# Mind the Gap Between Spatial Reasoning and Acting! Step-by-Step Evaluation of Agents With Spatial-Gym

arXiv: https://arxiv.org/abs/2604.09338 · HTML: https://mlsanity.com/paper/2604.09338/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 40 of its 70 references that are in the map.
- First posted on arXiv 10 Apr 2026.

## Placed in

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

## Builds on (most cited first, 30 of 40)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [AgentBench: Evaluating LLMs as Agents](https://mlsanity.com/paper/2308.03688/) (2023)
- [LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models](https://mlsanity.com/paper/2212.04088/) (2022)
- [RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning](https://mlsanity.com/paper/2504.20073/) (2025)
- [Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks](https://mlsanity.com/paper/1502.05698/) (2015)
- [To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning](https://mlsanity.com/paper/2409.12183/) (2024)
- [ZebraLogic: On the Scaling Limits of LLMs for Logical Reasoning](https://mlsanity.com/paper/2502.01100/) (2025)
- [A Careful Examination of Large Language Model Performance on Grade School Arithmetic](https://mlsanity.com/paper/2405.00332/) (2024)
- [LLMs Can't Plan, But Can Help Planning in LLM-Modulo Frameworks](https://mlsanity.com/paper/2402.01817/) (2024)
- [REASONING GYM: Reasoning Environments for Reinforcement Learning with Verifiable Rewards](https://mlsanity.com/paper/2505.24760/) (2025)
- [ARC Prize 2024: Technical Report](https://mlsanity.com/paper/2412.04604/) (2024)
- [SpartQA: : A Textual Question Answering Benchmark for Spatial Reasoning](https://mlsanity.com/paper/2104.05832/) (2021)
- [StepGame: A New Benchmark for Robust Multi-Hop Spatial Reasoning in Texts](https://mlsanity.com/paper/2204.08292/) (2022)
- [NVIDIA Nemotron 3: Efficient and Open Intelligence](https://mlsanity.com/paper/2512.20856/) (2025)
- [Magistral](https://mlsanity.com/paper/2506.10910/) (2025)
- [Voting or Consensus? Decision-Making in Multi-Agent Debate](https://mlsanity.com/paper/2502.19130/) (2025)
- [VisualPuzzles: Decoupling Multimodal Reasoning Evaluation from Domain Knowledge](https://mlsanity.com/paper/2504.10342/) (2025)
- [Can Large Language Models be Good Path Planners? A Benchmark and Investigation on Spatial-temporal Reasoning](https://mlsanity.com/paper/2310.03249/) (2023)
- [ARC-AGI-3: A New Challenge for Frontier Agentic Intelligence](https://mlsanity.com/paper/2603.24621/) (2026)
- [AlphaMaze: Enhancing Large Language Models' Spatial Intelligence via GRPO](https://mlsanity.com/paper/2502.14669/) (2025)
- [To Backtrack or Not to Backtrack: When Sequential Search Limits Model Reasoning](https://mlsanity.com/paper/2504.07052/) (2025)
- [AI Usage Cards: Responsibly Reporting AI-generated Content](https://mlsanity.com/paper/2303.03886/) (2023)

## Built on by (most cited first, 1 of 1)

- [Multi-Agent Reasoning Improves Compute Efficiency: Pareto-Optimal Test-Time Scaling](https://mlsanity.com/paper/2605.01566/) (2026)

## Abstract (arXiv)

Spatial reasoning is central to navigation and robotics, yet measuring model capabilities on these tasks remains difficult. Existing benchmarks evaluate models in a one-shot setting, requiring full solution generation in a single response, unlike humans, who work in interactive environments step-by-step. We introduce Spatial-Gym, a Gymnasium environment that isolates spatial constraint reasoning by testing pathfinding in 2D-grid puzzles as a sequential decision task with optional backtracking. We evaluate eight models in three settings (one-shot, step-by-step, step-by-step with backtracking) against human, random, and A* baselines on 500 episodes. The best model, GPT-OSS 120B, achieves a solve rate of 16.0%, 82 points below the human baseline (98.0%). Step-by-step format helps weaker models (up to +5.4%) by removing formatting errors, but hurts stronger models (up to 5.6%) by constraining global planning. Backtracking improves episode completion, but increases solve rate only for weaker models; stronger models rarely backtrack and do not benefit from it. Our experiments have three key findings: (1) models fail to scale reasoning effort with difficulty, (2) vision models receiving images of the spatial environment reduce solve rate by 73%, and (3) extended chain-of-thought reasoning retains a 3-5x accuracy advantage over standard inference even in the step-by-step setting. Spatial-Gym enables diagnosis of model limitations and provides a framework for improving spatial reasoning through reinforcement learning.