3 papers
cs.GT2026
Beyond Self-Resolution: Settlement Factorization for Robust Natural Language Mechanism
Nicolas Della Penna
Language models increasingly mediate paid advice: agents submit open-ended forecasts, recommendations, plans, and evidence; a principal acts on the reports; and the mechanism later…
stat.ML2026
What Do We Care About in Bandits with Noncompliance? BRACE: Bandits with Recommendations, Abstention, and Certified Effects
Nicolás Della Penna
Bandits with noncompliance separate the learner's recommendation from the treatment actually delivered, so the learning target itself must be chosen. A platform may care about reco…
cs.GT2024
Natural Language Mechanisms via Self-Resolution with Foundation Models
Nicolas Della Penna
Practical mechanisms often limit agent reports to constrained formats like trades or orderings, potentially limiting the information agents can express. We propose a novel class of…