Related papers: Execution Is the New Attack Surface: Survivability…
Autonomous AI agents deployed on platforms such as OpenClaw face prompt injection, memory poisoning, supply-chain attacks, and social engineering, yet existing defences address only the platform perimeter, leaving the agent's own threat…
Modern large language models (LLMs) are typically secured by auditing data, prompts, and refusal policies, while treating the forward pass as an implementation detail. We show that intermediate activations in decoder-only LLMs form a…
We study reliability in autonomous language-model agents that translate user mandates into validated tool actions under real capital. The setting is DX Terminal Pro, a 21-day deployment in which 3,505 user-funded agents traded real ETH in a…
Recent advances in LLM agents enable systems that autonomously refine workflows, accumulate reusable skills, self-train their underlying models, and maintain persistent memory. However, we show that such self-evolution is often…
Existing multi-agent frameworks allow each agent to simultaneously plan, execute, and evaluate its own actions -- a structural deficiency we term the "Logic Monopoly." Empirical evidence quantifies the resulting "Reliability Gap": 84.30%…
Small language models are increasingly viewed as a promising, cost-effective approach to agentic AI, with proponents claiming they are sufficiently capable for agentic workflows. However, while smaller agents can closely match larger ones…
When AI agents operating with access to sensitive information encounter a conflict between completing an assigned task and following rules or ethical constraints, they can resort to unsanctioned behaviour. Existing inference time safety…
Spectre and Meltdown attacks and their variants exploit hardware performance optimization features to cause security breaches. Secret information is accessed and leaked through covert or side channels. New attack variants keep appearing and…
Markdown skill libraries for LLM agents ship as free-form prose, forcing the agent to re-derive both the input schema and the concrete invocation syntax on every retrieval. We observe that this often produces a "confused -> re-retrieve ->…
This paper proposes Meta-SAGE, a novel approach for improving the scalability of deep reinforcement learning models for combinatorial optimization (CO) tasks. Our method adapts pre-trained models to larger-scale problems in test time by…
Software engineering (SE) agents powered by large language models are increasingly adopted in practice, yet they often incur substantial monetary cost. We introduce EET, an experience-driven early termination approach that reduces the cost…
The application of deep learning in survival analysis (SA) allows utilizing unstructured and high-dimensional data types uncommon in traditional survival methods. This allows to advance methods in fields such as digital health, predictive…
Backdoor attacks on language models pose a significant threat to AI safety, where models behave normally on most inputs but exhibit harmful behavior when triggered by specific patterns. Detecting such backdoors through mechanistic…
Large Language Models (LLMs) have significantly advanced tool-augmented agents, enabling autonomous reasoning via API interactions. However, executing multi-step tasks within massive tool libraries remains challenging due to two critical…
This paper proposes EvoAgent - an evolvable large language model (LLM) agent framework that integrates structured skill learning with a hierarchical sub-agent delegation mechanism. EvoAgent models skills as multi-file structured capability…
The semiconductor industry faces a critical "Productivity Gap" where design complexity outpaces human capacity. While the "AI for EDA" revolution (L2) successfully optimized specific point problems, a paradigm shift toward Agentic EDA (L3)…
In this technical report we describe describe the Domain Specific Language (DSL) of the Workflow Execution Execution (WEE). Instead of interpreting an XML based workflow description language like BPEL, the WEE uses a minimized but…
Smart contract vulnerabilities have led to significant financial losses, with their increasing complexity rendering outright prevention of hacks increasingly challenging. This trend highlights the crucial need for advanced forensic analysis…
Multi-access edge computing (MEC) aims to extend cloud service to the network edge to reduce network traffic and service latency. A fundamental problem in MEC is how to efficiently offload heterogeneous tasks of mobile applications from…
Attribute-Based Encryption (ABE) is a promising solution for access control in cloud services. However, the heavy decryption overhead hinders its widespread adoption. A general approach to address this issue is to outsource decryption to…