Related papers: Policy-Invisible Violations in LLM-Based Agents

When an omnimodal large language model accepts a question whose textual premise contradicts what it actually sees or hears, does the failure lie in perception or in action? Recent omnimodal models are positioned as perception-grounded…

Many computer systems are now being redesigned to incorporate LLM-powered agents, enabling natural language input and more flexible operations. This paper focuses on handling database transactions created by large language models (LLMs).…

Large language models (LLMs) remain vulnerable to jailbreak prompts that are fluent and semantically coherent, and therefore difficult to detect with standard heuristics. A particularly challenging failure mode occurs when an attacker tries…

Large language models are increasingly deployed as specialized agents that plan, call tools, and take actions over extended horizons. Yet many existing evaluations assume a "clean interface" where dynamics are specified and stable, tools…

LLM agents process trusted instructions, retrieved records, and tool observations through a common generative channel. This conflates data flow with authority: an untrusted string can affect a secret-bearing response or an action proposal…

We investigate strategic deception in large language models using two complementary testbeds: Secret Agenda (across 38 models) and Insider Trading compliance (via SAE architectures). Secret Agenda reliably induced lying when deception…

Mitigating elderly loneliness requires policy interventions that achieve both adaptability and auditability. Existing methods struggle to reconcile these objectives: traditional agent-based models suffer from static rigidity, while direct…

Enterprises need access decisions that satisfy least privilege, comply with regulations, and remain auditable. We present a policy aware controller that uses a large language model (LLM) to interpret natural language requests against…

As large language models (LLMs) are increasingly deployed as agents, their integration into interactive environments and tool use introduce new safety challenges beyond those associated with the models themselves. However, the absence of…

Frontier LLMs now perform strongly across a wide range of physics evaluations, but it is hard to disentangle genuine reasoning from recall of established science. We introduce DiscoverPhysics, an interactive benchmark that asks a LLM agent…

As language models (LMs) are widely utilized in personalized communication scenarios (e.g., sending emails, writing social media posts) and endowed with a certain level of agency, ensuring they act in accordance with the contextual privacy…

Stateful tool-using LLM agents treat the context window as working memory, yet today's agent harnesses manage residency and durability as best-effort, causing recurring failures: lost state after compaction, bypassed flushes on reset, and…

We read twelve well-known LLM agent benchmark papers and recorded, dimension by dimension, what each paper actually says about how its evaluation was run. The motivation came from a familiar frustration: two papers will report results on…

Detecting anomalies in business processes is crucial for ensuring operational success. While many existing methods rely on statistical frequency to detect anomalies, it's important to note that infrequent behavior doesn't necessarily imply…

Recent LLM-based data agents aim to automate data science tasks ranging from data analysis to deep learning. However, the open-ended nature of real-world data science problems, which often span multiple taxonomies and lack standard answers,…

As agentic network management gains popularity, there is a critical need for evaluation frameworks that transcend static, one-shot testing. To address this, we introduce NetAgentBench, a dynamic benchmark that evaluates agent interactions…

Scalable AI agents training relies on interactive environments that faithfully simulate the consequences of agent actions. Manually crafted environments are expensive to build, brittle to extend, and fundamentally limited in diversity. A…

We stress-tested 16 leading models from multiple developers in hypothetical corporate environments to identify potentially risky agentic behaviors before they cause real harm. In the scenarios, we allowed models to autonomously send emails…

Large Language Model (LLM) agents are increasingly improved through interaction, yet most self-evolution methods adapt either the policy or the learning environment in isolation. We identify this structural gap as \emph{Agent-Environment…

Task success can hide process anomalies in real-world agent executions. An agent may pass the final task oracle while still accumulating unresolved ambiguity, unsafe external writes, ignored errors, weakly grounded commitments, or…