AI News HubLIVE
Original source2 min read

Contrastive Reflection for Iterative Prompt Optimization

This paper introduces Contrastive Reflection, an iterative framework for optimizing prompts in agentic information retrieval workflows. By analyzing retrieval or reasoning traces, it identifies error-anchored behavioral slices and contrasts them with nearby successful examples, prompting a Teacher LLM to propose targeted edits. On HotpotQA, exact-match accuracy improved from 51.4% to 60.4%, outperforming failure-only and random-evidence variants, and comparable to MIPROv2 (59.4%) and GEPA (57.0%). The framework emphasizes interpretability and validation-driven prompt repair.

SourcearXiv AIAuthor: Derek Koh, Jinghui Mo, Benjamin H. Le, Jiening Zhan, Baofen Zheng, Kevin Bevis, Nathaniel C. Owen, Lauren Elizabeth Charney, Wenqiong Liu, Jingwei Wu

-->

[Submitted on 29 Jun 2026]

Title:Contrastive Reflection for Iterative Prompt Optimization

View a PDF of the paper titled Contrastive Reflection for Iterative Prompt Optimization, by Derek Koh and 9 other authors

View PDF HTML (experimental)

Abstract:LLM agents are becoming central to information retrieval: they issue retrieval queries, synthesize answers, and increasingly serve as judges for IR evaluation. Improving the prompts that control these agents is an optimization problem, but in applied IR settings it often looks less like blind search and more like debugging. Engineers need to know which behavior failed, which nearby behavior still worked, what distinguishes the two, and whether a prompt edit improves held-out quality without introducing regressions.

We present Contrastive Reflection, an iterative prompt-optimization framework for agentic IR workflows. The framework starts from a task-centric quality definition: QA agents expose retrieval or reasoning traces, and grading agents expose dimension-level scores and rationales. These structured traces are used to identify error-anchored behavioral slices, add nearby successful examples from the same region, and ask a Teacher LLM to propose a targeted prompt edit. Candidate edits are accepted only when validation performance improves, optionally subject to regression checks. We instantiate the framework with a tree-based slice selector, but the contribution is the contrastive reflection loop rather than the tree itself.

On a public HotpotQA retrieval-augmented QA setup, one tree-selected contrastive repair improves held-out exact-match accuracy from 51.4% to 60.4%. Failure-only and random-evidence variants improve less and break more previously correct examples. A light instruction-only comparison places the method near modern prompt optimizers: MIPROv2 reaches 59.4% and GEPA 57.0%. The result is an interpretable optimization loop for IR agents, aimed at making prompt repair more inspectable and validation-driven.

Comments: 6 pages, 1 figure. To appear at Agent4IR @ KDD 2026 (KDD 2026 Workshop on AI Agents for Information Retrieval)

Subjects:

Artificial Intelligence (cs.AI)

ACM classes: I.2.7; H.3.3; I.2.6

Cite as: arXiv:2606.30840 [cs.AI]

(or arXiv:2606.30840v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2606.30840

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Derek Koh [view email] [v1] Mon, 29 Jun 2026 19:16:07 UTC (58 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Contrastive Reflection for Iterative Prompt Optimization, by Derek Koh and 9 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.AI

new | recent | 2026-06

Change to browse by:

cs

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)