14 papers
Sound Probabilistic Safety Bounds for Large Language Models
Mahdi Nazeri, Anne-Kathrin Schmuck, Sadegh Soudjani +1
We propose a novel framework for computing rigorous bounds on the probability that a large language model (LLM) generates harmful output to a given prompt. We study a new applicati…
Context-Triggered Robust MPC for Temporal Logic Specifications
Arash Bahari Kordabad, Satya Prakash Nayak, Sadegh Soudjani +1
We consider the problem of synthesizing robust feedback controllers for discrete-time linear systems that ensure the satisfaction of context-dependent linear temporal logic specifi…
Doubly Fair Parity Games
Daniel Hausmann, Nir Piterman, Irmak SaÄlam +1
We consider two-player games over finite graphs in which both players are restricted by fairness constraints on their moves. Given a two player game graph and a set of fa…
MANTRA: Synthesizing SMT-Validated Compliance Benchmarks for Tool-Using LLM Agents
Ashwani Anand, Ivi Chatzi, Ritam Raha +1
Tool-using large language model (LLM) agents are increasingly deployed in settings where their reliable behavior is governed by strict procedural manuals. Ensuring that such agents…
Incremental Data-Driven Policy Synthesis via Game Abstractions
Irmak SaÄlam, Mahdi Nazeri, Alessandro Abate +2
We address the synthesis of control policies for unknown discrete-time stochastic dynamical systems to satisfy temporal logic objectives. We present a data-driven, abstraction-base…
Context-Triggered Contingency Games for Strategic Multi-Agent Interaction
Kilian Schweppe, Anne-Kathrin Schmuck
We address the challenge of reliable and efficient interaction in autonomous multi-agent systems, where agents must balance long-term strategic objectives with short-term dynamic a…