Unverified50% confidenceFactExact time
XiangqiBench is an executable benchmark using Chinese chess as its vehicle, published on arXiv, and argues that agent evaluation should measure closed-loop outcomes and report both coverage and reliability.
1
Sources
50%
Confidence
Long-term
Relevance
10/5/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedEvaluation methodologies that emphasize closed-loop, adversarial, and reproducibility properties—such as XiangqiBench—are likely to become an important direction for the next stage of agent evaluation frameworks.77% similarUnverifiedAgent evaluation benchmark suites include GAIA, AgentBench, and SWE-bench.64% similarUnverifiedGuardrails should be established for AI-generated output through static analysis, security scanning, and comprehensive test coverage.62% similarUnverified端到端测试位于测试金字塔的顶层，验证整条业务链路的完整性，与单元测试和集成测试形成互补分工60% similarUnverifiedGraphEcho is a benchmark proposed in a paper on arXiv that tests whether graph agents mistakenly treat repeatedly encountered information as additional corroboration.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/975454API
curl https://kongchang.com/api/v1/knowledge/claims/975454MCP
get_claim(id=975454)