6 papers
Beyond Outcome Rewards: Step-Level Self-Distilled Policy Optimization for Deep Search Agents
Haoze Wu, Chuqiao Kuang, Tianyi Zhuang +1
Deep search agents operate over trajectories spanning dozens of steps, yet standard reinforcement learning provides only a single outcome reward per trajectory, which is far too sp…
UIS-Digger: Towards Comprehensive Research Agent Systems for Real-world Unindexed Information Seeking
Chang Liu, Chuqiao Kuang, Tianyi Zhuang +4
Recent advancements in LLM-based information-seeking agents have achieved record-breaking performance on established benchmarks. However, these agents remain heavily reliant on sea…
DeepDiver: Adaptive Search Intensity Scaling via Open-Web Reinforcement Learning
Wenxuan Shi, Haochen Tan, Chuqiao Kuang +7
Information seeking demands iterative evidence gathering and reflective reasoning, yet large language models (LLMs) still struggle with it in open-web question answering. Existing…
Pushing Test-Time Scaling Limits of Deep Search with Asymmetric Verification
Weihao Zeng, Keqing He, Chuqiao Kuang +2
Test-time compute can be scaled both sequentially and in parallel. Sequential scaling involves lengthening the generation process, while parallel scaling involves verifying and sel…
DocPuzzle: A Process-Aware Benchmark for Evaluating Realistic Long-Context Reasoning Capabilities
Tianyi Zhuang, Chuqiao Kuang, Xiaoguang Li +4
We present DocPuzzle, a rigorously constructed benchmark for evaluating long-context reasoning capabilities in large language models (LLMs). This benchmark comprises 100 expert-lev…
More Tokens, Lower Precision: Towards the Optimal Token-Precision Trade-off in KV Cache Compression
Jiebin Zhang, Dawei Zhu, Yifan Song +6
As large language models (LLMs) process increasing context windows, the memory usage of KV cache has become a critical bottleneck during inference. The mainstream KV compression me…