Pith Number

pith:6XJMIR7Q

pith:2026:6XJMIR7QFCO3HR6R6IJLSJQCLH

not attested not anchored not stored refs resolved

PersonalAlign: Hierarchical Implicit Intent Alignment for Personalized GUI Agent with Long-Term User-Centric Records

Gongwei Chen, Liqiang Nie, Rui Shao, Weili Guan, Yibo Lyu

Hierarchical memory from long-term records lets GUI agents resolve vague instructions and anticipate routines.

arxiv:2601.09636 v2 · 2026-01-14 · cs.AI · cs.CV · cs.HC · cs.LG

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{6XJMIR7QFCO3HR6R6IJLSJQCLH}

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

HIM-Agent significantly improves both execution and proactive performance by 15.7% and 7.3% on the AndroidIntent benchmark.

C2weakest assumption

That the 20k long-term records contain stable, generalizable user preferences and routines that transfer to new vague instructions without overfitting to the 20 users in the benchmark.

C3one line summary

PersonalAlign introduces a hierarchical memory agent that uses long-term user records to resolve vague GUI instructions and provide proactive assistance, improving execution by 15.7% and proactive performance by 7.3% on the new AndroidIntent benchmark.

References

14 extracted · 14 resolved · 2 Pith anchors

[1] LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training 2025 · arXiv:2509.23661

[2] Score the steps, not just the goal: Vlm-based subgoal evaluation for robotic manipulation 2025

[3] InProceedings of the IEEE/CVF conference on com- puter vision and pattern recognition, pages 10023– 10031 2023

[4] Advances in Neural Information Processing Systems, 37:52040–52094 2025

[5] MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent 2024 · arXiv:2507.02259

Cited by

4 papers in Pith

$\pi$-Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows

ConsisVLA-4D: Advancing Spatiotemporal Consistency in Efficient 3D-Perception and 4D-Reasoning for Robotic Manipulation

Behavior Latticing: Inferring User Motivations from Unstructured Interactions

Receipt and verification

First computed	2026-05-18T03:09:24.498273Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

f5d2c447f0289db3c7d1f212b9260259ef70cca216990a857909fb723443730a

Aliases

arxiv: 2601.09636 · arxiv_version: 2601.09636v2 · doi: 10.48550/arxiv.2601.09636 · pith_short_12: 6XJMIR7QFCO3 · pith_short_16: 6XJMIR7QFCO3HR6R · pith_short_8: 6XJMIR7Q

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/6XJMIR7QFCO3HR6R6IJLSJQCLH \
  | 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: f5d2c447f0289db3c7d1f212b9260259ef70cca216990a857909fb723443730a

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "a49193ab6edf6abbdf7bfc1b3c120b124c335870cdd3beda373b2110122397fd",
    "cross_cats_sorted": [
      "cs.CV",
      "cs.HC",
      "cs.LG"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-01-14T17:12:48Z",
    "title_canon_sha256": "727806031e13f0e4d72d9f79b386a55a2ff732d15caea0223681d8386018b105"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2601.09636",
    "kind": "arxiv",
    "version": 2
  }
}