Unverified50% confidenceEventExact time
The 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).
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/14/2026
First Seen
Valid until: 1/12/2027
Sources
Related Entities
Related Claims
UnverifiedThe developer ran 20 batches of 200 trials each, totaling 4,000 attempts, each with a different random seed, and selected the best candidates by KL divergence.73% similarUnverifiedPilot 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 0.892.71% similarUnverifiedA long-horizon programming agent built an entire Minecraft clone almost entirely from scratch through code, comprising approximately 100,000 lines of game code, 26,000 lines of test code, 1,000 automated tests, and 775 files, with a cumulative working time of approximately 25 hours.68% similarUnverifiedThe ThinkingBox benchmark, released by Microsoft researchers and Hugging Face, contains 507 real business process tasks, with each task run 20 times.68% similarUnverified创建新Skill时应准备10-20条测试提示，包括5条快乐路径场景和5条该不用的场景68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1031411API
curl https://kongchang.com/api/v1/knowledge/claims/1031411MCP
get_claim(id=1031411)