models Across Cognition, Domain, and Task
Haosi Mo, Xinyu Ma, Xuebo Liu +4
Recent advances in Large Language Models (LLMs) have significantly enhanced their capabilities, highlighting the need for comprehensive evaluation frameworks that extend beyond tas…
AgentInit: Initializing LLM-based Multi-Agent Systems via Diversity and Expertise Orchestration for Effective and Efficient Collaboration
Chunhao Tian, Yutong Wang, Xuebo Liu +4
Proper initialization is crucial for any system, particularly in multi-agent systems (MAS), where it plays a pivotal role in determining both the system's efficiency and effectiven…
AQuilt: Weaving Logic and Self-Inspection into Low-Cost, High-Relevance Data Synthesis for Specialist LLMs
Xiaopeng Ke, Hexuan Deng, Xuebo Liu +4
Despite the impressive performance of large language models (LLMs) in general domains, they often underperform in specialized domains. Existing approaches typically rely on data sy…
SGIC: A Self-Guided Iterative Calibration Framework for RAG
Guanhua Chen, Yutong Yao, Lidia S. Chao +2
Recent research in retrieval-augmented generation (RAG) has concentrated on retrieving useful information from candidate documents. However, numerous methodologies frequently negle…