Unverified50% confidenceBenchmarkExact time
The hierarchical planner + 3 executors architecture has an end-to-end success rate of 38.2% and a spec drift failure rate of 36.1%.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/17/2026
First Seen
Valid until: 1/15/2027
Sources
Related Entities
Related Claims
UnverifiedThe simple 3-rule baseline used for comparison achieved an accuracy of only 64.4%, with Jev leading by approximately 8 percentage points.63% similarUnverifiedDevelopers ultimately selected the variant with the lowest KL divergence (0.028), resulting in a 1.83% drop on GSM8K, no change on MMLU, and an improvement in HarmBench compliance rate from 30.8% to 100%62% similarUnverifiedIn closed-loop experiments on RoboChallenge Table30-V2, after three rounds of deployment-training cycles, LoopWAM's success rate increased from 23.67% to 43.33%, an improvement of 19.7 percentage points, with a final score of 56.80.62% similarUnverifiedAcross a range of question sizes spanning 256x, the error judgment rate of a single run is almost unchanged: 0.531 at T=16 and 0.534 at T=4096.61% similarUnverifiedThe failure rate of prompt filtering schemes is about 3%.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1054835API
curl https://kongchang.com/api/v1/knowledge/claims/1054835MCP
get_claim(id=1054835)