Unverified50% confidenceFactExact time
The research team constructed a new evaluation set, MegaRCA-Mix, containing 50 manually annotated failure cases covering long-horizon, execution-intensive tasks.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/15/2026
First Seen
Valid until: 12/14/2026
Sources
Related Entities
Related Claims
UnverifiedThe test initiators explicitly stated that they value failure cases the most, and hope the community will provide feedback on which information is ambiguous, what hinders tool selection, and what information agents looked for but could not find.68% similarUnverifiedThe research team selected 8 models spanning different capability tiers and conducted cross-evaluations across 54 benchmarks66% similarUnverifiedThe orchestration layer contains four key components: task decomposition, model routing, result fusion, and quality verification.66% similarUnverifiedThe research tested 7 skills and 4 victim models.65% similarUnverifiedThe usage data of 175,000 scientists comes from the project team's own claims, and the scientific rigor and acceptance of results in peer review still need to be verified.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/921738API
curl https://kongchang.com/api/v1/knowledge/claims/921738MCP
get_claim(id=921738)