{"schema_version":"newruntime-agent-readable-v0.2","type":"post","stable_id":"post:arcee-open-model-science-post-training","slug":"arcee-open-model-science-post-training","title":"Arcee Turns Scientific Post-Training Into A Run Ledger","description":"Arcee's open-model science write-up shows a 21-run post-training loop around Trinity Mini, held-out scientific environments, trace review, and a promoted specialist adapter.","retrieval_nugget":"Arcee's open-model science write-up shows a 21-run post-training loop around Trinity Mini, held-out scientific environments, trace review, and a promoted specialist adapter. #OpenModels #ScientificAI #PostTraining #AgentHarness Arcee's \"Teaching an Open Model to Do Science\" is not just a model announcement.","status":"published","published_at":"2026-08-01","updated_at":"2026-08-01","record_date":"2026-08-01","date_kind":"published_at","topics":["open-models","scientific-ai","post-training","agent-harnesses"],"source_urls":["https://www.arcee.ai/blog/teaching-an-open-model-to-do-science"],"visuals":[{"id":"arcee-open-model-science-post-training","kind":"editorial-diagram","role":"hero","src":"https://newruntime.com/images/posts/arcee-open-model-science-post-training.webp","alt":"A whiteboard training-loop diagram showing hypotheses, versioned runs, held-out scientific evaluations, trace review, a promoted adapter, and an agentic research app.","caption":"Arcee's science model work is interesting as a ledgered loop: one hypothesis per run, held-out evaluations, trace review, and a promoted specialist adapter.","credit":"New Runtime synthesis from Arcee AI open-model science write-up","source_url":"https://www.arcee.ai/blog/teaching-an-open-model-to-do-science","generated_with":"gemini-3.1-flash-image","width":1600,"height":900,"legend":[{"label":"Run ledger","description":"Each experiment records a hypothesis, bounded change, metrics, traces, and decision."},{"label":"Held-out checks","description":"Scientific environments and verifier review decide whether a run improved."},{"label":"Promotion","description":"A specialist adapter is promoted into an agentic research application after validation."}]}],"routes":{"html":"https://newruntime.com/posts/arcee-open-model-science-post-training/","markdown":"https://newruntime.com/posts/arcee-open-model-science-post-training.md","json":"https://newruntime.com/posts/arcee-open-model-science-post-training.json"},"source_format":"markdown","next_reads":[{"type":"topic","path":"/topics/open-models/","reason":"Explore the open models topic hub.","url":"https://newruntime.com/topics/open-models/","title":"Open Models - New Runtime","media_type":"text/html"},{"type":"related_material","path":"/posts/fireworks-lora-fullft-three-test-protocol/","reason":"Shares open models and post training.","url":"https://newruntime.com/posts/fireworks-lora-fullft-three-test-protocol/","title":"Run Three Tests Before Replacing LoRA With Full Fine-Tuning","media_type":"text/html"},{"type":"related_material","path":"/posts/sequoia-open-model-dependency-paradox/","reason":"Shares open models and post training.","url":"https://newruntime.com/posts/sequoia-open-model-dependency-paradox/","title":"Open Weights Can Still Create A Strategic Dependency","media_type":"text/html"},{"type":"related_material","path":"/posts/open-secure-ai-alliance-open-defense-stack/","reason":"Shares agent harnesses and open models.","url":"https://newruntime.com/posts/open-secure-ai-alliance-open-defense-stack/","title":"Open Secure AI Alliance Turns the AI-Safety Fight Into a Stack Question","media_type":"text/html"},{"type":"related_material","path":"/posts/agentic-sdlc-software-factory-loop/","reason":"Shares agent harnesses.","url":"https://newruntime.com/posts/agentic-sdlc-software-factory-loop/","title":"A Software Factory Connects Agents Through Verified Outcomes","media_type":"text/html"}]}