Author

Daeyoung Roh

h-index 2 View on Semantic Scholar

We have 3 of 10 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Conference Open access 2026

Distilling LLM Reasoning into Dense Encoders: Bridging the Accuracy-Efficiency Gap in Recommendation

Reasoning-to-Encoder Distilla-tion (R2END), a framework that establishes a text encoder as the optimal student architecture for scalable recommendation, and compresses the teacher’s reasoning into a dense vector space via a semantic alignment objec-tive, effectively capturing user-item dynamics.

D. Han, Daeyoung Roh, A. Y. Kim et al. · Annual Meeting of the Associ... · 0 citations

Preprint Aug 2026

Before Reasoning Can Fail: Pre-Evidence Procedural Failures in Agentic RAG

It is shown that evidence-gathering should be evaluated as a trajectory-level control problem, separately from answer-side reasoning, because larger hidden thinking budgets do not necessarily increase evidence inspection.

Daeyoung Roh, D. Han · 0 citations

#artificial intelligence Preprint Aug 2026

HALT: Verification-Aware Stopping for Retrieval-Augmented Search Agents

Evidence coverage provides a practical runtime control signal for improving retrieval-augmented agents without retraining or modifying the host agent.

Daeyoung Roh, D. Han · 0 citations