# LEAP: Learning Efficient Action Proposals For LLM Agents

arXiv: https://arxiv.org/abs/2610.02670 · HTML: https://mlsanity.com/paper/2610.02670/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reinforcement learning for LLM agents, one of 16 directions in LLM agents and tool use.
- Builds on 23 of its 24 references that are in the map.
- First posted on arXiv 2 Oct 2026.

## Placed in

- LLM agents and tool use / [Reinforcement learning for LLM agents](https://mlsanity.com/agents/reinforcement-learning-for-llm-agents/)

## Builds on (most cited first, 23 of 23)

- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [Accelerating Large Language Model Decoding with Speculative Sampling](https://mlsanity.com/paper/2302.01318/) (2023)
- [Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads](https://mlsanity.com/paper/2401.10774/) (2024)
- [τ2-Bench: Evaluating Conversational Agents in a Dual-Control Environment](https://mlsanity.com/paper/2506.07982/) (2025)
- [EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty](https://mlsanity.com/paper/2401.15077/) (2024)
- [OpenAGI: When LLM Meets Domain Experts](https://mlsanity.com/paper/2304.04370/) (2023)
- [DistillSpec: Improving Speculative Decoding via Knowledge Distillation](https://mlsanity.com/paper/2310.08461/) (2023)
- [TaskBench: Benchmarking Large Language Models for Task Automation](https://mlsanity.com/paper/2311.18760/) (2023)
- [Online Speculative Decoding](https://mlsanity.com/paper/2310.07177/) (2023)
- [Speculative Actions: A Lossless Framework for Faster Agentic Systems](https://mlsanity.com/paper/2510.04371/) (2025)
- [Parallelizing Tool Execution and LLM Generation for Low-Latency Agent Serving](https://mlsanity.com/paper/2603.18897/) (2026)
- [Interactive Speculative Planning: Enhance Agent Efficiency through Co-design of System and User Interface](https://mlsanity.com/paper/2410.00079/) (2024)
- [Optimizing Agentic Language Model Inference via Speculative Tool Calls](https://mlsanity.com/paper/2512.15834/) (2025)
- [Dynamic Speculative Agent Planning](https://mlsanity.com/paper/2509.01920/) (2025)
- [Training Domain Draft Models for Speculative Decoding: Best Practices and Insights](https://mlsanity.com/paper/2503.07807/) (2025)
- [Reducing Latency of LLM Search Agent via Speculation-based Algorithm-System Co-Design](https://mlsanity.com/paper/2511.20048/) (2025)
- [DualSpec: Accelerating Deep Research Agents via Dual-Process Action Speculation](https://mlsanity.com/paper/2603.07416/) (2026)
- [SPORK: Self-Speculative Forking to Accelerate Agentic LLM Inference](https://mlsanity.com/paper/2607.03333/) (2026)
- [Speculate with Memory: Lossless Acceleration for LLM Agents](https://mlsanity.com/paper/2607.12236/) (2026)
- [AOSpec: Action and Observation Co-Speculation for Low-Latency Agent Serving](https://mlsanity.com/paper/2608.00881/) (2026)
- [Speculate While You Reason: Teaching Agents to Predict Their Next Tool Call via Joint Agent-Speculator RL](https://mlsanity.com/paper/2607.25816/) (2026)
- [Speculative Macro Commit for Faster Tool-Using Agents](https://mlsanity.com/paper/2609.03236/) (2026)
- [OoO-Spec: Out-of-Order Semantic Speculation for Fast Tool Calling](https://mlsanity.com/paper/2608.00814/) (2026)

## Abstract (arXiv)

LLM agents are known to be slow in rollouts. An agent completes a task one step at a time. At each step, it reasons and then chooses an action to execute. The next step and action cannot start until the previous one has finished. Speculative decoding accelerates the rollouts at the reason phase by drafting and verifying the inference tokens. Recent works have also started to apply similar ideas at the action phase. These works use off-the-shelf models, usually large, to draft action proposals for target model to verify. Large drafters match the target more often but take longer to propose, while small off-the-shelf models are fast but rarely make the same decision as the target. We ask a more general question: what determines the end-to-end speedup of action speculation? To answer it, we develop a latency framework for the speculative round. The framework compares what a round gains with what it costs. The gain depends on how well the drafter predicts the target and on how many steps the task can take before it ends. The cost comes from drafting, from waiting for target verification and from executing tools. Guided by the framework, we introduce LEAP (Learning Efficient Action Proposals) which keeps the drafter small and makes it accurate by training it on the target actions sequences. With a small 0.6B model, LEAP agrees with the target on most decisions and makes agents up to 60% faster in end-to-end wall clock time, with no systematic change in task success. Across various datasets, target models and draft models, the framework accounts for most of the measured speedups. We also show the draft model can be online trained with no prior trace collection and match the performance of offline training, making LEAP practical to deploy in the real world.