6 papers
MemSyco-Bench: Benchmarking Sycophancy in Agent Memory
Zhishang Xiang, Zerui Chen, Yunbo Tang +5
Memory has emerged as a cornerstone of modern LLM-based agents, supporting their evolution from single-turn assistants to long-term collaborators. However, memory is not always ben…
Evolution Fine-Tuning: Learning to Discover Across 371 Optimization Tasks
Young-Jun Lee, Seungone Kim, Minki Kang +5
Would experience designing faster GPU kernels also help close in on a long-standing open mathematical conjecture? Large Language Models (LLMs) integrated into evolutionary search h…
SAAS: Self-Aware Reinforcement Learning for Over-Search Mitigation in Agentic Search
Yunbo Tang, Chengyi Yang, Shiyu Liu +4
Agentic search enables LLMs to solve complex multi-hop questions through iterative reasoning and external search. Despite the effectiveness, these systems often suffer from a criti…
LegalGraphRAG: Multi-Agent Graph Retrieval-Augmented Generation for Reliable Legal Reasoning
Zerui Chen, Qinggang Zhang, Zhishang Xiang +5
Graph-based Retrieval-Augmented Generation (GraphRAG) advances flat document retrieval by structuring knowledge as relational graphs, enabling more coherent and effective reasoning…
Beyond Black-Box Interventions: Latent Probing for Faithful Retrieval-Augmented Generation
Linfeng Gao, Qinggang Zhang, Baolong Bi +9
Retrieval-Augmented Generation (RAG) systems often fail to maintain contextual faithfulness, generating responses that conflict with the provided context or fail to fully leverage…
SafeRBench: Dissecting the Reasoning Safety of Large Language Models
Xin Gao, Shaohan Yu, Zerui Chen +8
Large Reasoning Models (LRMs) have significantly improved problem-solving through explicit Chain-of-Thought (CoT) reasoning. However, this capability creates a Safety-Helpfulness P…