Pith Number

pith:OOTG6RML

pith:2023:OOTG6RMLL2REHAMBULK2MI2LLR

not attested not anchored not stored refs resolved

ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models

Binfeng Xu, Bowen Lei, Dongkuan Xu, Subhabrata Mukherjee, Yuchen Liu, Zhiyuan Peng

ReWOO generates a full reasoning plan without tool observations first, then executes it in one pass to cut token use and allow smaller models.

arxiv:2305.18323 v1 · 2023-05-23 · cs.CL · 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{OOTG6RMLL2REHAMBULK2MI2LLR}

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

ReWOO achieves 5x token efficiency and 4% accuracy improvement on HotpotQA, a multi-step reasoning benchmark, while demonstrating robustness under tool-failure scenarios and enabling offloading from 175B GPT-3.5 to 7B LLaMA.

C2weakest assumption

That a complete reasoning plan can be generated without any intermediate observations and that the subsequent single-pass execution of that plan will not lose critical information that interleaved observation would have supplied.

C3one line summary

ReWOO decouples reasoning from tool observations in augmented language models, delivering 5x token efficiency and 4% higher accuracy on multi-step reasoning benchmarks like HotpotQA.

References

42 extracted · 42 resolved · 22 Pith anchors

[1] Re- act: Synergizing reasoning and acting in language models 2023

[2] Augmented Language Models: a Survey 2023 · arXiv:2302.07842

[3] MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action 2023 · arXiv:2303.11381

[4] Taskmatrix.ai: Completing tasks by connecting foundation models with millions of apis.CoRR, abs/2303.16434, 2023 2023

[5] Tool Learning with Foundation Models 2023 · arXiv:2304.08354

Formal links

2 machine-checked theorem links

Cited by

24 papers in Pith

Boiling the Frog: A Multi-Turn Benchmark for Agentic Safety

LightZeroNav: Zero-Shot Vision Language Navigation in Continuous Environments Based on Lightweight VLMs

Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning

Agentic Reasoning for Large Language Models

Receipt and verification

First computed	2026-05-17T23:38:50.613007Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

73a66f458b5ea2438181a2d5a6234b5c4bbef388b05e43be9fb234259ae18057

Aliases

arxiv: 2305.18323 · arxiv_version: 2305.18323v1 · doi: 10.48550/arxiv.2305.18323 · pith_short_12: OOTG6RMLL2RE · pith_short_16: OOTG6RMLL2REHAMB · pith_short_8: OOTG6RML

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/OOTG6RMLL2REHAMBULK2MI2LLR \
  | 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: 73a66f458b5ea2438181a2d5a6234b5c4bbef388b05e43be9fb234259ae18057

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "193e6f09e2644cec02a9e77ddb4091d644eaf7f58e767c39fdc2edc780d07adf",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2023-05-23T00:16:48Z",
    "title_canon_sha256": "7cf452402aab2a45866e90c3750c1eabc04228f07ac43ef524016392fc4646c3"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2305.18323",
    "kind": "arxiv",
    "version": 1
  }
}