13 papers
Mitigating Context Interference for Reliable and Efficient Search Agents
Boyang Xue, Bin Wu, Shuofei Qiao +8
Recent research empowers Large Language Models (LLMs) as multi-turn search agents to iteratively retrieve and generate outputs until complex tasks are solved. However, the contexts…
ToolSelf: Unifying Task Execution and Self-Reconfiguration via Tool-Driven Emergent Adaptation
Jingqi Zhou, Sheng Wang, Dezhao Deng +9
LLM-powered agentic systems excel at complex long-horizon tasks, but remain constrained by static configurations fixed before execution. Such rigidity forces a trade-off between do…
TherapyGym: Evaluating and Aligning Clinical Fidelity and Safety in Therapy Chatbots
Fangrui Huang, Souhad Chbeir, Arpandeep Khatua +8
Large language models (LLMs) are increasingly used for mental-health support; yet prevailing evaluation methods--fluency metrics, preference tests, and generic dialogue benchmarks-…
ProReason: Multi-Modal Proactive Reasoning with Decoupled Eyesight and Wisdom
Jingqi Zhou, Sheng Wang, Jingwei Dong +6
Large vision-language models (LVLMs) have witnessed significant progress on visual understanding tasks. However, they often prioritize language knowledge over image information on…
QSpec: Speculative Decoding with Complementary Quantization Schemes
Juntao Zhao, Wenhao Lu, Sheng Wang +2
Quantization is widely adopted to accelerate inference and reduce memory consumption in large language models (LLMs). While activation-weight joint quantization enables efficient l…
TreeSynth: Synthesizing Diverse Data from Scratch via Tree-Guided Subspace Partitioning
Sheng Wang, Pengan Chen, Jingqi Zhou +7
Model customization necessitates high-quality and diverse datasets, but acquiring such data remains time-consuming and labor-intensive. Despite the great potential of large languag…