pith. sign in
Pith Number

pith:G7KHTIPU

pith:2026:G7KHTIPU23J2YBK7TP6AYSW5OD
not attested not anchored not stored refs resolved

EcoGEO: Trajectory-Aware Evidence Ecosystems for Web-Enabled LLM Search Agents

Hengwei Ye, Jiasheng Mao, Zheng Tian, Zhenhan Guan

Coordinating linked webpages into a consistent evidence ecosystem steers web-enabled LLM agents toward specific recommendations more reliably than optimizing any single page.

arxiv:2605.12887 v1 · 2026-05-13 · cs.IR · cs.AI

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{G7KHTIPU23J2YBK7TP6AYSW5OD}

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

Experiments show that it consistently outperforms page-level GEO baselines in final target recommendation. Trajectory-level metrics further show increased initial target-result crawls, target-specific follow-up searches, and internal-link crawls, suggesting that the gains come from shaping the agent's evidence-acquisition process rather than merely adding more target-related content.

C2weakest assumption

That the controlled evidence environment built by TRACE and the OPR-Bench benchmark accurately reflect real-world web-enabled LLM agent trajectories and that outperformance in this setup will generalize beyond the fictional target product scenario.

C3one line summary

EcoGEO reframes GEO as an ecosystem-level problem and introduces TRACE, a method that coordinates linked evidence pages to increase LLM agents' target product recommendations on OPR-Bench beyond page-level baselines.

References

13 extracted · 13 resolved · 0 Pith anchors

[1] Lisa Schilhan, Christian Kaier, and Karin Lackner 2021 · doi:10.1353/scp.0.0082
[2] It is only a bare product keyword, an overly broad product-category request, or an extremely vague product query without clear recommendation intent
[3] It restricts results to specific dates or websites
[4] It asks for ingredients, supplements, therapies, biologics, compounds, or other non-product compo- nents
[5] It asks for methods, treatments, remedies, strategies, or approaches rather than purchasable products

Formal links

2 machine-checked theorem links

Receipt and verification
First computed 2026-05-18T03:09:10.955301Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

37d479a1f4d6d3ac055f9bfc0c4add70d09a965dc407fea73827dc8e46fd518c

Aliases

arxiv: 2605.12887 · arxiv_version: 2605.12887v1 · doi: 10.48550/arxiv.2605.12887 · pith_short_12: G7KHTIPU23J2 · pith_short_16: G7KHTIPU23J2YBK7 · pith_short_8: G7KHTIPU
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/G7KHTIPU23J2YBK7TP6AYSW5OD \
  | 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: 37d479a1f4d6d3ac055f9bfc0c4add70d09a965dc407fea73827dc8e46fd518c
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "9f191df986775903fddac7bbad198044d4cbcbd01edb712bb1dc7aff1540df04",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.IR",
    "submitted_at": "2026-05-13T02:03:18Z",
    "title_canon_sha256": "e51cf756c3de3d9c4cf8e3a820be603ffc1e1462e21d456b63537ca0a0ab2b37"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.12887",
    "kind": "arxiv",
    "version": 1
  }
}