# Reflective Prompt Tuning through Language Model Function-Calling

arXiv: https://arxiv.org/abs/2605.21781 · HTML: https://mlsanity.com/paper/2605.21781/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Tool learning and function calling, one of 16 directions in LLM agents and tool use.
- Builds on 18 of its 39 references that are in the map.
- First posted on arXiv 20 May 2026.

## Placed in

- LLM agents and tool use / [Tool learning and function calling](https://mlsanity.com/agents/tool-learning-and-function-calling/)

## Builds on (most cited first, 18 of 18)

- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity](https://mlsanity.com/paper/2104.08786/) (2021)
- [Large Language Models Are Human-Level Prompt Engineers](https://mlsanity.com/paper/2211.01910/) (2022)
- [Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs](https://mlsanity.com/paper/2306.13063/) (2023)
- [DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines](https://mlsanity.com/paper/2310.03714/) (2023)
- [Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting](https://mlsanity.com/paper/2310.11324/) (2023)
- [Automatic Prompt Optimization with "Gradient Descent" and Beam Search](https://mlsanity.com/paper/2305.03495/) (2023)
- [Optimizing Instructions and Demonstrations for Multi-Stage Language Model Programs](https://mlsanity.com/paper/2406.11695/) (2024)
- [ProSA: Assessing and Understanding the Prompt Sensitivity of LLMs](https://mlsanity.com/paper/2410.12405/) (2024)
- [Agent-Pro: Learning to Evolve via Policy-Level Reflection and Optimization](https://mlsanity.com/paper/2402.17574/) (2024)
- [Learning to Route LLMs with Confidence Tokens](https://mlsanity.com/paper/2410.13284/) (2024)
- [A Systematic Survey of Automatic Prompt Optimization Techniques](https://mlsanity.com/paper/2502.16923/) (2025)
- [Dynamic Evaluation of Transformer Language Models](https://mlsanity.com/paper/1904.08378/) (2019)
- [FinLoRA: Benchmarking LoRA Methods for Fine-Tuning LLMs on Financial Datasets](https://mlsanity.com/paper/2505.19819/) (2025)
- [Are LLM Decisions Faithful to Verbal Confidence?](https://mlsanity.com/paper/2601.07767/) (2026)
- [ClusterFusion: Hybrid Clustering with Embedding Guidance and LLM Adaptation](https://mlsanity.com/paper/2512.04350/) (2025)

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

- [Adaptive-GEPA: Make Your Harness Fit Heterogeneous Requests](https://mlsanity.com/paper/2609.38762/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have become increasingly capable of following instructions and complex reasoning, making prompting a flexible interface for adapting models without parameter updates. Yet prompt design remains labor-intensive and highly sensitive to formatting, phrasing, and instruction order, motivating automated prompt optimization methods that reduce manual effort while preserving inference-time flexibility. However, existing methods often search over prompt candidates or use fixed critique-refine pipelines driven by individual examples or small batches, limiting their ability to capture systematic error patterns and make targeted edits grounded in failure history. We propose Reflective Prompt Tuning (RPT), a framework that uses LLM function calling to simulate the iterative workflow of human prompt engineers. An LLM optimizer calls a diagnostic function that evaluates the target model over an entire optimization set, summarizes recurring failure modes, and returns a structured diagnostic report. The optimizer uses this report, together with an accumulated memory of prior reports, to revise the prompt for the next iteration. RPT further supports confidence-aware optimization by using calibration signals in diagnostic feedback and final prompt selection. Across three reasoning tasks, RPT improves over initial prompts by up to 12.9 points, remains competitive with state of the art, and improves confidence calibration. Our analyses show that RPT is especially effective on multi-hop and mathematical reasoning, producing targeted prompt revisions that align with diagnosed failure patterns and lead to gains in task performance and calibration.