geis-a-generation-evaluation-improvement-loop-of-agent-skills-for-long-form-article-generation-af58cd98·1 events·first seen Aliases: GEIS: A Generation-Evaluation-Improvement Loop of Agent Skills for Long-Form Article Generation
Researchers introduce GEIS, a framework that decomposes long-form Wikipedia-style article generation into named, declarative agent skills organized in a generation-evaluation-improvement loop. Implemented in the Tasi Harness, GEIS outperforms STORM on structural and content quality dimensions and improves over the default writer by 8.0 points on a 100-point rubric across 20 Wikipedia Featured Article topics. A key contribution is the improvement skill, which maps recurrent evaluation findings into permanent patches to the writing skill, enabling iterative self-refinement without rewriting fixed pipelines.