# LinguaFluid: Language Guided Fluid Control via Semantic Rewards in Reinforcement Learning

arXiv: https://arxiv.org/abs/2508.05977 · HTML: https://mlsanity.com/paper/2508.05977/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reward modeling and RLHF, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 21 of its 31 references that are in the map.
- First posted on arXiv 8 Aug 2025.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Reward modeling and RLHF](https://mlsanity.com/alignment/reward-modeling-and-rlhf/)

## Builds on (most cited first, 21 of 21)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [Code as Policies: Language Model Programs for Embodied Control](https://mlsanity.com/paper/2209.07753/) (2022)
- [MPNet: Masked and Permuted Pre-training for Language Understanding](https://mlsanity.com/paper/2004.09297/) (2020)
- [An LLM Compiler for Parallel Function Calling](https://mlsanity.com/paper/2312.04511/) (2023)
- [The Learnability of In-Context Learning](https://mlsanity.com/paper/2303.07895/) (2023)
- [Q-attention: Enabling Efficient Learning for Vision-based Robotic Manipulation](https://mlsanity.com/paper/2105.14829/) (2021)
- [LLMLight: Large Language Models as Traffic Signal Control Agents](https://mlsanity.com/paper/2312.16044/) (2023)
- [RLOC: Terrain-Aware Legged Locomotion using Reinforcement Learning and Optimal Control](https://mlsanity.com/paper/2012.03094/) (2020)
- [RL-GPT: Integrating Reinforcement Learning and Code-as-policy](https://mlsanity.com/paper/2402.19299/) (2024)
- [A Large Language Model-Driven Reward Design Framework via Dynamic Feedback for Reinforcement Learning](https://mlsanity.com/paper/2410.14660/) (2024)
- [Latent Reward: LLM-Empowered Credit Assignment in Episodic Reinforcement Learning](https://mlsanity.com/paper/2412.11120/) (2024)
- [Trajectory Prediction Meets Large Language Models: A Survey](https://mlsanity.com/paper/2506.03408/) (2025)
- [DVPT: Dynamic Visual Prompt Tuning of Large Pre-trained Models for Medical Image Analysis](https://mlsanity.com/paper/2307.09787/) (2023)
- [Using Large Language Models for Parametric Shape Optimization](https://mlsanity.com/paper/2412.08072/) (2024)
- [Inverse Reinforcement Learning Meets Large Language Model Post-Training: Basics, Advances, and Opportunities](https://mlsanity.com/paper/2507.13158/) (2025)
- [Online identification and control of PDEs via Reinforcement Learning methods](https://mlsanity.com/paper/2308.04068/) (2023)

## Abstract (arXiv)

In the domain of scientific machine learning, designing effective reward functions remains a challenge in reinforcement learning (RL), particularly in environments where task goals are difficult to specify numerically. Reward functions in existing work are predominantly based on heuristics, manual engineering, or task-specific tuning. In this work, we introduce a semantically aligned reinforcement learning method where rewards are computed by aligning the current state with a target semantic instruction using a Sentence-Bidirectional Encoder Representations from Transformers (SBERT). Instead of relying on manually defined reward functions, the policy receives feedback based on the reward, which is a cosine similarity between the goal textual description and the statement description in the episode. We evaluated our approach in several environments and showed that semantic reward can guide learning to achieve competitive control behavior, even in the absence of hand-crafted reward functions. Our study demonstrates a correlation between the language embedding space and the conventional Euclidean space. This framework opens new horizons for aligning agent behavior with natural language goals and lays the groundwork for a more seamless integration of larger language models (LLMs) and fluid control applications.