Related papers: SABER: Small Actions, Big Errors -- Safeguarding M…

LLM agents achieve 85-96% success on tasks where instructions fully specify the action, but drop to 29-53% when action feasibility depends on environmental state that the instruction does not mention. We argue that this gap reflects a…

LLM-based agents execute real-world workflows via tools and memory. These affordances enable ill-intended adversaries to also use these agents to carry out complex misuse scenarios. Existing agent misuse benchmarks largely test…

Large Language Models are increasingly proposed as cognitive components for robotic systems, yet their opaque decision processes make it difficult to explain success or failure in closed-loop embodied tasks. Following an empirical AI…

Current methods for content safety in Large Language Models (LLMs), such as Supervised Fine-Tuning (SFT) and Reinforcement Learning from Human Feedback (RLHF), often rely on multi-stage training pipelines and lack fine-grained,…

Agentic systems for business process automation often require compliance with policies governing conditional updates to the system state. Evaluation of policy adherence in LLM-based agentic workflows is typically performed by comparing the…

Large Language Model (LLM) agents have shown strong results on multi-turn tool-use tasks, yet they operate in isolation during training, failing to leverage experiences accumulated across episodes. Existing experience-augmented methods…

Scaffolding Large Language Models (LLMs) into multi-agent systems often improves performance on complex tasks, but the safety impact of such scaffolds has not been thoroughly explored. We introduce AgentBreeder, a framework for…

The acquisition of agentic capabilities has transformed LLMs from "knowledge providers" to "action executors", a trend that while expanding LLMs' capability boundaries, significantly increases their susceptibility to malicious use. Previous…

Multi-agent systems achieve state-of-the-art outcomes through peer collaboration. However, when an agent in the pipeline silently drops a constraint, the system's final output may look correct even though the reasoning chain was quietly…

Coding agents represent a new paradigm in automated software engineering, combining the reasoning capabilities of Large Language Models (LLMs) with tool-augmented interaction loops. However, coding agents still have severe limitations.…

Solving complex or long-horizon problems often requires large language models (LLMs) to use external tools and operate over a significantly longer context window. New LLMs enable longer context windows and support tool calling capabilities.…

Multi-agent systems extend large language models (LLMs) by decomposing tasks among specialized agents, but their distributed decision process creates new attack surfaces. We identify semantic hijacking, an attack in which harmful requests…

LLM-powered coding agents, which operate in iterative loops (turns) to solve software engineering tasks, are becoming increasingly powerful. However, their practical deployment is hindered by significant and unpredictable costs. This…

With the integration of large language models (LLMs), embodied agents have strong capabilities to understand and plan complicated natural language instructions. However, a foreseeable issue is that those embodied agents can also flawlessly…

AI coding assistants powered by large language models (LLMs) have transformed software development, significantly boosting productivity. While existing benchmarks evaluate the correctness and security of LLM-generated code, they are…

Existing agent-safety evaluation has focused mainly on externally induced risks. Yet agents may still enter unsafe trajectories under benign conditions. We study this complementary but underexplored setting through the lens of…

Large Language Models (LLMs) are being increasingly used in software engineering tasks, with an increased focus on bug report resolution over the past year. However, most proposed systems fail to properly handle uncertain or incorrect…

Does continued scaling of large language models (LLMs) yield diminishing returns? In this work, we show that short-task benchmarks may give an illusion of slowing progress, as even marginal gains in single-step accuracy can compound into…

Organisations are starting to adopt LLM-based AI agents, with their deployments naturally evolving from single agents towards interconnected, multi-agent networks. Yet a collection of safe agents does not guarantee a safe collection of…

Large Language Model (LLM) agents commonly condition actions on full action-observation histories, which introduce task-irrelevant information that easily leads to redundant actions and higher inference cost. We propose Progress-Aware…