Ground-Compose-Reinforce: Grounding Language in Agentic Behaviours using Limited Data

• URL: http://arxiv.org/abs/2507.10741v2
• Date: Sun, 26 Oct 2025 19:50:20 GMT
• Title: Ground-Compose-Reinforce: Grounding Language in Agentic Behaviours using Limited Data
• Authors: Andrew C. Li, Toryn Q. Klassen, Andrew Wang, Parand A. Alamdari, Sheila A. McIlraith,
• Abstract summary: Grounding language in perception and action is a key challenge when building situated agents that can interact with humans, or other agents, via language.<n>We propose Ground-Compose-Reinforce, an end-to-end, neurosymbolic framework for training RL agents directly from high-level task specifications.
• Score: 17.614395125762304
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Grounding language in perception and action is a key challenge when building situated agents that can interact with humans, or other agents, via language. In the past, addressing this challenge has required manually designing the language grounding or curating massive datasets that associate language with the environment. We propose Ground-Compose-Reinforce, an end-to-end, neurosymbolic framework for training RL agents directly from high-level task specifications--without manually designed reward functions or other domain-specific oracles, and without massive datasets. These task specifications take the form of Reward Machines, automata-based representations that capture high-level task structure and are in some cases autoformalizable from natural language. Critically, we show that Reward Machines can be grounded using limited data by exploiting compositionality. Experiments in a custom Meta-World domain with only 350 labelled pretraining trajectories show that our framework faithfully elicits complex behaviours from high-level specifications--including behaviours that never appear in pretraining--while non-compositional approaches fail.

Related papers

• HELP: Hierarchical Embodied Language Planner for Household Tasks [75.38606213726906]
  Embodied agents tasked with complex scenarios rely heavily on robust planning capabilities.<n>Large language models equipped with extensive linguistic knowledge can play this role.<n>We propose a Hierarchical Embodied Language Planner, called HELP, consisting of a set of LLM-based agents.
  arXiv  Detail & Related papers  (2025-12-25T15:54:08Z)
• CuES: A Curiosity-driven and Environment-grounded Synthesis Framework for Agentic RL [35.086788669916594]
  Large language model based agents are increasingly deployed in complex, tool augmented environments.<n>Existing approaches typically assume predefined task collections, an assumption that fails in novel environments.<n>We propose CuES, a Curiosity driven and Environment grounded Synthesis framework that autonomously generates diverse, executable, and meaningful tasks.
  arXiv  Detail & Related papers  (2025-12-01T06:11:37Z)
• Words into World: A Task-Adaptive Agent for Language-Guided Spatial Retrieval in AR [8.295391485284298]
  We present a modular augmented reality (AR) agent system that integrates multimodal large language models (MLLMs) with grounded vision models.<n>Our adaptive task agent coordinates MLLMs and coordinate-aware perception tools to address varying query complexities.<n>The system guides human attention to information-dense areas while supporting human-in-the-loop refinement.
  arXiv  Detail & Related papers  (2025-11-29T03:29:15Z)
• Executable Analytic Concepts as the Missing Link Between VLM Insight and Precise Manipulation [70.8381970762877]
  Vision-Language Models (VLMs) have demonstrated remarkable capabilities in semantic reasoning and task planning.<n>We introduce GRACE, a novel framework that grounds VLM-based reasoning through executable analytic concepts.<n>G GRACE provides a unified and interpretable interface between high-level instruction understanding and low-level robot control.
  arXiv  Detail & Related papers  (2025-10-09T09:08:33Z)
• Breaking Down and Building Up: Mixture of Skill-Based Vision-and-Language Navigation Agents [43.5771856761934]
  Vision-and-Language Navigation (VLN) poses significant challenges for agents to interpret natural language instructions and navigate complex 3D environments.<n>We propose SkillNav, a modular framework that introduces structured, skill-based reasoning into Transformer-based VLN agents.
  arXiv  Detail & Related papers  (2025-08-11T05:50:30Z)
• The Synergy of LLMs & RL Unlocks Offline Learning of Generalizable Language-Conditioned Policies with Low-fidelity Data [50.544186914115045]
  TEDUO is a novel training pipeline for offline language-conditioned policy learning in symbolic environments.<n>Our approach harnesses large language models (LLMs) in a dual capacity: first, as automatization tools augmenting offline datasets with richer annotations, and second, as generalizable instruction-following agents.
  arXiv  Detail & Related papers  (2024-12-09T18:43:56Z)
• Symbolic Learning Enables Self-Evolving Agents [55.625275970720374]
  We introduce agent symbolic learning, a systematic framework that enables language agents to optimize themselves on their own. Agent symbolic learning is designed to optimize the symbolic network within language agents by mimicking two fundamental algorithms in connectionist learning. We conduct proof-of-concept experiments on both standard benchmarks and complex real-world tasks.
  arXiv  Detail & Related papers  (2024-06-26T17:59:18Z)
• tagE: Enabling an Embodied Agent to Understand Human Instructions [3.943519623674811]
  We introduce a novel system known as task and argument grounding for Embodied agents (tagE) At its core, our system employs an inventive neural network model designed to extract a series of tasks from complex task instructions expressed in natural language. Our proposed model adopts an encoder-decoder framework enriched with nested decoding to effectively extract tasks and their corresponding arguments from these intricate instructions.
  arXiv  Detail & Related papers  (2023-10-24T08:17:48Z)
• Embodied Task Planning with Large Language Models [86.63533340293361]
  We propose a TAsk Planing Agent (TaPA) in embodied tasks for grounded planning with physical scene constraint. During inference, we discover the objects in the scene by extending open-vocabulary object detectors to multi-view RGB images collected in different achievable locations. Experimental results show that the generated plan from our TaPA framework can achieve higher success rate than LLaVA and GPT-3.5 by a sizable margin.
  arXiv  Detail & Related papers  (2023-07-04T17:58:25Z)
• Goal Representations for Instruction Following: A Semi-Supervised Language Interface to Control [58.06223121654735]
  We show a method that taps into joint image- and goal- conditioned policies with language using only a small amount of language data. Our method achieves robust performance in the real world by learning an embedding from the labeled data that aligns language not to the goal image. We show instruction following across a variety of manipulation tasks in different scenes, with generalization to language instructions outside of the labeled data.
  arXiv  Detail & Related papers  (2023-06-30T20:09:39Z)
• Simple Embodied Language Learning as a Byproduct of Meta-Reinforcement Learning [56.07190845063208]
  We ask: can embodied reinforcement learning (RL) agents indirectly learn language from non-language tasks? We design an office navigation environment, where the agent's goal is to find a particular office, and office locations differ in different buildings (i.e., tasks) We find RL agents indeed are able to indirectly learn language. Agents trained with current meta-RL algorithms successfully generalize to reading floor plans with held-out layouts and language phrases.
  arXiv  Detail & Related papers  (2023-06-14T09:48:48Z)
• Grounded Decoding: Guiding Text Generation with Grounded Models for Embodied Agents [111.15288256221764]
  Grounded-decoding project aims to solve complex, long-horizon tasks in a robotic setting by leveraging the knowledge of both models. We frame this as a problem similar to probabilistic filtering: decode a sequence that both has high probability under the language model and high probability under a set of grounded model objectives. We demonstrate how such grounded models can be obtained across three simulation and real-world domains, and that the proposed decoding strategy is able to solve complex, long-horizon tasks in a robotic setting by leveraging the knowledge of both models.
  arXiv  Detail & Related papers  (2023-03-01T22:58:50Z)
• Differentiable Parsing and Visual Grounding of Verbal Instructions for Object Placement [26.74189486483276]
  We introduce ParaGon, a PARsing And visual GrOuNding framework for language-conditioned object placement. It parses language instructions into relations between objects and grounds those objects in visual scenes. ParaGon encodes all of those procedures into neural networks for end-to-end training.
  arXiv  Detail & Related papers  (2022-10-01T07:36:51Z)
• Compositional Generalization in Grounded Language Learning via Induced Model Sparsity [81.38804205212425]
  We consider simple language-conditioned navigation problems in a grid world environment with disentangled observations. We design an agent that encourages sparse correlations between words in the instruction and attributes of objects, composing them together to find the goal. Our agent maintains a high level of performance on goals containing novel combinations of properties even when learning from a handful of demonstrations.
  arXiv  Detail & Related papers  (2022-07-06T08:46:27Z)
• Sim-To-Real Transfer of Visual Grounding for Human-Aided Ambiguity Resolution [0.0]
  We consider the task of visual grounding, where the agent segments an object from a crowded scene given a natural language description. Modern holistic approaches to visual grounding usually ignore language structure and struggle to cover generic domains. We introduce a fully decoupled modular framework for compositional visual grounding of entities, attributes, and spatial relations.
  arXiv  Detail & Related papers  (2022-05-24T14:12:32Z)
• Do As I Can, Not As I Say: Grounding Language in Robotic Affordances [119.29555551279155]
  Large language models can encode a wealth of semantic knowledge about the world. Such knowledge could be extremely useful to robots aiming to act upon high-level, temporally extended instructions expressed in natural language. We show how low-level skills can be combined with large language models so that the language model provides high-level knowledge about the procedures for performing complex and temporally-extended instructions.
  arXiv  Detail & Related papers  (2022-04-04T17:57:11Z)
• Learning Language-Conditioned Robot Behavior from Offline Data and Crowd-Sourced Annotation [80.29069988090912]
  We study the problem of learning a range of vision-based manipulation tasks from a large offline dataset of robot interaction. We propose to leverage offline robot datasets with crowd-sourced natural language labels. We find that our approach outperforms both goal-image specifications and language conditioned imitation techniques by more than 25%.
  arXiv  Detail & Related papers  (2021-09-02T17:42:13Z)
• Language in a (Search) Box: Grounding Language Learning in Real-World Human-Machine Interaction [4.137464623395377]
  We show how a grounding domain, a denotation function and a composition function are learned from user data only. We benchmark our grounded semantics on compositionality and zero-shot inference tasks.
  arXiv  Detail & Related papers  (2021-04-18T15:03:16Z)
• Vokenization: Improving Language Understanding with Contextualized, Visual-Grounded Supervision [110.66085917826648]
  We develop a technique that extrapolates multimodal alignments to language-only data by contextually mapping language tokens to their related images. "vokenization" is trained on relatively small image captioning datasets and we then apply it to generate vokens for large language corpora. Trained with these contextually generated vokens, our visually-supervised language models show consistent improvements over self-supervised alternatives on multiple pure-language tasks.
  arXiv  Detail & Related papers  (2020-10-14T02:11:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.