50 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…
CAP: A Scalable Benchmark for Evaluating Cross-Site Browser Agents with Complex Actions and Perception
Zejun Xu, Taiyi Chen, Jin Li +13
Large language models are increasingly deployed as autonomous agents that interact with the web through browsers. While recent progress has been driven by benchmarks that evaluate…
Demystifying On-Policy Distillation: Roles, Pathologies, and Regulations
Rui Wang, Hongru Wang, Yi Chen +4
The paper investigates how on-policy distillation guides large language model students during training, identifies two main failure modes—student‑teacher mismatch and length exploi…
Learning from Own Solutions: Self-Conditioned Credit Assignment for Reinforcement Learning with Verifiable Rewards
Yingyu Shan, Yuhang Guo, Zihao Cheng +7
Reinforcement learning with verifiable rewards (RLVR) has driven substantial progress in training LLMs for reasoning tasks, but representative methods such as GRPO assign uniform c…
From Knowing to Acting: Benchmarking Self-Awareness Capability of LLM Agents
Yifan Li, Shengbin Yue, Boyu Feng +6
The integration of external tools has transitioned LLM agents from passive responders to autonomous systems. However, current benchmarks prioritize execution success, neglecting se…
Multi-Turn Evaluation of Deep Research Agents Under Process-Level Feedback
Rishabh Sabharwal, Hongru Wang, Amos Storkey +1
Existing benchmarks for deep research agents (DRAs) assess only single-shot outputs, ignoring a key question: can DRAs improve their reports when guided by feedback? To investigate…