Unverified50% confidenceFactExact time
Agentic retrieval is the variant actually adopted by current coding agents: there is no embedding index, the agent repeatedly runs grep, opens files and reads until it can answer, and the retriever is the model itself with shell tools.
1
Sources
50%
Confidence
Long-term
Relevance
10/14/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedAgent Retrieval Bench is an evaluation benchmark targeting the accuracy of the code retrieval stage in programming agents.78% similarUnverifiedThe Agent's scripts component uses predefined script files to enable the Agent to execute code, read and write the file system, access databases, and call third-party APIs.74% similarUnverifiedAgent Activity uses an architecture that reads existing files passively rather than intercepting via plugins or APIs, resulting in near-zero-configuration integration and no need for network permissions.73% similarUnverified在AI Agent语境下，hook切入点通常对应Agent执行的工具调用（Tool Call），如bash命令、文件读取、搜索等操作73% similarUnverifiedAn agentic loop enables the model to list file directories, read file contents, and determine the next action based on the information, which is the dividing line between an agent and an ordinary chatbot.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1032434API
curl https://kongchang.com/api/v1/knowledge/claims/1032434MCP
get_claim(id=1032434)