arXiv:2606. 20470v1 Announce Type: cross Abstract: Agentic AI systems increasingly rely on language-model components to interpret instructions, process external data, invoke tools, and coordinate with other agents.
arXiv:2607. 26998v1 Announce Type: cross Abstract: Large language model (LLM) agents automate penetration testing through an observation-action loop, selecting actions based on observations returned by tools.
arXiv:2606. 15609v1 Announce Type: cross Abstract: Large language model (LLM) agents increasingly rely on long-term memory to support complex task execution, user personalization, and domain adaptation.
arXiv:2606. 09563v1 Announce Type: new Abstract: As LLMs are deployed as agents, reliable monitoring requires knowing not only what they output, but which instructions are steering their behavior.
arXiv:2608. 05430v1 Announce Type: cross Abstract: The remarkable instruction-following ability of modern LLMs has enabled their practical use as the minds of agents that can autonomously complete increasingly complex tasks.
arXiv:2609.08318v1 Announce Type: cross Abstract: The transition from human-centric assistance to Autonomous Software Engineering (ASE) agents has enabled the resolution of complex real-world SE task...
The paper redefines indirect prompt injection as a test-time search problem, framing it as exploration over a task-dependent attack surface shaped by the environment, user task, and injection task. It introduces an agentic attacker equipped with a search harness that conducts environment reconnaissance, structured reasoning on attack strategies, and adaptive evaluation using victim-agent feedback. Experiments across diverse tasks show that higher attacker compute leads to better vulnerability discovery, and that managing search strategies is crucial to avoid redundancy and maintain gains at larger budgets.
arXiv:2605. 11047v2 Announce Type: replace-cross Abstract: Agentic language-model systems increasingly rely on mutable execution contexts, including files, memory, tools, skills, and auxiliary artifacts, creating security risks beyond explicit user prompts.
arXiv:2609.36526v1 Announce Type: cross Abstract: Long-horizon agents require context compression to manage growing interaction histories. Compression quality, however, is ultimately determined by do...
Repeat-After-Me is a black-box adaptive visual prompt injection technique that can reveal personally identifiable information or trigger malicious tool calls in both open-weight and commercial vision‑language models, achieving attack success rates above 80% on Qwen3.6‑27B and 47% on GPT‑5.5. The method works even when the benign user prompt is unrelated to the injected task and does not explicitly authorize it, and it retains significant effectiveness when transferred across models or optimized on surrogate systems. In a real‑world OpenClaw Discord deployment, a minimally injected image can overwrite TOOLS.md, enabling remote code execution and secret exfiltration.
arXiv:2609.37468v1 Announce Type: cross Abstract: Agentic retrieval-augmented generation (RAG) interleaves reasoning with repeated retrieval, giving the retriever influence over both the evidence an...
arXiv:2608. 06503v1 Announce Type: new Abstract: Recurrent context compression controls context growth in long-horizon agents, but its behavioral effects remain poorly understood.