11 papers
Self-Authored Verification Is Unreliable in Heuristic Self-Improving Agents
Diandian Guo, Cong Cao, Fangfang Yuan +3
Self-improving agents accumulate capability by repeatedly rewriting procedural policies, controllers, or heuristic rules. They typically rely on self-authored tests or metrics to d…
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…
AOCI: Symbolic-Semantic Indexing for Practical Repository-Scale Code Understanding with LLMs
Jinshi Liu, Hanying Zuo, Congyin Cao +3
Large language models struggle with understanding codebases beyond a certain scale -- repositories with hundreds of thousands of lines of code. Existing methods -- retrieval, summa…
A Hierarchical Error-Corrective Graph Framework for Autonomous Agents with LLM-Based Action Generation
Cong Cao, Jingyao Zhang, Kun Tong
We propose a Hierarchical Error-Corrective Graph FrameworkforAutonomousAgentswithLLM-BasedActionGeneration(HECG),whichincorporates three core innovations: (1) Multi-Dimensional Tra…
Does Faithfulness-Guided Alignment Hurt Accuracy? Unlocking Accurate and Faithful Post-Retrieval Reasoning
Yu Liu, Wenxiao Zhang, Diandian Guo +6
Retrieval-augmented generation (RAG) can achieve strong answer accuracy on multi-hop questions, but outcome-level rewards often leave reasoning traces weakly grounded and difficult…
PRISMA: Reinforcement Learning Guided Two-Stage Policy Optimization in Multi-Agent Architecture for Open-Domain Multi-Hop Question Answering
Yu Liu, Wenxiao Zhang, Cong Cao +10
Answering real-world open-domain multi-hop questions over massive corpora is a critical challenge in Retrieval-Augmented Generation (RAG) systems. Recent research employs reinforce…
MuVaC: A Variational Causal Framework for Multimodal Sarcasm Understanding in Dialogues
Diandian Guo, Fangfang Yuan, Cong Cao +5
The prevalence of sarcasm in multimodal dialogues on the social platforms presents a crucial yet challenging task for understanding the true intent behind online content. Comprehen…
Emotion Transfer with Enhanced Prototype for Unseen Emotion Recognition in Conversation
Kun Peng, Cong Cao, Hao Peng +5
Current Emotion Recognition in Conversation (ERC) research follows a closed-domain assumption. However, there is no clear consensus on emotion classification in psychology, which p…
Dialogues Aspect-based Sentiment Quadruple Extraction via Structural Entropy Minimization Partitioning
Kun Peng, Cong Cao, Hao Peng +5
Dialogues Aspect-based Sentiment Quadruple Extraction (DiaASQ) aims to extract all target-aspect-opinion-sentiment quadruples from a given multi-round, multi-participant dialogue.…
OPERA: A Reinforcement Learning--Enhanced Orchestrated Planner-Executor Architecture for Reasoning-Oriented Multi-Hop Retrieval
Yu Liu, Yanbing Liu, Fangfang Yuan +6
Recent advances in large language models (LLMs) and dense retrievers have driven significant progress in retrieval-augmented generation (RAG). However, existing approaches face sig…
T-T: Table Transformer for Tagging-based Aspect Sentiment Triplet Extraction
Kun Peng, Chaodong Tong, Cong Cao +6
Aspect sentiment triplet extraction (ASTE) aims to extract triplets composed of aspect terms, opinion terms, and sentiment polarities from given sentences. The table tagging method…