# JTPRO: A Joint Tool-Prompt Reflective Optimization Framework for Language Agents

arXiv: https://arxiv.org/abs/2604.19821 · HTML: https://mlsanity.com/paper/2604.19821/

## Key facts

- Cited by 4 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 30 of its 47 references that are in the map.
- First posted on arXiv 20 Apr 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, 30 of 30)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines](https://mlsanity.com/paper/2310.03714/) (2023)
- [Automatic Prompt Optimization with "Gradient Descent" and Beam Search](https://mlsanity.com/paper/2305.03495/) (2023)
- [GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning](https://mlsanity.com/paper/2507.19457/) (2025)
- [ReTool: Reinforcement Learning for Strategic Tool Use in LLMs](https://mlsanity.com/paper/2504.11536/) (2025)
- [ToolRL: Reward is All Tool Learning Needs](https://mlsanity.com/paper/2504.13958/) (2025)
- [Optimizing Instructions and Demonstrations for Multi-Stage Language Model Programs](https://mlsanity.com/paper/2406.11695/) (2024)
- [ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models](https://mlsanity.com/paper/2305.18323/) (2023)
- [RestGPT: Connecting Large Language Models with Real-World RESTful APIs](https://mlsanity.com/paper/2306.06624/) (2023)
- [CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets](https://mlsanity.com/paper/2309.17428/) (2023)
- [AvaTaR: Optimizing LLM Agents for Tool Usage via Contrastive Reasoning](https://mlsanity.com/paper/2406.11200/) (2024)
- [Seal-Tools: Self-Instruct Tool Learning Dataset for Agent Tuning and Detailed Benchmark](https://mlsanity.com/paper/2405.08355/) (2024)
- [Feedback Descent: Open-Ended Text Optimization via Pairwise Comparison](https://mlsanity.com/paper/2511.07919/) (2025)
- [ToolRerank: Adaptive and Hierarchy-Aware Reranking for Tool Retrieval](https://mlsanity.com/paper/2403.06551/) (2024)
- [AutoPDL: Automatic Prompt Optimization for LLM Agents](https://mlsanity.com/paper/2504.04365/) (2025)
- [Procedural Environment Generation for Tool-Use Agents](https://mlsanity.com/paper/2506.11045/) (2025)
- [Hard Negative Mining for Domain-Specific Retrieval in Enterprise Systems](https://mlsanity.com/paper/2505.18366/) (2025)
- [Aligning LLMs for Multilingual Consistency in Enterprise Applications](https://mlsanity.com/paper/2509.23659/) (2025)
- [Maestro: Joint Graph & Config Optimization for Reliable AI Agents](https://mlsanity.com/paper/2509.04642/) (2025)
- [Can LLMs Narrate Tabular Data? An Evaluation Framework for Natural Language Representations of Text-to-SQL System Outputs](https://mlsanity.com/paper/2510.23854/) (2025)
- [CITI: Enhancing Tool Utilizing Ability in Large Language Models without Sacrificing General Performance](https://mlsanity.com/paper/2409.13202/) (2024)
- [Meta-Reasoning Improves Tool Use in Large Language Models](https://mlsanity.com/paper/2411.04535/) (2024)
- [Hybrid AI for Responsive Multi-Turn Online Conversations with Novel Dynamic Routing and Feedback Adaptation](https://mlsanity.com/paper/2506.02097/) (2025)
- [DiffuMask: Diffusion Language Model for Token-level Prompt Pruning](https://mlsanity.com/paper/2604.06627/) (2026)

## Built on by (most cited first, 4 of 4)

- [SkillsInjector: Dynamic Skill Context Construction for LLM Agents](https://mlsanity.com/paper/2605.29794/) (2026)
- [MemeMind: Reference-Guided Trace Construction for Offline Context Optimization](https://mlsanity.com/paper/2608.09316/) (2026)
- [DOCSCHISEL: Adaptive Tool Documentation Optimization Framework for LLM Agents](https://mlsanity.com/paper/2608.10037/) (2026)
- [Adaptive-GEPA: Make Your Harness Fit Heterogeneous Requests](https://mlsanity.com/paper/2609.38762/) (2026)

## Abstract (arXiv)

Large language model (LLM) agents augmented with external tools often struggle as number of tools grow large and become domain-specific. In such settings, ambiguous tool descriptions and under-specified agent instructions frequently lead to tool mis-selection and incorrect slot/value instantiation. We hypothesize that this is due to two root causes: generic, one-size-fits-all prompts that ignore tool-specific nuances, and underspecified tool schemas that lack clear guidance on when and how to use each tool and how to format its parameters. We introduce Joint Tool-Prompt Reflective Optimization (JTPRO), a framework for improving tool-calling reliability in trace-supervised settings by iteratively using rollout-driven reflection to co-optimize global instructions and per-tool schema/argument descriptions for accurate tool selection and argument instantiation in large tool inventories. JTPRO is designed to preserve only tool-local cues needed for correct disambiguation and slot filling. We evaluate JTPRO across multi-tool benchmarks, which account for different number of tools using three metrics: Tool Selection Accuracy (TSA), Slot Filling Accuracy(SFA), and Overall Success Rate(OSR) (correct tool + correct slots + correct values). JTPRO consistently outperforms strong baselines, including CoT-style agents, and reflective prompt optimizers such as GEPA by 5%-20% (relative) on OSR. Ablations show that joint optimization of instructions and tool schemas is more effective and robust than optimizing either component in isolation.