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
Agentic AI systems for scientific discovery
CauTrigger: deciphering biological system state transitions by hierarchical causal decomposition
Tracing causal cascades underlying biological state changes
Using AI to offer personalized health advice
An AI tool improves weather forecasts up to a month ahead
Flexible multi-base-station cooperation towards 6G: a fully decoupled feedback-free access approach
New preprints (not yet peer-reviewed)
Exploring Jailbreak Vulnerability Across Depth-Based Dynamic Inference in Large Language Models
Large Language Models (LLMs) have been shown to be computationally expensive and vulnerable to jailbreak attacks, in which adversarial prompts bypass safety alignment and induce harmful responses. To address this inefficiency, a range of techniques have been proposed to enable efficient LLM inference.
Act on Your Behalf, Beyond Your Authorization: Benchmarking LLM Agent Authorization Alignment
When an LLM agent acts on behalf of a user, it is expected to act within the authorization scope the user grants. Existing agent evaluations largely measure task completion or harmful consequences and can therefore overlook actions that violate this delegation without producing conventional safety or privacy harms.
From Atomic to Agentic: Towards Interpretable Evaluation of LLMs' Agentic Mathematical Capabilities
Large Language Models (LLMs) are evolving from performing end-to-end mathematical reasoning to integrating agentic intelligence. However, most existing math benchmarks evaluate only final answers.
CoSec: Benchmarking Agent Security in Communities
LLM agents operate in persistent collaborative environments involving multiple users, communities, memories, files, and tools. Community boundaries may remain fixed or evolve with changes in membership, roles, composition, and relationships.
Beyond Binary Labels: Diagnostic Evaluation of LLM Safety with Prompt-Level Rubrics
Current LLM safety benchmarks predominantly rely on binary safe or unsafe labels, lacking explanatory depth and suffering from low consistency across automated judges. To address this, we introduce DiagSafe, a diagnostic evaluation framework that moves beyond binary classification by employing prompt-level rubrics.
Automating ML for Science: Can Frontier Agents Climb Scientific Hills in the Wild?
Frontier coding agents are increasingly framed as end-to-end automated researchers, and ML for science offers a demanding test of that promise: improving a scientific model often requires domain insight beyond routine ML engineering. We introduce Agent4Sci, a long-horizon testbed for measuring how far today's agents can improve the published best models on scientific ML benchmarks, spanning 20 benchmarks across 11 domains.
Black-Box Red-Teaming of Multi-Agent Systems via Reinforcement Learning
Large language model (LLM) agents are increasingly deployed in multi-agent systems (MAS) to accomplish complex tasks. Prior black-box red-teaming attacks mainly focus on single agents, but we find that these methods are far less effective in MAS, where multiple sub-agents may not directly interact with the user.
What Transfers from Text to Vision? Capability Scaling Laws and Transfer Dynamics for VLMs
Choosing the right large language model (LLM) backbone is the most consequential decision when building a vision-language model (VLM), yet it remains fundamentally unprincipled: compute-based scaling laws fail to generalize across model families, and no framework exists for directly predicting VLM performance before training begins. We propose the Capability-Driven Multimodal Scaling Law, the first cross-family framework that predicts VLM benchmark accuracy from directly observable textual capability.