When Better Gets Worse: Improvement Fidelity for Self-Improving Agents in Adaptive Worlds

arXiv:2609.32677 · cs.AI, cs.LG, cs.MA · Submitted 2026-09-26 · Read on arXiv

cs.AI, cs.LG, cs.MA

Submitted: 2026-09-26

Updated: 2026-09-26

Code: https://github.com/computational-decision-lab/pivot

Terminology

• Fidelity — 37× in this paper · explained in 2 episodes
• Actor — 26× in this paper · explained in 3 episodes
• Calibration — 16× in this paper · explained in 7 episodes
• Verifier — 15× in this paper · explained in 2 episodes
• Regret — 14× in this paper · explained in 3 episodes
• Reinforcement Learning — 8× in this paper · explained in 4 episodes
• Adaptation — 7× in this paper · explained in 1 episode
• Accuracy — 6× in this paper · explained in 1 episode
• Verification — 3× in this paper · explained in 2 episodes
• Adaptive Selection — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Bayesian Optimization — 1× in this paper · explained in 3 episodes
• Benchmark — 1× in this paper · explained in 2 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• Improvement Differential Error — 1× in this paper
• Reward Hacking — 1× in this paper · explained in 8 episodes
• Scaling Laws — 1× in this paper · explained in 4 episodes
• World Model — 1× in this paper · explained in 7 episodes

Sources

• Theoretical Foundations and Effective Algorithms for Policy-Aware Simulator Learning
• Self-Authored Verification Is Unreliable in Heuristic Self-Improving Agents
• Doubly Robust Off-policy Value Evaluation for Reinforcement Learning
• OpenSpiel: A Framework for Reinforcement Learning in Games
• Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
• Multi-agent Performative Prediction: From Global Stability and Optimality to Chaos
• EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments
• Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents

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
• 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
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection