Beichen Huang, Zhenyu Liang, Bowen Zheng, Ran Cheng
Author
Beichen Huang, Zhenyu Liang, Bowen Zheng, Ran Cheng
Date
Terms in this piece · Glossary
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
Why it matters
Offers a working alternative to session memory and context windowThe maximum amount of text a model can consider at once — its working memory for the current conversation or task.Full definition → stuffing for software work that outlives any single AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → run, with cost and test evidence attached.
articleMindForge: Teaching Small Language Models Whole-Life-Cycle Software Engineering via Source-Free Program SynthesisYihao Chen, Shi Chang, Khaled Chawa, Feng Lin, Boyuan Chen, Shaowei Wang, Ahmed E. Hassan
articleOurArkRoy Zhao (Paul G. Allen School of Computer Science & Engineering, University of Washington), Zhenyu Zhao (Independent Researcher)
articleOuroboros: A Self-Developing Frontier Coding Agent with Reviewed Core EvolutionAnton Razzhigaev, Andrei Gritsaev, Andrei Kaznacheev, Nikita Dragunov, Roman Yampolskiy, Andrei Kuznetsov