{"version":1,"type":"story","url":"https://digestai.news/story/readapt-improves-warmintroduction-and-reaction-selection-accuracy-for","json":"https://digestai.news/story/readapt-improves-warmintroduction-and-reaction-selection-accuracy-for.json","markdown":"https://digestai.news/story/readapt-improves-warmintroduction-and-reaction-selection-accuracy-for.md","slug":"readapt-improves-warmintroduction-and-reaction-selection-accuracy-for","headline":"ReAdapt improves warm‑introduction and reaction selection accuracy for Gemini‑3‑Flash","summary":"The paper “When LLM Agents Fail to Read the Room: ReAdapt for Relational Social Reasoning” argues that standard LLM‑agent loops ignore relational evidence, causing surface‑obvious choices when content and relationship cues diverge. To expose this failure, the authors build a benchmark of 500 synthetic social worlds that generate 1,000 queries across two tasks—reaction selection and warm introduction—where the surface‑obvious candidate differs from the relationship‑grounded oracle in about 53% of queries.\n\nThey introduce ReAdapt (Relationship‑Adaptive Agent with Policy‑driven sTate), which augments the ReAct loop with an explicit structured social state z = (G, B, R, N, D) capturing goal, belief, relationship, norm, and disclosure. After each tool observation, ReAdapt runs a typed Adapt step that updates this state and emits a policy operation (continue, switch, abandon, or clarify) before selecting the next action.\n\nEvaluated with Gemini‑3‑Flash on a stratified subset of n = 150 queries per task, ReAdapt raises warm‑introduction accuracy from 37% to 51% (+14 points) and reaction‑selection accuracy from 69% to 77% (+8 points). Oracle regret drops from 0.260 to 0.152 and from 0.095 to 0.053, suggesting explicit relational‑state adaptation helps LLM agents revise decisions based on social evidence.","keyPoints":["Benchmark includes 500 synthetic social worlds and 1,000 queries across reaction selection and warm introduction tasks","ReAdapt adds an explicit relational state and policy‑driven Adapt step to the ReAct loop","On 150‑query subsets, Gemini‑3‑Flash with ReAdapt improves warm‑introduction accuracy from 37% to 51% and reaction‑selection from 69% to 77%"],"whyItMatters":"Demonstrates that modeling relational context can substantially boost LLM‑agent performance in social decision‑making, impacting recommendation, outreach and other interaction‑heavy AI applications.","category":{"slug":"research","name":"Research","url":"https://digestai.news/category/research"},"entities":{"companies":[],"models":["Gemini-3-Flash"],"people":[]},"firstPublishedAt":"2026-09-23T04:00:00Z","updatedAt":"2026-09-23T04:00:00Z","sourceCount":1,"hasPrimarySource":true,"sources":[{"outlet":"arXiv cs.AI","title":"When LLM Agents Fail to Read the Room: ReAdapt for Relational Social Reasoning","url":"https://arxiv.org/abs/2609.25284","publishedAt":"2026-09-23T04:00:00Z","type":"primary","primary":true,"lead":true}],"sourceNotes":null,"discussions":[],"thread":null,"cite":{"text":"Digest AI, \"ReAdapt improves warm‑introduction and reaction selection accuracy for Gemini‑3‑Flash\", 23 September 2026, https://digestai.news/story/readapt-improves-warmintroduction-and-reaction-selection-accuracy-for","publisher":"Digest AI","title":"ReAdapt improves warm‑introduction and reaction selection accuracy for Gemini‑3‑Flash","datePublished":"2026-09-23T04:00:00Z","url":"https://digestai.news/story/readapt-improves-warmintroduction-and-reaction-selection-accuracy-for"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}