[EMNLP 2026] Aligning Agentic World Models via Knowledgeable Experience Learning
-
Updated
May 15, 2026 - Python
[EMNLP 2026] Aligning Agentic World Models via Knowledgeable Experience Learning
Evolution for the Agent Era. Inspired by Darwin, an open framework for experience-driven recursive self-improvement of AI agents.
DSH-Reforge (dsh-reforge) — DeepSeek Harness plugin for traceable experience from test-verified Python bug fixes. 从有测试依据的 Python 修复中积累可追溯经验。Experimental alpha · DSH 0.2.0-rc.2.
[arXiv] ExpHarness: Model-Agnostic Experience Learning through a Trainable Harness
Open-source memory and experience layer for persistent AI agents, with auditable decisions, evidence-based learning, and evolving identity.
To associate your repository with the experience-learning topic, visit your repo's landing page and select "manage topics."