# Contrastive Reflection for Iterative Prompt Optimization

arXiv: https://arxiv.org/abs/2606.30840 · HTML: https://mlsanity.com/paper/2606.30840/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 8 of its 18 references that are in the map.
- First posted on arXiv 29 Jun 2026.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 8 of 8)

- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Large Language Models Are Human-Level Prompt Engineers](https://mlsanity.com/paper/2211.01910/) (2022)
- [Beyond Accuracy: Behavioral Testing of NLP models with CheckList](https://mlsanity.com/paper/2005.04118/) (2020)
- [PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt Optimization](https://mlsanity.com/paper/2310.16427/) (2023)
- [Domino: Discovering Systematic Errors with Cross-Modal Embeddings](https://mlsanity.com/paper/2203.14960/) (2022)
- [Large language models can accurately predict searcher preferences](https://mlsanity.com/paper/2309.10621/) (2023)
- [StraGo: Harnessing Strategic Guidance for Prompt Optimization](https://mlsanity.com/paper/2410.08601/) (2024)

## Built on by (most cited first, 1 of 1)

- [AtomSearch: Evidence-Grounded Tree Search for Agent Skill Optimization](https://mlsanity.com/paper/2610.19951/) (2026)

## Abstract (arXiv)

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.