6 papers
Only What You've Signed up For: Secure Workflows with Constrained Diffusion Agents
Michael Cardei, Anjun Hu, Chenrui Ma +4
As agentic AI systems take on increasingly complex and consequential tasks, securing them against prompt injection becomes critical. Existing defenses often rely on detecting or re…
Training-Free Diffusion Planning with Analytical Local Scores
Michael Y. Fatemi, Jinhao Liang, Ferdinando Fioretto
Path finding and multi-robot motion planning require trajectories that are smooth, goal-directed, and collision-free in environments with complex geometric constraints. Recent diff…
SEABench: Benchmarking Endogenous Misalignment In Self-Evolving Agents
Saswat Das, Parvati Viswanathan, Daniel Donnelly +3
Self-evolving LLM agents have gained prominence for their ability to improve after deployment by modifying their harness, including their controller instructions, memory management…
Simulation-Informed Diffusion for Decentralized Multi-robot Motion Planning
Jinhao Liang, Sven Koenig, Ferdinando Fioretto
Decentralized multi-robot motion planning requires each robot to generate collision-free trajectories from local observations, without global sensing or reliable communication. How…
Colosseum: Auditing Collusion in Cooperative Multi-Agent Systems
Mason Nakamura, Abhinav Kumar, Saswat Das +5
Multi-agent systems, where LLM agents communicate through free-form language, enable sophisticated coordination for solving complex cooperative tasks. This surfaces a unique safety…
NeuroFilter: Activation-Based Guardrails for Privacy-Conscious LLM Agents
Saswat Das, Ferdinando Fioretto
Agentic Large Language Models (LLMs) are models able to reason, plan, and execute tools over unstructured data. These abilities enable transformative applications in domains spanni…