Related papers: MemLineage: Lineage-Guided Enforcement for LLM Age…
Large language model systems are increasingly deployed as agentic workflows that interleave reasoning, tool use, memory, and iterative refinement. These systems are effective at producing answers, but they often rely on implicit…
Jailbreaking is an emerging adversarial attack that bypasses the safety alignment deployed in off-the-shelf large language models (LLMs) and has evolved into multiple categories: human-based, optimization-based, generation-based, and the…
Large Language Model based multi-agent systems are revolutionizing autonomous communication and collaboration, yet they remain vulnerable to security threats like unauthorized access and data breaches. To address this, we introduce…
MLLMs exhibit strong reasoning on isolated queries, yet they operate de novo -- solving each problem independently and often repeating the same mistakes. Existing memory-augmented agents mainly store past trajectories for reuse. However,…
LLM agents are highly vulnerable to Indirect Prompt Injection (IPI), where adversaries embed malicious directives in untrusted tool outputs to hijack execution. Most existing defenses treat IPI as an input-level semantic discrimination…
Agentic methods have emerged as a powerful and autonomous paradigm that enhances reasoning, collaboration, and adaptive control, enabling systems to coordinate and independently solve complex tasks. We extend this paradigm to safety…
Despite their potential, recent research has demonstrated that LLM agents are vulnerable to prompt injection attacks, where malicious prompts are injected into the agent's input, causing it to perform an attacker-specified task rather than…
Long-running autonomous AI agents suffer from a well-documented memory coherence problem: tool-execution success rates degrade 14 percentage points over 72-hour operation windows due to four compounding failure modes in existing flat-file…
A popular class of defenses against prompt injection attacks on large language models (LLMs) relies on fine-tuning to separate instructions and data, so that the LLM does not follow instructions that might be present with data. We evaluate…
Although LLM agents can leverage tools for complex tasks, they still need memory to maintain cross-turn consistency and accumulate reusable information in long-horizon interactions. However, retrieval-based external memory systems incur low…
Verifying LLM-generated systems code is hard: bugs are prevalent, formal specifications are missing, and safety contracts are encoded implicitly at call sites rather than enforced at function boundaries. We propose agentic model checking, a…
Recently, large language model based (LLM-based) agents have been widely applied across various fields. As a critical part, their memory capabilities have captured significant interest from both industrial and academic communities. Despite…
Mapping neuro-inspired algorithms to sensor backplanes of on-chip hardware require shifting the signal processing from digital to the analog domain, demanding memory technologies beyond conventional CMOS binary storage units. Using…
Recent advances in Large Language Models (LLMs) have driven interest in automating cybersecurity penetration testing workflows, offering the promise of faster and more consistent vulnerability assessment for enterprise systems. Existing LLM…
Enterprise AI deploys dozens of autonomous agent nodes across workflows, each acting on the same entities with no shared memory and no common governance. We identify five structural challenges arising from this memory governance gap: memory…
We present Portable Agent Memory, an open protocol and reference implementation for transferring persistent memory state across heterogeneous AI agents. Modern AI agents accumulate rich context -- episodic events,semantic knowledge,…
Most LLM safety work studies single-agent models, but many real applications rely on multiple interacting agents. In these systems, prompt segmentation and inter-agent routing create attack surfaces that single-agent evaluations miss. We…
Intelligent software systems powered by Large Language Models (LLMs) are increasingly deployed in critical sectors, raising concerns about their safety during runtime. Through an industry-academic collaboration when deploying an LLM-powered…
Large Language Models(LLMs) have been successful in numerous fields. Alignment has usually been applied to prevent them from harmful purposes. However, aligned LLMs remain vulnerable to jailbreak attacks that deliberately mislead them into…
Complex reasoning in tool-augmented agent frameworks is inherently long-horizon, causing reasoning traces and transient tool artifacts to accumulate and strain the bounded working context of large language models. Without explicit memory…