arXiv Game AI· Jingwei Song·· 2026-10-10PickAI score49
MC-EvoBench: Auditing experience-driven self-improvement in Minecraft agents with 19 evolution chains
MC-EvoBench: Auditing Experience-Driven Self-Improvement in Minecraft Agents
AI summary
The paper builds a controlled Minecraft benchmark, MC-EvoBench, which audits experience-driven self-improvement in agents using 19 registered evolution chains (12 main evaluation chains and 7 calibration or probe chains). It requires the target world to be reset and allows only declared agent artifacts to cross the source-target boundary.
Why it matters
The paper uses paired probes to separate capability changes from leftover resources and uneven source exposure, making it a useful reference design for controlled evaluation of self-improving agents.
Source: arXiv Game AI · arxiv.org