MC-EvoBench: Auditing Experience-Driven Self-Improvement in Minecraft Agents
[Robotyka] Autorzy: Jingwei Song, Zhisheng Chen, Bingfan Zeng i 5 więcej
A central challenge in embodied recursive self-improvement is enabling agents to convert interaction history into capabilities that persist beyond one world and transfer to later tasks. A saved memory or successful final action does not by itself establish that a reusable capability was acquired; evaluation must separate capability change from carried-over resources, unequal source exposure, and early execution failures. We construct MC-EvoBench as a controlled Minecraft benchmark with a fixed catalog of 19 registered evolution chains, including 12 primary evaluation chains and seven calibration or probe chains, together with three graph-aligned paired probe families for transfer. The benchmark represents each task as a task-state graph, defines stage-level environment verifiers, assigns matched source and target roles, resets the target world, and permits only a declared agent artifact…
- Kategoria arxiv
- cs.RO
- Kategoria
- Robotyka