This paper proposes a two-stage training framework to pretrain action modules with motion priors before Vision-Language-Action (VLA) alignment, improving VLA performance and reducing optimization chal…

MyoSem introduces an EMG-action semantic alignment framework that transforms low-level muscle signals into a shared semantic space, enabling bidirectional retrieval between EMG data and natural langua…

The paper introduces FabriVLA, a lightweight Vision-Language-Action model that achieves strong performance on the Meta-World MT50 benchmark using a compact 1B scale VLM backbone and a flow-matching ac…

The paper proposes Proof-Carrying Agent Actions (PCAA), a runtime-neutral governance model that uses action certificates to consistently track and authorize high-risk actions across diverse and hetero…

ETAS is a programming language for agent systems that separates deterministic computation from agentic nondeterminism and provides a foundation for reasoning about authorization, nondeterminism, recov…

The paper identifies a 'deployment-safety gap' in Vision-Language-Action (VLA) policies, showing that identical model checkpoints can result in physically different and unsafe robot actions due to act…

The paper develops a unified, cross-layer security framework for autonomous LLM agents operating in agentic commerce, identifying key attack vectors and proposing a layered defense architecture.

SIRI introduces a self-internalizing reinforcement learning framework that allows LLM agents to autonomously discover and integrate reusable skills directly into their core policy, significantly impro…

AIRGuard is a runtime authority control guard that operationalizes least privilege to prevent language agents from executing unauthorized side effects, significantly reducing attack success rates on a…

AIRGuard is a runtime authority control guard that operationalizes least privilege to prevent agent attacks by enforcing step-level authorization over external side effects.

The paper introduces AgentDoG 1.5, a lightweight and scalable alignment framework that significantly improves AI agent safety and security for complex open-world agent deployments.

The paper introduces AgentDoG 1.5, a lightweight and scalable alignment framework that significantly improves AI agent safety and security for complex, open-world agentic scenarios.

The paper analyzes the escalating security and safety threats posed by generative AI systems as they transition from merely generating content to executing real-world actions via tools and agents, fin…

The paper introduces MATRA, a systematic threat modeling framework, to assess how known LLM threats translate into concrete, deployment-specific risks within autonomous agentic AI systems.

This paper introduces SAFE, a new framework for multi-agent reinforce learning with continuous action spaces using a counterfactual baseline conditioned on a self-evolving default action.

This paper introduces Agentic Workflow Injection (AWI), a new class of vulnerability in LLM-powered GitHub Actions, and presents TaintAWI, a novel taint-analysis tool that identifies hundreds of explo…

This paper introduces BadWAM, a framework for modeling and evaluating World-Action Drift Attacks, a new class of adversarial attacks that break the alignment between a World-Action Model's (WAM's) ima…

The paper demonstrates that jointly training a single lightweight neural reranker on multiple diverse environments significantly improves action selection performance and achieves positive cross-domai…