# GroundAct: Can LLM Agents Ground Actions in Environmental States?

arXiv: https://arxiv.org/abs/2508.05614 · HTML: https://mlsanity.com/paper/2508.05614/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 14 of its 25 references that are in the map.
- First posted on arXiv 7 Aug 2025.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 14 of 14)

- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [ALFWorld: Aligning Text and Embodied Environments for Interactive Learning](https://mlsanity.com/paper/2010.03768/) (2020)
- [WizardLM: Empowering large pre-trained language models to follow complex instructions](https://mlsanity.com/paper/2304.12244/) (2023)
- [ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks](https://mlsanity.com/paper/1912.01734/) (2019)
- [Group-in-Group Policy Optimization for LLM Agent Training](https://mlsanity.com/paper/2505.10978/) (2025)
- [DataComp-LM: In search of the next generation of training sets for language models](https://mlsanity.com/paper/2406.11794/) (2024)
- [TextWorld: A Learning Environment for Text-based Games](https://mlsanity.com/paper/1806.11532/) (2018)
- [Machine Theory of Mind](https://mlsanity.com/paper/1802.07740/) (2018)
- [EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents](https://mlsanity.com/paper/2502.09560/) (2025)
- [TaskBench: Benchmarking Large Language Models for Task Automation](https://mlsanity.com/paper/2311.18760/) (2023)
- [ViewSpatial-Bench: Evaluating Multi-perspective Spatial Localization in Vision-Language Models](https://mlsanity.com/paper/2505.21500/) (2025)
- [PARTNR: A Benchmark for Planning and Reasoning in Embodied Multi-agent Tasks](https://mlsanity.com/paper/2411.00081/) (2024)
- [Counting to Explore and Generalize in Text-based Games](https://mlsanity.com/paper/1806.11525/) (2018)

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

- [Milestone-Guided Policy Learning for Long-Horizon Language Agents](https://mlsanity.com/paper/2605.06078/) (2026)
- [Perceive-to-Reason: Decoupling Perception and Reasoning for Fine-Grained Visual Reasoning](https://mlsanity.com/paper/2607.01191/) (2026)

## Abstract (arXiv)

LLM agents achieve 85-96% success on tasks where instructions fully specify the action, but drop to 29-53% when action feasibility depends on environmental state that the instruction does not mention. We argue that this gap reflects a missing capability: action grounding, the ability to infer from structured environmental state whether an action is feasible, what prerequisites it lacks, and whether it exceeds individual capacity. We introduce GroundAct, a benchmark of 1,500 scenarios and 16,592 task instances in text-based interactive environments spanning 11 domains, with tasks organized into seven categories along a cognitive complexity hierarchy. Evaluating 15 LLMs (3B-671B), we find three diagnostic patterns: (i) attribute reasoning is weakly correlated with tool and coordination reasoning, producing distinct model profiles; (ii) complete environment graphs yield up to +27.6/-22.9% on tool use vs. implicit collaboration, separating search-bound from constraint-filtering bottlenecks; and (iii) supervised fine-tuning lifts Qwen2.5-3B from 0.6% to 76.3% on direct command but only 1.5% to 5.5% on implicit collaboration. These results establish action grounding as a multi-dimensional challenge irreducible to scaling.