Unverified50% confidenceBenchmarkExact time
In 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.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/14/2026
First Seen
Valid until: 1/12/2027
Sources
Related Entities
Related Claims
UnverifiedLoopWAM achieves an overall success rate of 49.5% on RoboCasa365.69% similarUnverifiedIn the temperature control task, the learned policy improved from -304 to -35.8, demonstrating a significant advantage.67% similarUnverifiedOn the NL2RepoBench benchmark, QwenGyre raised the score from 52.5% to 58.5% in 48 steps, and end-to-end training time was shortened by about 44% compared with the Async scheme.67% similarUnverifiedAfter full pretraining, NCP-ArchPreview outperforms OLMo-3-7B by 2.45 points on the macro-average score across downstream tasks.66% similarUnverified3,189 successful rollouts were collected from Qwen3.8-27B for supervised fine-tuning (imitation learning), and performance stagnated at 47.5%, below the results of two rounds of RL training.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1026781API
curl https://kongchang.com/api/v1/knowledge/claims/1026781MCP
get_claim(id=1026781)