Unverified50% confidenceFactExact time
The supervisor is a state machine that runs in DUNGEON mode most of the time with decisions made by the reinforcement learning model, and switches to PATHFIND mode after the step budget is exhausted or enough monsters are killed, using BFS to pathfind to the most recently seen stairs.
1
Sources
50%
Confidence
Long-term
Relevance
10/16/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe run supervisor is responsible for handling timeouts, retry policies, replanning after failures, budget control, and structured tracing.76% similarUnverifiedStateful tool agents maintain persistent state across multi-turn interactions, with each tool call result written into the execution trajectory and influencing subsequent decisions, giving their errors a cascading effect.72% similarUnverified后台任务机制的核心设计是通知队列：后台管理器用守护线程跑慢命令，结果放进通知队列，每次调用大模型之前排空队列将结果喂给模型71% similarUnverified外层循环与控制理论中的闭环控制系统高度同构，通过可观测性采集状态、评估器比较偏差、执行机构输出纠正动作70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1048194API
curl https://kongchang.com/api/v1/knowledge/claims/1048194MCP
get_claim(id=1048194)