JTPRO: A Joint Tool-Prompt Reflective Optimization Framework for Language Agents
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Slot FillingSimilar Papers 제목 키워드 기반
Maestro: Joint Graph & Config Optimization for Reliable AI Agents
Building reliable LLM agents requires decisions at two levels: the graph (which modules exist and how information flows) and the configuration of each node (models, prompts, tools, control knobs). Most existing optimizer…
Reflection in the Dark: Exposing and Escaping the Black Box in Reflective Prompt Optimization
Automatic prompt optimization (APO) has emerged as a powerful paradigm for improving LLM performance without manual prompt engineering. Reflective APO methods such as GEPA iteratively refine prompts by diagnosing failure…
Prompt EngineeringMax-Min Fairness in IRS-Aided Multi-Cell MISO Systems with Joint Transmit and Reflective Beamforming
This paper investigates an intelligent reflecting surface (IRS)-aided multi-cell multiple-input single-output (MISO) system with several multi-antenna base stations (BSs) each communicating with a single-antenna user, in…
FairnessCan Large Language Models Self-Correct in Medical Question Answering? An Exploratory Study
Large language models (LLMs) have achieved strong performance on medical question answering (medical QA), and chain-of-thought (CoT) prompting has further improved results by eliciting explicit intermediate reasoning; me…
Question AnsweringGEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Large language models (LLMs) are increasingly adapted to downstream tasks via reinforcement learning (RL) methods like Group Relative Policy Optimization (GRPO), which often require thousands of rollouts to learn new tas…
Reinforcement Learning