Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.12126 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915936111427584 |
|---|---|
| author | Wei, Rongzhe Shi, Ge Cheng, Min Zhang, Na Li, Pan Ghosh, Sarthak Gorde, Vaibhav Akoglu, Leman |
| author_facet | Wei, Rongzhe Shi, Ge Cheng, Min Zhang, Na Li, Pan Ghosh, Sarthak Gorde, Vaibhav Akoglu, Leman |
| contents | Large Language Models (LLMs) have significantly advanced tool-augmented agents, enabling autonomous reasoning via API interactions. However, executing multi-step tasks within massive tool libraries remains challenging due to two critical bottlenecks: (1) the absence of rigorous, plan-level evaluation frameworks and (2) the computational demand of exploring vast decision spaces stemming from large toolsets and long-horizon planning. To bridge these gaps, we first introduce SLATE (Synthetic Large-scale API Toolkit for E-commerce), a large-scale context-aware benchmark designed for the automated assessment of tool-integrated agents. Unlike static metrics, SLATE accommodates diverse yet functionally valid execution trajectories, revealing that current agents struggle with self-correction and search efficiency. Motivated by these findings, we next propose Entropy-Guided Branching (EGB), an uncertainty-aware search algorithm that dynamically expands decision branches where predictive entropy is high. EGB optimizes the exploration-exploitation trade-off, significantly enhancing both task success rates and computational efficiency. Extensive experiments on SLATE demonstrate that our dual contribution provides a robust foundation for developing reliable and scalable LLM agents in tool-rich environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_12126 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Long-Horizon Plan Execution in Large Tool Spaces through Entropy-Guided Branching Wei, Rongzhe Shi, Ge Cheng, Min Zhang, Na Li, Pan Ghosh, Sarthak Gorde, Vaibhav Akoglu, Leman Artificial Intelligence Computation and Language Large Language Models (LLMs) have significantly advanced tool-augmented agents, enabling autonomous reasoning via API interactions. However, executing multi-step tasks within massive tool libraries remains challenging due to two critical bottlenecks: (1) the absence of rigorous, plan-level evaluation frameworks and (2) the computational demand of exploring vast decision spaces stemming from large toolsets and long-horizon planning. To bridge these gaps, we first introduce SLATE (Synthetic Large-scale API Toolkit for E-commerce), a large-scale context-aware benchmark designed for the automated assessment of tool-integrated agents. Unlike static metrics, SLATE accommodates diverse yet functionally valid execution trajectories, revealing that current agents struggle with self-correction and search efficiency. Motivated by these findings, we next propose Entropy-Guided Branching (EGB), an uncertainty-aware search algorithm that dynamically expands decision branches where predictive entropy is high. EGB optimizes the exploration-exploitation trade-off, significantly enhancing both task success rates and computational efficiency. Extensive experiments on SLATE demonstrate that our dual contribution provides a robust foundation for developing reliable and scalable LLM agents in tool-rich environments. |
| title | Long-Horizon Plan Execution in Large Tool Spaces through Entropy-Guided Branching |
| topic | Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2604.12126 |