The paper presents a defense‑in‑depth framework for large language models that separates internal activation steering from external memory handling to combat sycophancy. It evaluates four open‑weight models on a new MemSyco‑Bench dataset, testing five memory‑defense configurations—including a Router Gate that selectively rewrites, keeps, or drops memories—and measures sycophancy and accuracy across 1,550 items. Results show that selective Router Gate filtering preserves more accuracy than complete memory removal, while inverse steering slightly reduces sycophancy but is not statistically significant.
By Ritvij Sharma, Russell Dlugosz, Ryan Zhou, Maheep Chaudhary
PsyCIDRA is a dual‑agent framework that couples a free‑form psychiatric interviewer with a diagnostic reasoning agent to support expert review. The interviewer agent uses tools to keep working notes, load expert skills, and pull ICD‑11 references, while the diagnostic agent receives the interview transcript and generates hypotheses with supporting, conflicting, and missing evidence, withholding a final hypothesis if insufficient support exists. In simulations and a blinded human study, PsyCIDRA achieved higher diagnostic agreement and rank‑1 accuracy than direct prompting, indicating its promise for assisting psychiatric assessment through interactive dialogue.
By Milad Mohammadi, Fatemeh Akrami Shamsabadi, Zahra Mohseni, Amirhossein Safdarian, Malekfarhad Malek, Hadi Moradi, Hesham Faili
arXiv:2610.07521v1 Announce Type: new
Abstract: Driving models increasingly ground reasoning in causal relations, spatial structure, perceptual evidence, and predicted futures. These advances make re...
By Minkyoung Cho, Zewei Zhou, Wenhao Ding, Shuhan Tan, Boyi Li, Yuxiao Chen, Yan Wang, Zheng Lian, Min-Hung Chen, Chaowei Xiao, Zhuoqing Mao, Boris Ivanovic, Marco Pavone, Yulong Cao
arXiv:2610.07544v1 Announce Type: new
Abstract: Large language models (LLMs) are increasingly used to judge how well an advertisement matches a query, but the fairness of these judgments has received...
By Weiwei Wang, Yinchuan Xu, Jialu Gao, Youkow Homma, Jian Jiao
arXiv:2610.07582v1 Announce Type: new
Abstract: Quantitative imaging pipelines can produce precise but systematically different measurements of the same object. We present an empirical reliability as...
By Farouk Ganiyu Adewumi, Timothy Oladunni
The paper presents a symbolic sub‑policy model for chess that incorporates domain knowledge to improve interpretability. By adapting patterns learned through inductive logic programming (PAL), the authors evaluate the model using a divergence metric against a random baseline and show that it can suggest moves comparable to a human beginner. They also propose a computational evaluation scheme that augments an existing engine with their model.
By Abhijeet Krishnan, Chris Martens
OTel is an open telecom AI resource that provides derived datasets for retrieval, reranking, instruction tuning, and safety/abstention, along with 30 full‑parameter post‑trained baselines covering 10 embedding models, 3 rerankers, and 17 language models. The project has seen significant community engagement, with over 16 million model downloads and more than 157 media mentions by May 2026. Post‑training on OTel data improves performance across all model families, achieving 93.1% NDCG@10 for embeddings, 0.947 MRR@10 for rerankers, and 87.8% correctness for language models.
By Farbod Tavakkoli, Gregory Diamos, Kenneth Church, David Kanter, Mark Austin, Imtiaz Karim, Mirza Masfiqur Rahman, Merouane Abdelkader Debbah, Zeinab Nezami, Ali Maatouk, Leandros Tassiulas, Rex Ying, Nick Sorros, Louis Powell, Nikolaos Vasiloglou, Ashish Vaswani, Somanshu Singla, Adarsh Chaluvaraju
arXiv:2610.08106v1 Announce Type: new
Abstract: Multimodal large language models (MLLMs) advance rapidly, while conventional benchmark development lags behind, delaying investigation of newly observe...
By Langxi Huang, Pingping Zhang, Lanyun Zhu, Chunyang Jiang, Jiawei Shao, Haocheng Yuan, Peilin Chen
arXiv:2610.08216v1 Announce Type: new
Abstract: Multimodal vision-language systems typically fuse image and text embeddings through classical operators such as concatenation, attention, bilinear pool...
By Srikar Alla, Ali Shiri Sichani, Chi-Ren Shyu
arXiv:2610.08250v1 Announce Type: new
Abstract: Large language models are increasingly used to simulate clients for counselor training and psychological counseling research, but reliable simulation r...
By Shixin Peng, Kun Jiang, Jiaxing Zheng, Qihao Yang, Jingying Chen
arXiv:2610.08363v1 Announce Type: new
Abstract: Maritime systems operate in highly dynamic environments where unexpected equipment failures can compromise safety, reliability, and operational efficie...
By Dionisis Kalogeropoulos, Georgia Sovatzidi, Panagiotis G. Kalozoumis, Dimitris K. Iakovidis
arXiv:2610.08647v1 Announce Type: new
Abstract: LLM-based agents solve complex multi-step tasks, but sequential execution incurs substantial latency. In principle, parallelizing work across multiple...
By Yexiong Lin, Shanshan Ye, Yu Yao, Zhen Fang, Bo Han, Tongliang Liu
arXiv:2610.08761v1 Announce Type: new
Abstract: Self-improving policies continually expose new failure patterns, changing what their judges must be able to verify. However, current fixed judges const...
By Zewei Zhou, Rachel Luo, Yulong Cao, Chaowei Xiao, Chensheng Peng, Boyi Li, Thomas Tian, Zheng Lian, Yan Wang, Jiaqi Ma, Boris Ivanovic, Marco Pavone, Wenhao Ding
arXiv:2610.05094v1 Announce Type: cross
Abstract: Researchers increasingly use Large Language Models as judges (LLM-as-a-judge) to evaluate model outputs. Yet there are no standards for how to design...
By Laur\`ene Vaugrante, Thilo Hagendorff
arXiv:2610.06892v1 Announce Type: cross
Abstract: Learning from human preference data is the dominant route to aligning language models with human values. In linear social choice, where rewards are l...
By Soumya Nasipuri, Sayak Ray Chowdhury, Sanjukta Roy
arXiv:2610.06927v1 Announce Type: cross
Abstract: The key-value (KV) cache of autoregressive transformers grows linearly with context length and dominates memory at long context. Most training-free r...
By Sara Abdali, Jongwoo Ko, Pashmina Cameron
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
The study audits the frequency and decoder‑depth claims of the audio jailbreak AdvWave‑P on the Qwen2‑Audio model. Using a protocol that masks frequency components in the short‑time Fourier transform domain, the authors evaluate attack success across 520 prompts, finding that 76.7% of adversarial inputs are labeled as jailbreaks. Detailed analyses show that masking specific frequency bands can sharply reduce attack success, with finer 16‑band partitions revealing that a narrow 7520‑7960 Hz band is critical, while global rescaling and re‑optimization experiments further illuminate the role of frequency partitioning and energy distribution in jailbreak effectiveness.
By Boyuan Chen, Minseok Kim, Sohaila Abdulsattar, Minghao Shao, Siddharth Garg, Ramesh Karri, Muhammad Shafique
arXiv:2610.07128v1 Announce Type: cross
Abstract: Aggregating the preferences of diverse user groups into a collective outcome raises fundamental challenges of equity, diversity, and inclusion (EDI):...
By Adji Marieme Sita Ciss\'e, Malek Mouhoub