# Specification-Aware Distribution Shaping for Robotics Foundation Models

arXiv: https://arxiv.org/abs/2603.17969 · HTML: https://mlsanity.com/paper/2603.17969/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 28 references that are in the map.
- First posted on arXiv 18 Mar 2026.

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

- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [Objaverse: A Universe of Annotated 3D Objects](https://mlsanity.com/paper/2212.08051/) (2022)
- [AI2-THOR: An Interactive 3D Environment for Visual AI](https://mlsanity.com/paper/1712.05474/) (2017)
- [Foundation Models in Robotics: Applications, Challenges, and the Future](https://mlsanity.com/paper/2312.07843/) (2023)
- [Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis](https://mlsanity.com/paper/2312.08782/) (2023)
- [SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning](https://mlsanity.com/paper/2503.03480/) (2025)
- [Plug in the Safety Chip: Enforcing Constraints for LLM-driven Robot Agents](https://mlsanity.com/paper/2309.09919/) (2023)
- [Q-Learning for Robust Satisfaction of Signal Temporal Logic Specifications](https://mlsanity.com/paper/1609.07409/) (2016)
- [PoliFormer: Scaling On-Policy RL with Transformers Results in Masterful Navigators](https://mlsanity.com/paper/2406.20083/) (2024)
- [Grammar-Aligned Decoding](https://mlsanity.com/paper/2405.21047/) (2024)
- [FLaRe: Achieving Masterful and Adaptive Robot Policies with Large-Scale Reinforcement Learning Fine-Tuning](https://mlsanity.com/paper/2409.16578/) (2024)
- [SPOC: Imitating Shortest Paths in Simulation Enables Effective Navigation and Manipulation in the Real World](https://mlsanity.com/paper/2312.02976/) (2023)
- [Generating Robot Constitutions & Benchmarks for Semantic Safety](https://mlsanity.com/paper/2503.08663/) (2025)
- [Tractable Reinforcement Learning of Signal Temporal Logic Objectives](https://mlsanity.com/paper/2001.09467/) (2020)
- [Robust Temporal Logic Model Predictive Control](https://mlsanity.com/paper/1511.00347/) (2015)
- [SELP: Generating Safe and Efficient Task Plans for Robot Agents with Large Language Models](https://mlsanity.com/paper/2409.19471/) (2024)
- [On-Line Monitoring for Temporal Logic Robustness](https://mlsanity.com/paper/1408.0045/) (2014)
- [Deep reinforcement learning under signal temporal logic constraints using Lagrangian relaxation](https://mlsanity.com/paper/2201.08504/) (2022)
- [Funnel-based Reward Shaping for Signal Temporal Logic Tasks in Reinforcement Learning](https://mlsanity.com/paper/2212.03181/) (2022)
- [Multi-Agent Reinforcement Learning Guided by Signal Temporal Logic Specifications](https://mlsanity.com/paper/2306.06808/) (2023)
- [Constrained Decoding for Safe Robot Navigation Foundation Models](https://mlsanity.com/paper/2509.01728/) (2025)
- [Control Barrier Functions with Actuation Constraints under Signal Temporal Logic Specifications](https://mlsanity.com/paper/2204.03631/) (2022)

## Abstract (arXiv)

Robotics foundation models have demonstrated strong capabilities in executing natural language instructions across diverse tasks and environments. However, they remain largely data-driven and lack formal guarantees on safety and satisfaction of time-dependent specifications during deployment. In practice, robots often need to comply with operational constraints involving rich spatio-temporal requirements such as time-bounded goal visits, sequential objectives, and persistent safety conditions. In this work, we propose a specification-aware action distribution optimization framework that enforces a broad class of Signal Temporal Logic (STL) constraints during execution of a pretrained robotics foundation model without modifying its parameters. At each decision step, the method computes a minimally modified action distribution that satisfies a hard STL feasibility constraint by reasoning over the remaining horizon using forward dynamics propagation. We validate the proposed framework in simulation using a state-of-the-art robotics foundation model across multiple environments and complex specifications.