arXiv:2608.23045v1 Announce Type: new
Abstract: Web search agents powered by Large Language Models (LLMs) show strong promise, but deep research tasks expose a recurring failure mode: once an agent h...
By Xiangxin Zhang, Zhanwei Zhang, Zhihang Fu, Binbin Lin, Wenxiao Wang
The paper introduces Traverse, an autonomous web‑search agent that manages its search process through three states—Rubric, Answer, and Verify—while using a Seal Memory tool for active context management. Reinforcement learning is employed to train the agent, but a training instability called Seal Collapse is mitigated by training only the final segment after context management. The resulting 35B model achieves state‑of‑the‑art performance on BrowseComp and related benchmarks, outperforming comparable open‑source systems.
By Jingyuan Ma, Lynx Aster, He Zhang, Siyao Song, Weijie Yuan, Zhe Zhang, Kai Jia, Zhifang Sui
arXiv:2608. 12847v1 Announce Type: new Abstract: Retrieval can identify a past trajectory that may matter, yet it does not specify how an acting agent should use that trajectory after users, entities, constraints, or environment state have changed.
By Yifei Li, Heng Wang, Lingling Zhang, Muye Huang, Xinyu Zhang, Jiashuai Liu, Hang Yan, Rongman Xu
arXiv:2607. 08032v1 Announce Type: new Abstract: Large language models, and the agents built on them, spend an ever-growing share of their compute and memory on remembering: caching attention keys and values, carrying long prompts, maintaining recurrent state, and storing what happened in previous turns and sessions.
By Ashwin Gerard Colaco, Nada Lahjouji
arXiv:2607. 23809v1 Announce Type: new Abstract: Agentic tasks are inherently long-horizon and multi-turn, constantly accumulating context through interactions with the environment.
By Xiaochuan Li, Ryan Ming, Meng Chu, Shuai Shao, Rong Jin, Chenyan Xiong
arXiv:2608. 16370v1 Announce Type: new Abstract: Task completion is the standard metric for evaluating context compression, yet it is incomplete: compression can increase an agent's interaction cost by forcing it to reacquire dropped state while leaving completion statistically unchanged.
By Shuyu Liu