Unverified50% confidenceFactExact time
In real-world tests covering twelve tasks and three robot instances, the AMP1 agent succeeded zero-shot in 104 of 108 trials.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
11/9/2026
First Seen
Valid until: 11/23/2026
Sources
Related Entities
Related Claims
UnverifiedPilot experiments had three coding agents and eight models each run eight 20-minute single-pass tasks, with label-aware F1 showing extremely high variance ranging from 0.143 to 0.892.74% similarUnverifiedThe developer ran 1932 test runs, using 100 realistic tools (including deliberately confusable tools such as pdf_compress, pdf_optimize, image_compress), with tool counts in 8 tiers from 5 to 100, running each condition twice, testing 18 tasks (including 10 ambiguous tasks).71% similarUnverifiedThe developer trained a single policy from scratch in MuJoCo to solve the 2D ragdoll getting-up task, and in 160 tests it succeeded in getting up 0 times.71% similarUnverifiedIn the survival game Arena experiment, approximately 100 agents working in parallel completed the task in about 20 minutes, whereas sequential execution would have taken several hours.68% similarUnverifiedIn ThinkingBox, each task is executed independently 20 times, each starting from a clean backend initial state, requiring each model to run 10,140 trials.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1150463API
curl https://kongchang.com/api/v1/knowledge/claims/1150463MCP
get_claim(id=1150463)