5 papers
G-ReAct: Graph-Guided Deep Search via Structure-State Co-Evolution
Shaoxiong Yang, Mengyuan Zhang, Shaojun Lin +4
Deep search has become a fundamental capability of large language models (LLMs) for solving open-domain complex tasks. However, existing approaches typically rely on linear sequent…
MemReranker: Reasoning-Aware Reranking for Agent Memory Retrieval
Chunyu Li, Mengyuan Zhang, Jingyi Kang +6
In agent memory systems, the reranking model serves as the critical bridge connecting user queries with long-term memory. Most systems adopt the "retrieve-then-rerank" two-stage pa…
FutureMind: Equipping Small Language Models with Strategic Thinking-Pattern Priors via Adaptive Knowledge Distillation
Shaoxiong Yang, Junting Li, Mengyuan Zhang +3
Small Language Models (SLMs) are attractive for cost-sensitive and resource-limited settings due to their efficient, low-latency inference. However, they often struggle with comple…
ICPO: Intrinsic Confidence-Driven Group Relative Preference Optimization for Efficient Reinforcement Learning
Jinpeng Wang, Chao Li, Ting Ye +3
Reinforcement Learning with Verifiable Rewards (RLVR) demonstrates significant potential in enhancing the reasoning capabilities of Large Language Models (LLMs). However, existing…
MM-Eval: A Hierarchical Benchmark for Modern Mongolian Evaluation in LLMs
Mengyuan Zhang, Ruihui Wang, Bo Xia +2
Large language models (LLMs) excel in high-resource languages but face notable challenges in low-resource languages like Mongolian. This paper addresses these challenges by categor…