7 papers
Minority Sentinel: When to Overturn Majority Voting in Multi-Agent LLM Debates
Chuan He, Zebin Chen, Zhengyi Yang +5
Multi-Agent Debate (MAD) with Majority Voting is a dominant paradigm for improving LLM reasoning, yet its effectiveness rests on the Condorcet Jury Theorem's assumption of independ…
HyperSU: Corpus-Driven Semantic-Unit Hypergraph for Retrieval-Augmented Generation
Jiate Liu, Liuyi Chen, Zhengyi Yang +5
Recent Hypergraph-based retrieval-augmented generation (HyperRAG) methods use hyperedges to connect multiple entities simultaneously, enabling more efficient multi-entity evidence…
Evolving Skill-Structured Attack Memory Enhances LLM Jailbreaking
Junke Zhang, Jianwei Wang, Sishuo Chen +3
Jailbreak attacks on large language models (LLMs) aim to induce LLMs to produce content that they are expected to refuse. Automated black-box jailbreak generation is important for…
Grounding the Score: Explicit Visual Premise Verification for Reliable Vision-Language Process Reward Models
Junxin Wang, Dai Guan, Weijie Qiu +7
Vision-language process reward models (VL-PRMs) are increasingly used to score intermediate reasoning steps and rerank candidates under test-time scaling. However, they often funct…
A2RAG: Adaptive Agentic Graph Retrieval for Cost-Aware and Reliable Reasoning
Jiate Liu, Zebin Chen, Shaobo Qiao +10
Graph Retrieval-Augmented Generation (Graph-RAG) enhances multihop question answering by organizing corpora into knowledge graphs and routing evidence through relational structure.…
Beyond Linearization: Attributed Table Graphs for Table Reasoning
Yuxiang Wang, Junhao Gan, Shengxiang Gao +3
Table reasoning, a task to answer questions by reasoning over data presented in tables, is an important topic due to the prevalence of knowledge stored in tabular formats. Recent s…