Related papers: Evaluating Generalization Mechanisms in Autonomous…
Generalist LLM agents are often post-trained on a narrow set of environments but deployed across far broader, unseen domains. In this work, we investigate the challenge of agentic post-training when the eventual test domains are unknown.…
Large language model (LLM)-based agents struggle to generalize to novel and complex environments, such as unseen websites or new sets of functions, due to a fundamental mismatch between their pre-training and test-time conditions. This…
LLM agents are increasingly deployed in long-horizon, complex environments to solve challenging problems, but this expansion exposes them to long-horizon attacks that exploit multi-turn user-agent-environment interactions to achieve…
Agent decision making using Reinforcement Learning (RL) heavily relies on either a model or simulator of the environment (e.g., moving in an 8x8 maze with three rooms, playing Chess on an 8x8 board). Due to this dependence, small changes in…
Language Model Agents (LMAs) are emerging as a powerful primitive for augmenting red-team operations. They can support attack planning, adversary emulation, and the orchestration of multi-step activity such as lateral movement, a core…
Autonomous agent frameworks built upon large language models (LLMs) are evolving into complex, tool-integrated, and continuously operating systems, introducing security risks beyond traditional prompt-level vulnerabilities. As this paradigm…
LLM-based agents are increasingly deployed for complex tasks requiring planning, tool use, and interaction with external services. Their reliance on untrusted external content exposes them to indirect prompt injection (IPI), in which…
This work carries out a detailed transient analysis of the learning behavior of multi-agent networks, and reveals interesting results about the learning abilities of distributed strategies. Among other results, the analysis reveals how…
Despite the recent success of deep reinforcement learning (RL), domain adaptation remains an open problem. Although the generalization ability of RL agents is critical for the real-world applicability of Deep RL, zero-shot policy transfer…
Collaborative multi-agent reinforcement learning has rapidly evolved, offering state-of-the-art algorithms for real-world applications, including sensitive domains. However, a key challenge to its widespread adoption is the lack of a…
Many recent successful off-policy multi-agent reinforcement learning (MARL) algorithms for cooperative partially observable environments focus on finding factorized value functions, leading to convoluted network structures. Building on the…
As Large Language Models (LLMs) move from curated training sets into open-ended real-world environments, a fundamental limitation emerges: static training cannot keep pace with continual deployment environment change. Scaling training-time…
In the face of evolving cyber threats such as malware, ransomware and phishing, autonomous cybersecurity defense (ACD) systems have become essential for real-time threat detection and response with optional human intervention. However,…
Deep reinforcement learning (RL) policies are known to be vulnerable to adversarial perturbations to their observations, similar to adversarial examples for classifiers. However, an attacker is not usually able to directly modify another…
This paper investigates generalisation in multi-agent games, where the generality of the agent can be evaluated by playing against opponents it hasn't seen during training. We propose two new games with concealed information and complex,…
We introduce a method to address goal misgeneralization in reinforcement learning (RL), leveraging Large Language Model (LLM) feedback during training. Goal misgeneralization, a type of robustness failure in RL occurs when an agent retains…
For over a decade, cybersecurity has relied on human labor scarcity to limit attackers to high-value targets manually or generic automated attacks at scale. Building sophisticated exploits requires deep expertise and manual effort, leading…
The dynamic and evolutionary nature of service requirements in wireless networks has motivated the telecom industry to consider intelligent self-adapting Reinforcement Learning (RL) agents for controlling the growing portfolio of network…
As artificial intelligence (AI) assistants become more widely adopted in safety-critical domains, it becomes important to develop safeguards against potential failures or adversarial attacks. A key prerequisite to developing these…
Recent advances in intelligent network control have primarily relied on task-specific Artificial Intelligence (AI) models deployed separately within the Radio Access Network (RAN) and Core Network (CN). While effective for isolated models,…