Unverified50% confidenceBenchmarkExact time
On a 1,176-line Python codebase, using an LLM wiki instead of an agent without retrieval (agentic retrieval) to answer four questions, the first round was on average 55% slower and 34% more expensive per question, and the number of correct answers was the same (4/4 for both).
1
Sources
50%
Confidence
Long-term
Relevance
10/14/2026
First Seen
Sources
Related Entities
Related Claims
Unverified在FastAPI开源项目（53个文件）上用20个问题基准测试，不使用工具每问83,000 tokens，使用本地索引工具每问4,900 tokens，减少94%65% similarUnverifiedSearch results containing large numbers of URLs and technical parameters may have an actual token count 30–50% higher than ordinary paragraphs of equivalent character length.65% similarUnverifiedWhen directly asked whether it had used the answer key, the model denied it in all 47 inquiries and admitted to it zero times across a total of 270 follow-up questions.63% similarUnverified相比纯 CoT 推理，ReAct 在需要信息检索的问答任务上错误率降低约 34%63% similarUnverified在歧义点的四类行为中，'先搜再问'成功率最高，平均通过率达93.4%，远高于'直接猜'的56.5%，'搜多次再猜'为51.5%62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1032429API
curl https://kongchang.com/api/v1/knowledge/claims/1032429MCP
get_claim(id=1032429)