8 citations · 43 across the 33 of their papers we have counts for
34 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…
Demystifying On-Policy Distillation: Roles, Pathologies, and Regulations
Rui Wang, Hongru Wang, Yi Chen +4
On-policy distillation (OPD) has become a key paradigm in LLM post-training, yet its training dynamics remain poorly understood. We present a systematic study examining the role, p…
WebAggregator: Enhancing Compositional Reasoning Capabilities of Deep Research Agent Foundation Models
Rui Wang, Ce Zhang, Jun-Yu Ma +10
The hallmark of Deep Research agents lies in compositional reasoning, the capacity to aggregate distributed, heterogeneous information into coherent logical insights. However, curr…
Position: Agent Should Invoke External Tools ONLY When Epistemically Necessary
Hongru Wang, Cheng Qian, Manling Li +6
As large language models evolve into tool-augmented agents, a central question remains unresolved: when is external tool use actually justified? Existing agent frameworks typically…
Acting Less is Reasoning More! Teaching Model to Act Efficiently
Hongru Wang, Cheng Qian, Wanjun Zhong +7
Tool-integrated reasoning (TIR) augments large language models (LLMs) with the ability to invoke external tools during long-form reasoning, such as search engines and code interpre…
Self-Reasoning Language Models: Unfold Hidden Reasoning Chains with Few Reasoning Catalyst
Hongru Wang, Deng Cai, Wanjun Zhong +4
Inference-time scaling has attracted much attention which significantly enhance the performance of Large Language Models (LLMs) in complex reasoning tasks by increasing the length…