MAP: A Map-then-Act Paradigm for Long-Horizon Interactive Agent Reasoning
Summary
The paper proposes the Map-then-Act Paradigm (MAP), a plug-and-play framework that shifts environmental understanding before execution in interactive LLM agents, achieving consistent gains across benchmarks and enabling frontier models to surpass near-zero baseline performance in 22 of 25 game environments.
View Cached Full Text
Cached at: 05/14/26, 04:16 AM
Paper page - MAP: A Map-then-Act Paradigm for Long-Horizon Interactive Agent Reasoning
Source: https://huggingface.co/papers/2605.13037
Abstract
Interactive LLM agents suffer from delayed environmental perception and epistemic bottlenecks due to reactive understanding during execution, which the proposed Map-then-Act Paradigm (MAP) addresses by acquiring environmental knowledge beforehand through global exploration, task-specific mapping, and knowledge-augmented execution.
Current interactive LLM agents rely ongoal-conditioned stepwise planning, whereenvironmental understandingis acquired reactively during execution rather than established beforehand. This temporal inversion leads to Delayed Environmental Perception: agents must infer environmental constraints throughtrial-and-error, resulting in anEpistemic Bottleneckthat traps them in inefficient failure cycles. Inspired by humanaffordance perceptionandcognitive map theory, we propose theMap-then-Act Paradigm(MAP), a plug-and-play framework that shifts environment understanding before execution. MAP consists of three stages: (1)Global Exploration, acquiring environment-general priors; (2)Task-Specific Mapping, constructing a structured cognitive map; and (3)Knowledge-Augmented Execution, solving tasks grounded on the map. Experiments show consistent gains across benchmarks and LLMs. OnARC-AGI-3, MAP enables frontier models to surpass near-zero baseline performance in 22 of 25 game environments. We further introduceMAP-2K, a dataset of map-then-act trajectories, and show that training on it outperforms expert execution traces, suggesting that understanding environments is more fundamental than imitation.
View arXiv pageView PDFAdd to collection
Get this paper in your agent:
hf papers read 2605\.13037
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2605.13037 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2605.13037 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2605.13037 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes
SpatialAct is a new simulator-grounded benchmark that probes whether VLM agents can perform coherent spatial reasoning and translate it into actions in 3D environments across multi-turn feedback settings. Experiments reveal a significant reasoning-to-action gap, with current VLMs struggling to maintain spatial beliefs and produce reliable actions despite performing well on isolated reasoning tasks.
MapSatisfyBench: Benchmarking Satisfaction-Aware Map Agents through Behavior-Grounded Implicit Decision Factors
MapSatisfyBench is a benchmark for evaluating LLM-based map agents on their ability to recover implicit decision factors from underspecified user queries, shifting evaluation from task completion to satisfaction-aware spatial decision making.
M-Plan: Comprehensive Planning For LLM Agents with Memory Arrangement
M-Plan is a closed-loop multi-agent system framework that integrates long-term and short-term memory with global-local and past-current guidance to improve LLM agents' planning on long-horizon multi-turn tasks, outperforming baselines on ALFWorld, Webshop, and PDDL.
Reason--Imagine--Act: Closed-Loop LLM Decision Making with World Models for Autonomous Driving
Proposes Reason-Imagine-Act (RIA), a closed-loop framework coupling an LLM reasoner with an action-conditioned world model for online safety verification in autonomous driving, achieving 80.05% route completion and 0.20% collision rate in CARLA simulations.
Learning What to Investigate Next: Meta-Reasoning for Long-Horizon Research Agents
The paper introduces MIRA, a hierarchical meta-reasoning architecture for long-horizon research agents that separates research allocation from execution, and MIRA-AC, a generative actor-critic that learns credit assignment at meta-reasoning decision boundaries, improving theorem proving and neural architecture research.