Pith Number

pith:QIQWH6BY

pith:2024:QIQWH6BYM5BQKFXEQ4BE4XQO2H

not attested not anchored not stored refs resolved

Agent Workflow Memory

Daniel Fried, Graham Neubig, Jiayuan Mao, Zora Zhiruo Wang

Agent Workflow Memory extracts reusable task routines from past examples to guide language model agents on new web navigation tasks.

arxiv:2409.07429 v1 · 2024-09-11 · cs.CL

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{QIQWH6BYM5BQKFXEQ4BE4XQO2H}

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

AWM substantially improves the baseline results by 24.6% and 51.1% relative success rate on Mind2Web and WebArena while reducing the number of steps taken to solve WebArena tasks successfully. Furthermore, online AWM robustly generalizes in cross-task, website, and domain evaluations.

C2weakest assumption

That workflows induced from past examples can be reliably identified as reusable and selectively provided without introducing noise or incorrect guidance that harms the agent's generation process on new queries.

C3one line summary

AWM induces reusable workflows from agent experiences and provides them selectively to improve success rates by 24.6% on Mind2Web and 51.1% on WebArena while reducing steps taken.

References

53 extracted · 53 resolved · 2 Pith anchors

[1] Proceedings of the 34th International Conference on Machine Learning , pages= 2017

[2] International Conference on Learning Representations , year=

[3] WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents , url=

[4] The Twelfth International Conference on Learning Representations , year=

[5] Thirty-seventh Conference on Neural Information Processing Systems Datasets and Benchmarks Track , year=

Formal links

3 machine-checked theorem links

Cited by

40 papers in Pith

Ratchet: A Minimal Hygiene Recipe for Self-Evolving LLM Agents

Auto-Dreamer: Learning Offline Memory Consolidation for Language Agents

Evaluating Temporal Semantic Caching and Workflow Optimization in Agentic Plan-Execute Pipelines

A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications

Dynamic Skill Lifecycle Management for Agentic Reinforcement Learning

Receipt and verification

First computed	2026-05-17T23:39:05.201050Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

822163f83867430516e487024e5e0ed1c0adc8371db017172de12240604399e5

Aliases

arxiv: 2409.07429 · arxiv_version: 2409.07429v1 · doi: 10.48550/arxiv.2409.07429 · pith_short_12: QIQWH6BYM5BQ · pith_short_16: QIQWH6BYM5BQKFXE · pith_short_8: QIQWH6BY

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/QIQWH6BYM5BQKFXEQ4BE4XQO2H \
  | 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: 822163f83867430516e487024e5e0ed1c0adc8371db017172de12240604399e5

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "02578bfa6f47c678462ed2526ac1a460eaaee929b86309a493c3c5ee9dd69693",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by-sa/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2024-09-11T17:21:00Z",
    "title_canon_sha256": "2334de0b5de562250b0177cc3d3d15e4cf31b9170e0a5fd37f50f018fb48121f"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2409.07429",
    "kind": "arxiv",
    "version": 1
  }
}