Tuesday, November 17, 2026
Translate
PrivacySubmit newsShare your story Newsletter Advertise
Breaking
Research news

Research Radar, October 2, 2026: 11 new AI and security papers to know

The most relevant new AI and security research from Nature & arXiv, with the authors' own summaries and links to the papers.

11 papers, Nature & arXiv

New research on AI and security, selected for relevance to language models, AI agents and cybersecurity. Summaries are the authors’ or publisher’s own words, linked to the original.

Peer-reviewed

Large language models discover complementary heuristics for combinatorial optimization

Nature

Sign of the times: AI lingo muscles into esteemed dictionary

Nature

The TechUpscale Brief. The day's cyber, AI and tech news in one short email, every weekday morning. Free. Unsubscribe anytime.

Sign of the times: AI lingo muscles into esteemed dictionary

Nature

New preprints (not yet peer-reviewed)

From A2A Attacks to Envelope-Layer Defense: Red-Teaming Evaluation of LLM Agents and a Three-Layer Isomorphic Attack-Defense Model

arXiv · Yuelin Han

Agent interaction protocols such as ACP and A2A have moved LLM-based agents toward multi-agent collaboration, introducing new security threats. A task sent by a remote peer over A2A is treated as a legitimate request, providing a natural channel for indirect prompt injection.

HarnessAgent: Scaling Automatic Fuzzing Harness Construction with Tool-Augmented LLM Pipelines

arXiv · Kang Yang, Yunhang Zhang, Zichuan Li, Guanhong Tao, Jun Xu, Xiaojing Liao

Large language model (LLM)-based techniques have achieved notable progress in generating harnesses for program fuzzing. However, applying them to arbitrary functions (especially internal functions) textit{at scale} remains challenging due to the requirement of sophisticated contextual information, such as specification, dependencies, and usage examples.

SyzHarness: Patch-Based Kernel Bug Reproduction with LLM-Synthesized Fuzzing Harnesses

arXiv · Xingyu Li, Juefei Pu, Haonan Li, Arrdya Srivastav, Kareem Shehada, Srikanth V. Krishnamurthy, Zhiyun Qian

Automated kernel vulnerability reproduction is essential for bug triage, patch validation, and regression testing, but still lacks an effective and efficient solution. The core challenge is twofold: a reproducer must first recover the trigger scaffold needed to reach the vulnerable state and determine the precise concrete values that actually trigger the bug.

No One Architecture Fits All: A Cross-Environment Evaluation of Hierarchical Red Team Agents

arXiv · Ayan Javeed Shaikh, Arunesh Sinha, Nathaniel D. Bastian, Ankit Shah

Autonomous red team agents increasingly stress-test AI-enabled cyber defenses by planning strategy and executing multistage attacks. Reinforcement learning (RL) and large language models (LLMs) offer complementary mechanisms for the planning and execution such agents require, and prior work has combined them in hybrid hierarchies.

A rubric landscape for evaluating clinical reasoning in large language models: what exists, what is missing, and what needs to be combined

arXiv · Zhangshu Joshua Jiang, Zina Ibrahim, James T. Teo

Exam-style accuracy does not establish whether large language models (LLMs) reason well over clinical records. We define clinical reasoning as integrating and updating evidence across time and sources to form, revise and justify a patient's problem representation and a defensible plan.

Spatial Strategies, Not Actions: Vector-Quantized Geodesics as Tools for LLM-Driven Agents

arXiv · Gabriel Turinici

Large language model (LLM) based agents are often criticized for lacking spatial understanding and mainly exploiting statistical text patterns. We investigate their spatial comprehension through an architecture combining geometrical tools with a LLM serving as a high-level orchestrator in grid-world environments.

UnifiedAttack: Evaluating the Safety of Large Multimodal Models in Synergistic Harmful Image-Text Generation

arXiv · Bingjun Luo, Jialin Guo, Tony Wang, Siqi Li

As Large Multimodal Models (LMMs) transition toward natively unified architectures, evaluating their safety in synergistic harmful image-text generation tasks becomes a critical challenge. Unlike unimodal threats, synergistic risks emerge when text and image modalities are coordinated to produce harm that significantly exceeds their individual components.

Safety of Latent Communication in Multi-Agent Systems

arXiv · Muhammad Huzaifa, Sina Mavali, Thorsten Eisenhofer

Latent communication enables multi-agent systems to exchange information directly in internal representation space, reducing the token, computation, and latency overhead of text-based communication. To this end, lightweight trainable links are introduced to map the sender's representations into the receiver's input space.

Add TechUpscale as a preferred source on Google

The TechUpscale Brief

The day's cyber, AI and tech news in one short email, every weekday morning. Free. Unsubscribe anytime.

I'm most interested in

Join the conversation

Comments are moderated. Be civil and stay on the story: no personal attacks, hate, spam or ads, and no one else's private details. Your email is never shown. Privacy policy.

More Research