Pith Number

pith:GDI64H2A

pith:2026:GDI64H2ASOLEVCX32BMVPM23EB

not attested not anchored not stored refs resolved

MAP: A Map-then-Act Paradigm for Long-Horizon Interactive Agent Reasoning

Jinwei Xiao, Lei Zhang, Mingye Zhu, Qi Gu, Xunliang Cai, Yueqing Sun, Yuxin Liu, Zhuowen Han, Ziang Ye

The Map-then-Act Paradigm lets LLM agents build environment maps before execution to escape trial-and-error cycles.

arxiv:2605.13037 v1 · 2026-05-13 · cs.AI

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{GDI64H2ASOLEVCX32BMVPM23EB}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

On ARC-AGI-3, MAP enables frontier models to surpass near-zero baseline performance in 22 of 25 game environments. We further introduce MAP-2K, a dataset of map-then-act trajectories, and show that training on it outperforms expert execution traces.

C2weakest assumption

That global exploration can efficiently acquire accurate environment-general priors and that the resulting structured cognitive map will remain valid and useful during subsequent task execution without introducing new errors or excessive overhead.

C3one line summary

MAP improves LLM agent reasoning by constructing a structured cognitive map of the environment before task execution, yielding performance gains on benchmarks like ARC-AGI-3 and superior training data via the new MAP-2K dataset.

References

50 extracted · 50 resolved · 18 Pith anchors

[1] GPT-4 Technical Report 2023 · arXiv:2303.08774

[2] Self-rag: Learn- ing to retrieve, generate, and critique through self-reflection 2023

[3] Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolution 2025 · arXiv:2512.10696

[4] MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention 2025 · arXiv:2506.13585

[5] Learning to self-verify makes language models better reasoners.CoRR, abs/2602.07594 2026

Receipt and verification

First computed	2026-05-18T03:08:59.620200Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

30d1ee1f4093964a8afbd05957b35b205aea96bbffb1c9c78d30e96b5a2940fc

Aliases

arxiv: 2605.13037 · arxiv_version: 2605.13037v1 · doi: 10.48550/arxiv.2605.13037 · pith_short_12: GDI64H2ASOLE · pith_short_16: GDI64H2ASOLEVCX3 · pith_short_8: GDI64H2A

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/GDI64H2ASOLEVCX32BMVPM23EB \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 30d1ee1f4093964a8afbd05957b35b205aea96bbffb1c9c78d30e96b5a2940fc

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "5bde62e90ba08e809701597ea224f4219739e38baecbbf8ce3e4b49c1f13d497",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-05-13T05:46:29Z",
    "title_canon_sha256": "d87452eb6514a3c74ed0d9eb5d6ed03a7e72653d7cecd600adad4f3300cf5a2f"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13037",
    "kind": "arxiv",
    "version": 1
  }
}