{"data":{"event":{"id":"6bb82322-0181-4816-a264-8609b010b6aa","slug":"scacorn-context-engineered-agent-orchestration-of-specialized-small-lang-cde183adba","title":"\n\nscACORN: Context-engineered agent orchestration of specialized small language models for single-cell transcriptomic interpretation \n\n","short_summary":"Single-cell atlases now exceed 66 million cells, but turning a ranked expression profile and a free-form biological question into a reliable, evidence-grounded answer remains unsolved. Scaling a single model does not resolve this, because single-cell interpretation is a heterogeneous family of tasks whose correct answer depends on tissue, cohort, perturbation and annotation resolution. Here we present scACORN, an agentic alternative to monolithic single-cell language models that combines specialized small language models with context-engineered agent orchestration for their selection and compo","full_description":"Single-cell atlases now exceed 66 million cells, but turning a ranked expression profile and a free-form biological question into a reliable, evidence-grounded answer remains unsolved. Scaling a single model does not resolve this, because single-cell interpretation is a heterogeneous family of tasks whose correct answer depends on tissue, cohort, perturbation and annotation resolution. Here we present scACORN, an agentic alternative to monolithic single-cell language models that combines specialized small language models with context-engineered agent orchestration for their selection and composition at inference time. Each expert is built in two stages: domain-aligned contrastive adaptation fits a pretrained cell-to-text backbone to the transcriptomic geometry of a target dataset, and geometry-preserving specialization learns question-conditioned biological completions without eroding that geometry. A fixed orchestrating language model agent then selects and combines experts under a natural-language playbook that is itself optimized from textual feedback, with no gradient updates to the orchestrator. Across 10 Tabula Sapiens tissues, domain alignment raised transfer macro-F1 from 0.36 to 0.64 and Recall@5 from 0.87 to 0.97; specialized experts reached 0.89 mean exact-match annotation accuracy; and playbook optimization reduced unsupported gene citations from 14.5% to 3.5%. Our findings support specialization and orchestration as complementary responses to the heterogeneity and evidentiary demands of single-cell analysis.","ledger_type":"benefit","primary_domain_id":"8f1af1b9-7302-4b51-aae9-fdfac04d158a","event_status":"provisional","event_date":"2026-09-16T00:00:00.000Z","discovery_date":"2026-09-16T00:00:00.000Z","first_published_date":"2026-09-16T00:00:00.000Z","last_reviewed_date":"2026-09-16T00:00:00.000Z","geographic_scope":"International","affected_population":null,"base_impact_tier":1,"base_score":"1.00","attribution_multiplier":"0.1000","evidence_multiplier":"0.1000","realization_multiplier":"0.2000","durability_multiplier":"0.5000","current_event_score":"0.001000","confidence_level":"low","score_explanation":"Auto-published from news ingest as a provisional placeholder. Score is conservative until a named release is identified and the record is rescored.","methodology_version_id":"8745541b-0f8e-4d5a-9b47-5291d3813a8d","original_methodology_version_id":"8745541b-0f8e-4d5a-9b47-5291d3813a8d","published_at":"2026-09-16T20:00:53.660Z","created_at":"2026-09-16T20:00:53.660Z","updated_at":"2026-09-16T20:00:53.660Z","flags":[],"domain_name":"Biology","domain_slug":"biology","methodology_version":"0.2"},"contributions":[{"id":"d7d64120-f56b-49f8-828a-f0dc298d7ab2","event_id":"6bb82322-0181-4816-a264-8609b010b6aa","model_id":"535014f7-c941-4d39-aa9b-8f9c1d3d07b7","role_description":"Unspecified system mentioned or implied by a news item. Remap to a named release when identified.","attribution_multiplier":"0.1000","credit_share":"1.0000","contribution_score":"0.001000","attribution_rationale":"News ingest does not infer a named model from the publisher alone. Attribution stays unspecified until a release is identified.","attribution_confidence":"medium","first_used_date":"2026-09-16T00:00:00.000Z","model_version_if_known":null,"review_status":"approved","created_at":"2026-09-16T20:00:53.673Z","model_slug":"unspecified-ai-system","model_name":"Unspecified AI system","identity_class":"unknown","is_internal":false,"family_name":"Unspecified","family_slug":"unknown-unspecified","organization_name":"Unknown","organization_slug":"unknown"}],"sources":[{"id":"76efc0e4-ab5d-48b1-b23a-8b9087f03b5a","event_id":"6bb82322-0181-4816-a264-8609b010b6aa","url":"\nhttps://www.biorxiv.org/content/10.64898/2026.09.10.750801v1?rss=1\n","canonical_url":"\nhttps://www.biorxiv.org/content/10.64898/2026.09.10.750801v1?rss=1\n","source_type":"preprint","publisher":"bioRxiv","author":null,"publication_date":"2026-09-16T00:00:00.000Z","retrieved_at":"2026-09-16T20:00:53.682Z","title":"\n\nscACORN: Context-engineered agent orchestration of specialized small language models for single-cell transcriptomic interpretation \n\n","excerpt":"Single-cell atlases now exceed 66 million cells, but turning a ranked expression profile and a free-form biological question into a reliable, evidence-grounded answer remains unsolved. Scaling a single model does not resolve this, because single-cell interpretation is a heterogeneous family of tasks whose correct answer depends on tissue, cohort, perturbation and annotation resolution. Here we present scACORN, an agentic alternative to monolithic single-cell language models that combines special","content_hash":null,"source_reliability_class":"medium","is_primary_source":true,"is_independent":true,"is_peer_reviewed":false,"archived_url":null,"created_at":"2026-09-16T20:00:53.682Z"}],"claims":[{"id":"a163af87-4ece-4fd7-b6d1-0096bcf9a8dc","event_id":"6bb82322-0181-4816-a264-8609b010b6aa","claim_text":"\n\nscACORN: Context-engineered agent orchestration of specialized small language models for single-cell transcriptomic interpretation \n\n","claim_type":"outcome","claim_status":"supported","confidence_score":null,"created_at":"2026-09-16T20:00:53.690Z","updated_at":"2026-09-16T20:00:53.690Z"}],"revisions":[{"id":"7713b69e-d781-4872-9e4a-416f7a1d131a","event_id":"6bb82322-0181-4816-a264-8609b010b6aa","model_id":null,"previous_score":"0.000000","new_score":"0.001000","previous_factors":{},"new_factors":{"evidence":0.1,"base_score":1,"durability":0.5,"attribution":0.1,"realization":0.2},"change_reason":"Auto-published from news ingest.","trigger_type":"news_ingest","trigger_source_ids":null,"reviewer_id":null,"review_status":"published","created_at":"2026-09-16T20:00:53.697Z"}],"secondary":[]},"methodology_version":"0.1"}