# ReAdapt improves warm‑introduction and reaction selection accuracy for Gemini‑3‑Flash

Digest AI · Research · published 2026-09-23T04:00:00Z

Canonical: https://digestai.news/story/readapt-improves-warmintroduction-and-reaction-selection-accuracy-for

## 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.

They 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.

Evaluated 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.

## Key points

- 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%

## Why it matters

Demonstrates that modeling relational context can substantially boost LLM‑agent performance in social decision‑making, impacting recommendation, outreach and other interaction‑heavy AI applications.

## Sources

1. [When LLM Agents Fail to Read the Room: ReAdapt for Relational Social Reasoning](https://arxiv.org/abs/2609.25284) (arXiv cs.AI, 2026-09-23, primary source)

## Cite

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

---

Written by Digest AI's editorial model from the linked sources; the sources are the record. 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
JSON: https://digestai.news/story/readapt-improves-warmintroduction-and-reaction-selection-accuracy-for.json