3 papers
cs.CL2026
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.…
cs.CL2026
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…
cs.CL2025
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…