# PACE: Adaptive Budget Allocation for Time-Efficient Embodied Planning

arXiv: https://arxiv.org/abs/2608.03034 · HTML: https://mlsanity.com/paper/2608.03034/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 12 of its 34 references that are in the map.
- First posted on arXiv 4 Aug 2026.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)

## Builds on (most cited first, 12 of 12)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [On the Planning Abilities of Large Language Models : A Critical Investigation](https://mlsanity.com/paper/2305.15771/) (2023)
- [Token-Budget-Aware LLM Reasoning](https://mlsanity.com/paper/2412.18547/) (2024)
- [PDDLStream: Integrating Symbolic Planners and Blackbox Samplers via Optimistic Adaptive Planning](https://mlsanity.com/paper/1802.08705/) (2018)
- [Compositional Foundation Models for Hierarchical Planning](https://mlsanity.com/paper/2309.08587/) (2023)
- [Robotouille: An Asynchronous Planning Benchmark for LLM Agents](https://mlsanity.com/paper/2502.05227/) (2025)
- [Adaptively Informed Trees (AIT*): Fast Asymptotically Optimal Path Planning through Adaptive Heuristics](https://mlsanity.com/paper/2002.06599/) (2020)
- [Adaptive Informative Path Planning with Multimodal Sensing](https://mlsanity.com/paper/2003.09746/) (2020)
- [Draft-Thinking: Learning Efficient Reasoning in Long Chain-of-Thought LLMs](https://mlsanity.com/paper/2603.00578/) (2026)
- [Language Cognition and Language Computation -- Human and Machine Language Understanding](https://mlsanity.com/paper/2301.04788/) (2023)

## Built on by (most cited first, 2 of 2)

- [The Organization of Inference: Information, Resource Constraints, and AI Production](https://mlsanity.com/paper/2609.20449/) (2026)
- [RT-Safe: Benchmarking Agent Safety in Real-Time Embodied Environment](https://mlsanity.com/paper/2610.09294/) (2026)

## Abstract (arXiv)

Reasoning-enhanced large language models have achieved remarkable improvements in planning tasks, yet their deployment in embodied systems remains impractical due to prohibitive inference delays-often exceeding minutes per planning instance. The fundamental bottleneck stems from the serial nature of existing paradigms: models must complete all reasoning before any action execution, leaving execution time windows entirely unexploited. We introduce PACE (Planning with Adaptive Cognitive Effort), a framework that enables interleaved reasoning and execution through two key innovations: an Interleaved Think-Act architecture that pipelines cognitive processing with action execution, and a Dynamic Budget Allocator that adapts reasoning token budgets to available execution time windows. On the Robotouille benchmark using Qwen3-8B-AWQ, PACE achieves a 10% success rate-representing a 67% improvement over the ReAct+Think baseline-while delivering 6.9 times acceleration in thinking time compared to unconstrained reasoning. The framework hides 66.8% of thinking time within execution windows, demonstrating that strategic cognitive effort allocation can simultaneously improve both planning quality and time efficiency. These results provide evidence that time-aware architectural innovations enable reasoning models to operate in latency-sensitive embodied domains where they were previously impractical.