SAGE: A Statistical Acceptance Gate for Self-Evolving Agents

arXiv:2609.36043 · cs.AI · Submitted 2026-09-28 · Read on arXiv

cs.AI

Submitted: 2026-09-28

Updated: 2026-09-28

Terminology

• Self-Evolving Agents — 1× in this paper · explained in 2 episodes

Sources

• Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills
• SkillOpt: Executive Strategy for Self-Evolving Agent Skills
• SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine
• OfficeQA Pro: An Enterprise Benchmark for End-to-End Grounded Reasoning
• LiveMathematicianBench: A Live Benchmark for Research-Level Mathematical Reasoning with Proof Sketches

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems