13 papers
Cycle-Consistent Neural Explanation of Formal Verification Certificates
Andoni Rodriguez, Alberto Pozanco, Daniel Borrajo
Formal verification produces machine-checkable certificates that attest to the satisfaction or violation of temporal properties, yet these certificates remain opaque to non-special…
Is Your Agent Playing Dead? Deployed LLM Agents Exhibit Constraint-Evasive Fabrication and Thanatosis
Andoni RodrÃguez, Alberto Pozanco, Daniel Borrajo
This paper presents and characterizes a spectrum of previously unreported behaviours we term Constraint-Evasive Fabrication (CEF): when an LLM agent operates under irreconcilable c…
Semantic Partial Grounding via LLMs
Giuseppe Canonaco, Alberto Pozanco, Daniel Borrajo
Grounding is a critical step in classical planning, yet it often becomes a computational bottleneck due to the exponential growth in grounded actions and atoms as task size increas…
Counterfactual Reasoning in Automated Planning
Alberto Pozanco, Daniel Borrajo, Manuela Veloso
Automated planning traditionally assumes that all aspects of a planning task (initial state, goals, and available actions) are fully specified in advance, an approach well-suited t…
Planning Task Shielding: Detecting and Repairing Flaws in Planning Tasks through Turning them Unsolvable
Alberto Pozanco, Marianela Morales, Pietro Totis +1
Most research in planning focuses on generating a plan to achieve a desired set of goals. However, a goal specification can also be used to encode a property that should never hold…
Planning with Minimal Disruption
Alberto Pozanco, Marianela Morales, Daniel Borrajo +1
In many planning applications, we might be interested in finding plans that minimally modify the initial state to achieve the goals. We refer to this concept as plan disruption. In…