{"type":"post","id":"frontiersmind-releases-lumma-fev-v2-decision-models-4b-76a463","slug":"frontiersmind-releases-lumma-fev-v2-decision-models-4b-76a463","title":"FrontiersMind releases Lumma-Fev-v2 decision models (4B and 27B) that return option probabilities in one forward pass","description":"FrontiersMind has released Lumma-Fev-4B-v2 and Lumma-Fev-27B-v2, decision models that return option probabilities rather than generated prose.","retrieval_nugget":"FrontiersMind has released Lumma-Fev-4B-v2 and Lumma-Fev-27B-v2, decision models that return option probabilities rather than generated prose. For teams building agent workflows, the relevant idea is a bounded decision interface: route, threshold, or escalate work using a distribution that code can consume directly instead of parsing model text.","published_at":"2026-10-31","updated_at":"2026-10-31","record_date":"2026-10-31","date_kind":"published_at","topics":["agent-workflows"],"entities":["FrontiersMind","Lumma-Fev-v2","Lumma-Fev-4B-v2","Lumma-Fev-27B-v2","decisionformer","TypeSafe Jev 1.13.0","Qwen3.8-27B"],"related_patterns":["model-answers-become-task-interfaces"],"novelty_label":"new_fact","what_changed":"FrontiersMind adds Lumma-Fev-v2 in 4B and 27B sizes, with option probabilities in one pass, to the growing set of decision-model releases.","prior_refs":["memory:5a6771e8-b2f0-854c-a784-d230a2b3b62b","memory:1249beae-0fc0-836e-af5e-38a8ed26f1e4"],"source_url":"https://huggingface.co/blog/FrontiersMind/lumma-fev-27b-v2","source_urls":["https://huggingface.co/blog/FrontiersMind/lumma-fev-27b-v2"],"schema_version":"newruntime-agent-readable-v0.2","stable_id":"post:frontiersmind-releases-lumma-fev-v2-decision-models-4b-76a463","status":"published","visuals":[],"editor":{"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]},"routes":{"html":"https://newruntime.com/posts/frontiersmind-releases-lumma-fev-v2-decision-models-4b-76a463/","markdown":"https://newruntime.com/posts/frontiersmind-releases-lumma-fev-v2-decision-models-4b-76a463.md","json":"https://newruntime.com/posts/frontiersmind-releases-lumma-fev-v2-decision-models-4b-76a463.json"},"next_reads":[{"type":"topic","path":"/topics/agent-workflows/","url":"https://newruntime.com/topics/agent-workflows/","title":"Agent Workflows","reason":"Explore the agent-workflows topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/agent-workflows.md","json_url":"https://newruntime.com/topics/agent-workflows.json"},{"type":"collection","path":"/posts/","url":"https://newruntime.com/posts/","title":"Field Notes","reason":"Open the latest editorial analysis.","media_type":"text/html","json_url":"https://newruntime.com/posts.json"},{"type":"collection","path":"/source-ledger.json","url":"https://newruntime.com/source-ledger.json","title":"Source Ledger","reason":"Inspect the public source evidence graph.","media_type":"application/json"}]}
