Unverified50% confidenceBenchmarkExact time
In tests on four manipulation task families, CoDA raised the out-of-distribution (OOD) success rate from 5.3% after supervised fine-tuning to 27.6%, exceeding the strongest closed-loop baseline by 9.5 percentage points under the same generation budget.
1
Sources
50%
Confidence
Long-term
Relevance
10/16/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedOn the LIBERO-Pro benchmark, after 15 rounds of generation and training, CoDA raised the success rate under position perturbation from 25% to 84%, and under instruction perturbation from 1% to 76%.72% similarUnverifiedIn code review tests, Opus 5.5 improved recall on more difficult pull requests from a baseline of 54% to nearly 77%, but the number of comments increased by approximately 20%.70% similarUnverifiedIn a test simulating real Cursor coding, the score improved from 34.1% to 55.5%.69% similarUnverifiedWhen the coding agent no longer generates its own tests, the task success rate improves, overall speed increases by approximately 6%, and costs decrease by approximately 9%.68% similarUnverifiedOn the cluster panel, replacing the model's structured decision-making with code (based on the same extracted facts) improved family accuracy by an average of 20.5 percentage points, with Llama 3.1 8B rising from 1% under self-judgment to 56% under code adjudication.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1041797API
curl https://kongchang.com/api/v1/knowledge/claims/1041797MCP
get_claim(id=1041797)