Unverified50% confidenceFactExact time
SWE-RPG是在SWE-bench基础上发展而来的新一代AI编程能力评估框架，引入了角色扮演机制模拟不同经验水平开发者的需求提交方式
1
Sources
50%
Confidence
Long-term
Relevance
8/24/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe core design philosophy of AI programming tools such as Devin, OpenHands, and SWE-Agent is based on the ReAct (Reasoning + Acting) paradigm.75% similarUnverifiedThe "Niuma Project Builder" AI website-building Agent adopts a four-layer modular prompt architecture, comprising a base Coding Assistant rules layer, an AnimeJS animation planning layer, a design style reference Agent layer, and an on-demand extension module layer.72% similarVerifiedThe core design philosophy of SWE-agent is to optimize the interaction between large language models and code repositories through the Agent-Computer Interface (ACI)70% similarVerifiedAn Agent is an application-layer architecture built on top of an LLM that enables the model to decompose complex tasks, invoke external tools, maintain context state, and iteratively optimize results by introducing mechanisms such as Planning, Memory, Tool Use, and Reflection.69% similarUnverifiedRAG (Retrieval-Augmented Generation) is one of the core concepts that needs to be mastered during the foundational theory stage of AI Agent development.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/795354API
curl https://kongchang.com/api/v1/knowledge/claims/795354MCP
get_claim(id=795354)