# Lookahead-R: Budget-Aware Tool Retrieval via Execution-Centric Planning

arXiv: https://arxiv.org/abs/2609.35811 · HTML: https://mlsanity.com/paper/2609.35811/

## 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 7 of its 52 references that are in the map.
- First posted on arXiv 20 Sep 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, 7 of 7)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [ZeRO: Memory Optimizations Toward Training Trillion Parameter Models](https://mlsanity.com/paper/1910.02054/) (2019)
- [Where LLM Agents Fail and How They can Learn From Failures](https://mlsanity.com/paper/2509.25370/) (2025)
- [Budget-Aware Tool Use Enables Effective Agent Scaling](https://mlsanity.com/paper/2511.17006/) (2025)
- [WebSynthesis: World-Model-Guided MCTS for Efficient WebUI-Trajectory Synthesis](https://mlsanity.com/paper/2507.04370/) (2025)
- [Enhancing Tool Retrieval with Iterative Feedback from Large Language Models](https://mlsanity.com/paper/2406.17465/) (2024)
- [Cost-Awareness in Tree-Search LLM Planning: A Systematic Study](https://mlsanity.com/paper/2505.14656/) (2025)

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

- [What Can Component-Replacement Evidence Establish? A Critical Scoping Review of Local Decisions in LLM Agents](https://mlsanity.com/paper/2609.39989/) (2026)

## Abstract (arXiv)

Tool retrieval is a critical bottleneck for LLM-based agents operating over large, heterogeneous API ecosystems. Existing approaches face an inherent trade-off: semantic retrievers are fast but suffer from the semantic-functional gap, while execution-based validation improves precision at the cost of prohibitive latency. We propose Lookahead-R, a planning-based framework that reformulates tool retrieval as a resource-constrained sequential decision-making problem. At its core, Lookahead-R introduces a lightweight execution-aware surrogate world model that jointly predicts tool execution success, latency cost, and semantic utility---without invoking real APIs. This world model drives a cost-sensitive, uncertainty-guided Monte Carlo Tree Search that navigates the tool space under strict budget constraints. Evaluated on the large-scale ToolBench benchmark, Lookahead-R achieves a superior accuracy-efficiency trade-off across all test scenarios. On the most challenging I3 split, it attains an NDCG@5 of 91.40%, outperforming the state-of-the-art ToolGen (90.16%) by 1.24%. Ablation studies confirm that explicit latency modeling is the key discriminative signal for identifying high-quality tools under resource constraints.