AI Paper Atlas

Research map / Large language models / Agents, code and math

ReIn: Conversational Error Recovery with Reasoning Inception

Takyoung Kim, Jinseok Nam, Chandrayee Basu, Xing Fan, Chengyuan Ma, Heng Ji, Gokhan Tur, Dilek Hakkani-Tür

ICLR 2026 · Large language models › Agents, code and math · approach: Long-horizon LLM agents · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add ReIn inception blocktask agent (Sonnet 3.7, Haiku 3.5) · tau-Bench retail, seen error typesPass^1Improved
add ReIn on ambiguous requeststask agent · tau-Bench ambiguous scenariosPass^1Improved
add ReIn on unseen error types (Contradiction, Domain)task agent · tau-Bench unseen scenariosPass^1Improved
use smaller Llama 3.2 3B inception module instead of larger modules (ablation)ReIn · tau-Bench seen and unseenPass^1: 100% -> 81.48% (activation, airline Anaphora)Hurt
use ReIn instead of explicit prompt modification (NPI, self-refine)Sonnet 3.7 · tau-Bench retailPass^1Improved
let ReIn activate dynamically at any turnSonnet 3.7 · tau-Bench airlinePass^1Improved
define recovery plan as plain response phrase instead of a recovery tool (ablation)ReIn · instruction-hierarchy testtask completion rate: tool-based -> 0%Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy