Verified75% confidenceFactTime unknown
LATS (Language Agent Tree Search) is a tree-search-based Agent decision-making method suited for complex scenarios that require exploring multiple possible paths.
5
Sources
75%
Confidence
Long-term
Relevance
6/1/2026
First Seen
Sources
AI-Assistant开源项目解析：用Anthropic API打造本地AI Agent
githubJosephcc2
Related Entities
Related Claims
UnverifiedAgentic Search 是赋予大模型工具调用能力，让模型自主决策何时搜索、搜什么以及是否充分74% similarUnverifiedEGCForest's three-forest architecture enables the Agent to distinguish the temporal thread, speaker conditions, and deliverable status of information during retrieval.66% similarUnverifiedPro Search的多步骤推理本质上是一种Agent工作流，将复杂问题分解为多个子问题依次进行搜索和推理66% similarUnverifiedA parallel web search Agent can initiate multiple retrieval tasks simultaneously, rather than executing them serially one by one.65% similarUnverifiedThe intelligence of the search experience—understanding intent, multi-step retrieval, result synthesis—mainly happens at the model and orchestration layers, not at the protocol layer.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/29226API
curl https://kongchang.com/api/v1/knowledge/claims/29226MCP
get_claim(id=29226)