37 papers
StreamTTT: Reconciling Real-Time Perception and Long-Term Memory in Streaming VLMs
Joya Chen, Zeyun Zhong, Mike Zheng Shou
Humans effortlessly perceive the present while remembering the past, yet streaming VLMs often trade off real-time perception against long-term memory. Prior work shows that shorten…
SAF-OPD: Stable Advantage Fusion for On-Policy Distillation
Yifan Ding, Xincheng Wei, Yoshua Y. Li +7
Reinforcement learning with verifiable rewards (RLVR) broadcasts a single response-level reward to every token, while on-policy distillation (OPD) scores each token against a stron…
ClawTrack: Towards Trace-Level Evaluation and Improvement of Real-World Autonomous Agents
Xingjian Wu, Xuhang Zhu, Xingchen Liu +6
The paper introduces ClawTrack, a benchmark that evaluates both the final outcomes and the step-by-step reasoning processes of LLM-based autonomous agents across multiple dimension…
Contrastive Reinforced Policy Optimization via Privileged Self-Distillation
Xingjian Wu, Junlin Liu, Xingchen Liu +6
The paper introduces Contrastive Reinforced Policy Optimization (CRPO), a method that frames on‑policy self‑distillation for large language models as a contrastive learning problem…
LoHoSearch: Benchmarking Long-Horizon Search Agents Beyond the Human Difficulty Ceiling
Jiarui Zhao, Rongzhi Zhang, Lingchuan Liu +3
Search agent benchmarks exemplified by BrowseComp have rapidly saturated over the past year, with the strongest models surpassing 90% accuracy. Since these benchmarks are predomina…
Doctor-RAG: A Failure-Aware Repair Framework for Agentic Retrieval-Augmented Generation
Shuguang Jiao, Chengkai Huang, Shuhan Qi +6
Agentic Retrieval-Augmented Generation interleaves retrieval and reasoning for multi-hop QA and complex knowledge tasks. As reasoning trajectories lengthen, failures become more fr…