Recent advances in Reinforcement Learning (RL) have substantially improved the capabilities of autonomous search agents, enabling sophisticated planning, and iterative retrieval over dynamic information sources. However, optimizing language models for specialized search behaviors often incurs an alignment tax, where gains in search performance come at the expense of general-purpose capabilities, limiting their effectiveness as universal assistants.
Post-training Large Language Models (LLMs) with Reinforcement Learning (RL) has become an important tool for improving model capabilities, but the LLM action-space structure introduces challenges distinct from classical RL, with implications for inducing exploration. New methods are required that leverage the broad knowledge and flexibility of pre-trained LLMs to deliberately generate diverse experience at training time.
On-policy distillation (OPD) provides teacher supervision on states visited by the student, reducing the distribution gap between training and inference. However, in multi-turn agentic tasks, student deviations may accumulate over time, gradually moving the trajectory away from states where teacher guidance remains effective.
Large language models (LLMs) are increasingly extended into deep search agents that solve complex questions through multi-step interaction with external search and browsing tools. However, existing agents often incur substantial computational and interaction costs, generating lengthy trajectories that contain redundant queries, inefficient exploration, and irrelevant observations.
arXiv:2605. 26168v2 Announce Type: replace-cross Abstract: Any device that runs Linux uses the Linux page cache, a central pillar in OS and application performance, serving to reduce extraneous disk access.
By Zejia Qi
arXiv:2607. 28826v1 Announce Type: new Abstract: Autonomous Cyber Operations (ACO) are increasingly important for defending enterprise networks as cyber threats continue to evolve in sophistication.
By Konur Tholl, Fran\c{c}ois Rivest, Mariam El Mezouar, Adrian Taylor, Ranwa Al Mallah
arXiv:2607. 28633v1 Announce Type: cross Abstract: Disaggregated LLM inference creates a datacenter networking problem that no existing system solves correctly.
By Sanjeev Rao Ganjihal
arXiv:2607. 29320v1 Announce Type: new Abstract: Graphical user interface (GUI) agents based on large language models are increasingly deployed across mobile, web, and desktop environments.
By Hang Yan, Zhangxuan GU, Beitong Zhou, Jiaxuan Chen, Runze Li, Yusong Hu, Shuheng Shen, Changhua Meng
arXiv:2607. 28699v1 Announce Type: cross Abstract: KV-cache quantization is validated today by offline benchmark averages; a deployed system cannot tell whether compression is damaging the request it is serving right now.
By Fanzhe Wei, Li Liu
arXiv:2607. 28659v1 Announce Type: new Abstract: Cross-domain sequential recommendation (CDSR) aims to model users' dynamic interest transitions and sequential patterns across multiple domains.
By Yuxuan Hu, Yuhao Wang, Tianbo Huang, Chao Zhang, Ziwei Liu, Lihua Zhang, Xiangyu Zhao
arXiv:2607. 29221v1 Announce Type: cross Abstract: We address the challenge of securely and efficiently outsourcing AI computations from a trusted but computationally weak client to an untrusted but powerful server, in the setting where the client holds both the input and the model, and the server must learn neither.
By James Hsin-yu Chiang, Sheila Zingg, Kari Kostiainen, Srdjan Capkun
arXiv:2607. 29235v1 Announce Type: cross Abstract: Although world-action models (WAMs) enhance long-horizon robot control by predicting visual evolution before acting, long-horizon reliability demands repeated re-grounding in real observations--not recursive rollout.
By Peize Li, Ruimeng Zhang, Ru Zhang, Cong Huang, Kai Chen, Shanghang Zhang
arXiv:2605. 17160v2 Announce Type: replace-cross Abstract: Model quantization is widely used to reduce memory, latency, and deployment cost, and is typically judged by whether predictive accuracy is preserved.
By Chaymae Yahyati, Ismail Lamaakal, Khalid El Makkaoui, Ibrahim Ouahbi
arXiv:2605. 15100v2 Announce Type: replace Abstract: Large Language Models (LLMs) have demonstrated remarkable abilities in reasoning.
By Rongman Xu, Yifei Li, Tianzhe Zhao, Yanrui Wu, Bo Li, Hang Yan
arXiv:2607. 29209v1 Announce Type: cross Abstract: 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 stronger teacher for a dense advantage but caps performance at teacher quality and discourages exploration beyond it.
By Yifan Ding, Xincheng Wei, Yoshua Y. Li, Ziheng Li, Yuquan Lu, Siyu Zhang, Dongsheng Ma, Rongxiang Weng, Xunliang Cai, Yun Chen
arXiv:2607. 29071v1 Announce Type: cross Abstract: Federated learning of foundation models faces a fundamental resource-asymmetry challenge: the institutions holding the most valuable domain-specific data cannot host billion-parameter models.
By Shengkun Zhu, Jinshan Zeng, Zhihua Allen-Zhao, Mayi Xu, Quanqing Xu, Wei Ren, Qiang Yang, Yang Liu
arXiv:2607. 28955v1 Announce Type: cross Abstract: AI-generated videos are becoming increasingly realistic and difficult to distinguish from authentic ones, which facilitates malicious misuse and poses growing threats to cybersecurity and social governance.
By Renxi Cheng, Chaolei Han, Jie Gui, Hongsong Wang
arXiv:2607. 29158v1 Announce Type: cross Abstract: We introduce implicit machine learning force fields (I-MLFFs), which replace explicit stacks of neural network layers with self-consistent fixed-point equations.
By Johannes Mae{\ss}, Leon Werner, J. Thorben Frank, Winfried Ripken, Martin Michajlow, Joshua Futterer, Klaus-Robert M\"uller, Stefan Chmiela
arXiv:2607. 28986v1 Announce Type: cross Abstract: Zero-shot image captioning (ZIC) describes images without paired image-caption supervision during captioner training, relying on text-only corpora and frozen pretrained image-text scorers.
By Duy Tran Thanh, Thien-Phuc Doan, Long Nguyen-Vu, Ngo Tan Vu Khanh
arXiv:2602. 07339v2 Announce Type: replace Abstract: Diffusion-based trajectory planners can model multi-modal driving behavior, but their iterative denoising process introduces a latency bottleneck for real-time closed-loop deployment.
By Ruturaj Reddy, Hrishav Bakul Barua, Junn Yong Loo, Thanh Thi Nguyen, Ganesh Krishnasamy