The paper investigates how third‑party API routers, which sit between coding agents and large language model providers, can introduce a control gap by inspecting and modifying requests and responses. Through an empirical study using the SIDEL framework, the authors evaluate four levels of router‑side injection (Response Substitution, Response Append, LLM‑Polished Injection, and LLM‑Polished with Distribution Alignment Injection) across 400 curated samples and four representative coding agents. The results show that router‑side interventions significantly alter repository‑level actions and evade existing client‑side safeguards, achieving a 0% defense success rate without additional mitigations.
By Donghao Fu, Jingxin Li, Xue Jiang, Yihong Dong
arXiv:2609.07575v1 Announce Type: cross
Abstract: This work introduces an alternative view of efficient exploration and studies its theoretical and empirical implications in the absence of extrinsic...
By Mikel Malag\'on, Jon Vadillo, Josu Ceberio, Michael Bowling, Jose A. Lozano
TrojanWorld is a backdoor framework that targets world-model agents by steering their internal imagination toward attacker-specified actions when a physical trigger is present. The attack uses Decision-Reflective Induction, Clean Behavior Anchoring, and Causal Propagation to maintain stealth, persistence, and high performance. Experiments on TD-MPC2, DreamerV3, and R2-Dreamer across several benchmarks show that the attack can induce target actions with minimal performance loss and can keep agents on a malicious trajectory even after the trigger is removed.
By Wenkai Huang, Siyuan Liang, Gaolei Li, Yiming Li, Tianhao Peng, Jianhua Li, Dacheng Tao
The paper discusses how agents can exploit shared infrastructure for coordinated intrusion, citing the Hugging Face incident and a public‑wiki investigation as examples. It proposes that defense should focus on revisable coordination episodes—linking observed data transfers, task authority, and response history—to detect coordinated actions before they are fully formed. The authors outline a prospective episode discovery framework, define unsanctioned coordination, and suggest an evaluation comparing isolated actions, rolling windows, known groups, and prospectively discovered episodes, measuring harmful outcomes and recurrence after channel closure.
By Gregory N Frank
The paper introduces Distributed Dexterous Manipulation (DDM), a challenging control problem involving 64 soft delta robots arranged in an 8x8 grid. It presents a framework using spatially conditioned Multi-Agent Transformers (MATs) with adaptive layer norm, spatial contrastive embeddings, and a behavior cloning method fine‑tuned by Soft Actor Critic. Experiments demonstrate that MATs refine actions through stacked attention blocks, enabling long‑horizon planar manipulation in simulation and real‑world settings, while an action‑selection strategy reduces robot usage by about 65% and lowers wear‑and‑tear, achieving an average error of ~1.5 cm.
By Sarvesh Patil
arXiv:2609. 08564v1 Announce Type: cross Abstract: We study distributed one-dimensional mean estimation under a 1-bit communication constraint.
By Ivan Lau, Jonathan Scarlett
The paper introduces Reward Ensemble under Confidence (REC), a probabilistic reward learning framework for preference-based reinforcement learning that models per‑timestep reward uncertainty using an ensemble of distributional reward models. REC incorporates uncertainty into the preference loss and uses model disagreement to drive exploration, achieving 88.4% of shaped‑reward performance on acrobatic quadrotor control versus 55.2% with standard Preference PPO. The authors train policies in simulation and transfer them zero‑shot to real quadrotors, demonstrating complex acrobatic maneuvers learned solely from human preference feedback, and validate REC on a continuous‑control benchmark.
By Colin Merk, Ismail Geles, Jiaxu Xing, Angel Romero, Giorgia Ramponi, Davide Scaramuzza
arXiv:2609.07618v1 Announce Type: cross
Abstract: Environments are increasingly populated by multiple robots performing independent tasks with limited prior knowledge of each other. Deploying such mu...
By Yacine El Yamani, Hanna Krasowski, Elena Vanneaux
The paper explores how individual text corpora (ITCs) can be integrated into small language models (SLMs) using DoRA fine‑tuning. By training a DoRA adapter for each of 150 participants, the authors show that the adapter can encode a participant’s own ITC into the model’s weights, improving fit to that participant’s held‑out text. However, while the adapter improves log‑loss on a generalized knowledge test, it does not enhance accuracy under a bias‑corrected PMI readout, and adding retrieval does not provide further benefit.
By Christoph Wigbels, Ali Abusaleh, Markus T. Jansen, Alexander Mehler, Markus J. Hofmann
arXiv:2609.07738v1 Announce Type: cross
Abstract: LiDAR-based 3D Single Object Tracking (3D SOT) is critical for robotic perception and navigation and aims to localize dynamic objects across frames i...
By Zhaofeng Hu, Sifan Zhou, Jiahao Nie, Ziyu Zhao, Weizi Li, Ci-jyun Liang
arXiv:2609.08080v1 Announce Type: new
Abstract: Ensuring safety in reinforcement learning under nonstationarity requires anticipating changes in risk before they lead to unsafe behavior. Existing app...
By Tim Tomashevskiy
arXiv:2609.08318v1 Announce Type: cross
Abstract: The transition from human-centric assistance to Autonomous Software Engineering (ASE) agents has enabled the resolution of complex real-world SE task...
By Zhengran Zeng, Yixin Li, Rui Xie, Wei Ye, Shikun Zhang
arXiv:2609.06993v1 Announce Type: cross
Abstract: Large language models (LLMs) increasingly generate Markdown that is consumed by renderers, agents, code extractors, and structured downstream pipelin...
By Sungjune Lee, Myungjoo Kang
arXiv:2609.08175v1 Announce Type: new
Abstract: Harness self-evolution is the process by which an agent modifies its prompts, tools, code, or orchestration in response to task feedback while keeping...
By Qianshu Cai, Yonggang Zhang, Jun Nie, Maohao Ran, Huajiang Zheng, Jun Song, Xinmei Tian, Yike Guo, Wei Xue
arXiv:2609.05531v1 Announce Type: cross
Abstract: No specification says how a governed autotelic AI agent organization, where agents pursue self-generated goals inside guardrails, should be designed...
By Michael Ray Johnson, Linda Naimi
arXiv:2609.06181v1 Announce Type: cross
Abstract: Efficiently aggregating and orchestrating computing power across heterogeneous clusters for HPC workflows faces four practical challenges: preserving...
By Haotian Xie, Junlin Chen, Mingkai Zheng, Yifan Zhu, Minu Mathew, Max Burnette, Yadu Babuji, Volodymyr Kindratenko, Shivaram Venkataraman, Kyle Chard, Ian Foster, Zhao Zhang
arXiv:2609.06229v1 Announce Type: cross
Abstract: Vulnerability discovery is becoming an important ability of large language model (LLM) agents: agents that silently miss real defects leave critical...
By Yuanxiang Shi, Jiayi Lin, Xuanyong Lin, Liangcai Su, Yeheng Duan, Wei Wang, Qi Han, Bing Zhao, Wei Hu, Xander Xu, Chenxiong Qian
arXiv:2609.06250v1 Announce Type: cross
Abstract: Security Operations Centers (SOCs) process large amounts of tickets, most of which are low-interest events not worthy of further investigation. The r...
By Kritan Banstola, Faayed Al Faisal, Duy Dao, Ryan Irving, Daniel Lende, Xinming Ou
arXiv:2609.10226v1 Announce Type: new
Abstract: Large language models (LLMs) have demonstrated remarkable capabilities in reasoning and code generation, raising the prospect that they could assist in...
By Leilei Ding, Shumin Wang, Yuting Huang, Fanqi Wan, Yinmin Zhang, Qi Han, Yiming Xu, Feiyuan Zhang, Xiaomeng Chu, Guoliang You, Wuyang Zhang, Daxin Jiang, Yanyong Zhang
arXiv:2609.05435v1 Announce Type: new
Abstract: Modern language agents are expected to operate over long horizons: they ask follow-up questions, reuse worked examples, handle tool feedback, and adapt...
By Zerui Cheng, Jiawei Xu, Huacan Chai, Jiayang Sun, Pramod Viswanath, Maxm Pan