JTPRO: A Joint Tool-Prompt Reflective Optimization Framework for Language Agents
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913053504700416 |
|---|---|
| author | Ghoshal, Sandip Mittal, Anshul Singh, Jyotika Ballesteros, Miguel Sun, Weiyi Tu, Fang Singh, Shailender Benajiba, Yassine Shah, Fahad Bharadwaj, Sujeeth Ravi, Sujith Roth, Dan |
| author_facet | Ghoshal, Sandip Mittal, Anshul Singh, Jyotika Ballesteros, Miguel Sun, Weiyi Tu, Fang Singh, Shailender Benajiba, Yassine Shah, Fahad Bharadwaj, Sujeeth Ravi, Sujith Roth, Dan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_19821 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | JTPRO: A Joint Tool-Prompt Reflective Optimization Framework for Language Agents Ghoshal, Sandip Mittal, Anshul Singh, Jyotika Ballesteros, Miguel Sun, Weiyi Tu, Fang Singh, Shailender Benajiba, Yassine Shah, Fahad Bharadwaj, Sujeeth Ravi, Sujith Roth, Dan Artificial Intelligence Software Engineering 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. |
| title | JTPRO: A Joint Tool-Prompt Reflective Optimization Framework for Language Agents |
| topic | Artificial Intelligence Software Engineering |
| url | https://arxiv.org/abs/2604.19821 |