The paper introduces APEX, an active defense for large language model agents that protects against indirect prompt injection by enforcing safety at execution boundaries. APEX uses an evidence‑gated prevention contract and deception‑based exposure to ensure that only authorized effects, endorsed by the task, are executed. Evaluation shows APEX achieves near‑zero attack success across multiple benchmarks and capability‑unit types, outperforming 13 baseline defenses.
By Xinran Zheng, Xin Fan Guo, Zhiqiang Hao, Fan Yang, Xingzhi Qian, Jiawei Du, Jinfeng Xu, Zheng Xing, Shuo Yang, Xingjun Wang
arXiv:2610.06977v1 Announce Type: cross
Abstract: Multimodal large language models (MLLMs) remain vulnerable to transferable adversarial examples, especially in black-box settings where only open-sou...
By Xiaojun Jia, Simeng Qin, Yiming Li, Jie Liao, Sensen Gao, Ke Ma, Yang Liu, Xiaochun Cao
arXiv:2610.06993v1 Announce Type: cross
Abstract: Evolution Strategies (ES) enable memory efficient full parameter fine-tuning of large language models (LLMs) using only forward computation. However,...
By Zhishen Sun, Hongzhan Wang, Sizhe Dang, Guang Dai, Haishan Ye
arXiv:2610.07062v1 Announce Type: cross
Abstract: Large language models are increasingly used to simulate how individuals respond to new situations, yet the behavioral reasoning behind these response...
By Yining Zhao, Bushi Liu, Haofei Yu, Zhengyang Qi, Shanyong Wang, Chuyue Li, Yuxiang Liu, Jiaxuan You
PlaySuite is a large-scale benchmark that evaluates interactive visual intelligence by using over 5,000 open-source video games from platforms like PyWeek and itch.io. The benchmark covers diverse game engines (Pygame, HTML5, Godot, Unity) and introduces a unified closed-loop interaction framework and a Video-LLM-as-a-judge protocol to standardize progress measurement. Evaluation of fourteen recent models shows a perception-action gap, with strong reasoning but poor sustained progress, spatial grounding, action execution, and self-correction.
By Dheeraj Varghese, Anna Vettoruzzo, Walter Simoncini, Michelle Lorena Acevedo Callejas, Mohammad Mahdi Derakhshani, Kristof Meding, Joaquin Vanschoren, Cees G. M. Snoek
arXiv:2610.07177v1 Announce Type: cross
Abstract: An open contrastive decision model is near chance as a judge on the hard public benchmarks: Contrastive-LM/CLM-v0.1-8B scores between 0.351 (best- of...
By Gowthamkumar Nandakishore
The paper introduces TraceDSE, an agentic design space exploration framework for jointly mapping AI inference workloads to heterogeneous edge SoCs and configuring each processing unit. Unlike traditional black-box optimization, TraceDSE uses a proposer‑critic loop powered by large language models and enriched with system execution traces to identify bottlenecks and refine design choices. Experiments on an Intel Meteor Lake SoC show that TraceDSE outperforms state‑of‑the‑art evolutionary and Bayesian methods, improving Pareto frontier hypervolume by up to 68% while reducing hardware evaluations by 6–9×.
By Geetha Prasuna Yarramneni, Surya Selvam, Wilfried Haensch, Anand Raghunathan
The paper introduces FlowAgent, an AI agent deployed at Google to automatically repair test failures in the pre-submit continuous integration workflow. FlowAgent uses a ReAct-style generate-and-validate loop with strict latency and quality filters, and was evaluated on 195 real-world failures with a 67.18% accuracy rate. After deployment, it suggested fixes on 295,508 changes, with developers previewing 65,069 and applying 28,554, and received positive feedback from interviews.
By Celal Ziftci, Spencer Greene, Ray Liu, Livio Dalloro, Lorenzo Dini
arXiv:2610.07335v1 Announce Type: cross
Abstract: Improving the reliability of large language model (LLM) agents in long-horizon decision-making remains a key challenge. When deployed as autonomous a...
By Heewon Park, Somin Im, Minhae Kwon
The paper introduces SEMAADB, a dataset comprising 3,000 engineering contexts and 15,000 SysML diagrams, each context containing five interconnected views (Requirement, Block Definition, Activity, State Machine, and Sequence). The authors verified diagram consistency and created a 100-context human‑verified benchmark. They evaluated three language models on diagram repair and cross‑diagram update tasks, finding that while syntax repair is largely solved, semantic repair and cross‑diagram consistency remain challenging.
By Ardalan Aryashad, Yan Jin
arXiv:2610.07384v1 Announce Type: cross
Abstract: Individual animal re-identification from camera-trap imagery is an instance retrieval problem central to non-invasive wildlife monitoring: a query im...
By Turhan Can Kargin, Piotr Kubaty, Ekaterina Rostovskaya, Izabela Wierzbowska, Bartosz Zieli\'nski, Marcin Przewi\k{e}\'zlikowski
arXiv:2610.07532v1 Announce Type: cross
Abstract: LLMs have advanced rapidly, raising growing concerns about their safety. Recent work has proposed approaches to detect and defend against attacks inc...
By Wonjun Lee, Kyungsik Yang, Gaeun Ji, Vaidehi Patil, Haon Park, Bumsub Ham, Mohit Bansal, Suhyun Kim
arXiv:2610.07557v1 Announce Type: cross
Abstract: Static-analysis checker synthesis requires agents to interpret a defect specification, inspect a repository, implement analyzer-specific logic, and r...
By Hang He, Li Wang, Hao Chen, Yuchen Shao, Yuling Shi, Lisheng Wang, Peiyang Liu, Goose Lin, Zaiyuan Wang, Haiying Sun, Ting Su, Chengcheng Wan
arXiv:2610.07625v1 Announce Type: cross
Abstract: Automated research systems increasingly run LLM agents over long horizons, but more inference does not by itself produce more progress: agents replay...
By Qizheng Zhang, Changxiu Ji, Isaac Sun, Yuetai Li, Shubhangi Upasani, Sherry Ruan, Boyuan Ma, Fenglu Hong, Vamsidhar Kamanuru, Yoonho Lee, Yuzhen Mao, Genghan Zhang, Rulin Shao, Qiuyang Mang, Andy Dimnaku, Changran Hu, Radha Poovendran, Kunle Olukotun
arXiv:2610.07731v1 Announce Type: cross
Abstract: Dense retrieval models are typically trained with contrastive objectives that learn effective representations but do not directly optimize retrieval...
By Qi Liu, Fengming Liang, Yiqun Chen, Erhan Zhang, Jiaxin Mao
arXiv:2610.07832v1 Announce Type: cross
Abstract: Large language models (LLMs) equipped with terminal access have demonstrated strong capabilities in automating software engineering tasks. However, e...
By Haibo Jin, Xinjie Li, Peng Kuang, Haohan Wang
arXiv:2610.07863v1 Announce Type: cross
Abstract: Long-horizon LLM agents act on an append-only interaction history that is re-sent to the model at every step, so the context and its cost grow with s...
By Yupeng Su, Jiayi Tian, Zheng Zhang, Souvik Kundu
arXiv:2610.07885v1 Announce Type: cross
Abstract: Electrocardiogram (ECG) delineation, the identification of waveform boundaries, is a foundational step that translates raw ECG signals into clinicall...
By Jeonghwa Lim, Minje Park, Yeongyeon Na, Yujin Eom, Soyeon Lim, Young Ho Lee, Yu Jeong Kim, Sunghoon Joo, Ki Hong Lee
arXiv:2610.07913v1 Announce Type: cross
Abstract: Gastric adenocarcinoma (GA) is a leading cause of cancer-related mortality worldwide, and accurate histopathological subtype classification from whol...
By Shrihari Dumbre, Bikash Santra
arXiv:2610.07940v1 Announce Type: cross
Abstract: Looped language models apply the same stack of layers T times to each token, which deepens the model without adding parameters but multiplies its key...
By Yuhan Chen, Siyuan Zhang, Nan Wang, Feiyang Kang, Ruoxi Jia