pith. sign in
Pith Number

pith:3FVYZ57R

pith:2026:3FVYZ57RV7G22DYWBAK6DFMAGM
not attested not anchored not stored refs resolved

DiscoverLLM: From Executing Intents to Discovering Them

Jaesang Yu, John Joon Young Chung, Juho Kim, Tae Soo Kim, Yoonjoo Lee

DiscoverLLM trains LLMs to help users form and discover intents they have not yet formed by modeling how those intents concretize during interaction.

arxiv:2602.03429 v2 · 2026-02-03 · cs.AI · cs.CL · cs.HC · cs.LG

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{3FVYZ57RV7G22DYWBAK6DFMAGM}

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

Across proposed interactive benchmarks in creative writing, technical writing, and SVG drawing, DiscoverLLM achieves over 10% higher task performance while reducing conversation length by up to 40%. In a user study with 75 human participants, DiscoverLLM improved conversation satisfaction and efficiency compared to baselines.

C2weakest assumption

The user simulator accurately models human cognitive state via a hierarchy of intents whose degree of concretization provides a reliable reward signal for training.

C3one line summary

DiscoverLLM introduces a hierarchical intent simulator that rewards LLMs for helping users concretize vague requests, yielding over 10% better task performance and up to 40% shorter conversations in creative writing, technical writing, and SVG drawing benchmarks plus higher satisfaction in a 75-part

References

58 extracted · 58 resolved · 0 Pith anchors

[1] Establishes m yst er y ar ound t he band name's origin
[2] 1 Establishes pr olonged m yst er y ar ound t he band name's origin
[3] includes a cat
[4] I want it to be about a cat, not a dog
[5] maybe a smaller, more domestic animal?

Cited by

4 papers in Pith

Receipt and verification
First computed 2026-05-18T02:44:31.659498Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

d96b8cf7f1afcdad0f160815e195803326acb3598b65a881fea40a5985aaf87d

Aliases

arxiv: 2602.03429 · arxiv_version: 2602.03429v2 · doi: 10.48550/arxiv.2602.03429 · pith_short_12: 3FVYZ57RV7G2 · pith_short_16: 3FVYZ57RV7G22DYW · pith_short_8: 3FVYZ57R
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/3FVYZ57RV7G22DYWBAK6DFMAGM \
  | 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: d96b8cf7f1afcdad0f160815e195803326acb3598b65a881fea40a5985aaf87d
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "f8a269b51a77612a0ff8ffb2fc51d215c6040df5440f782d95dfcf60d72ccdbd",
    "cross_cats_sorted": [
      "cs.CL",
      "cs.HC",
      "cs.LG"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-02-03T11:51:46Z",
    "title_canon_sha256": "f4faf62c6ba7142f7d7a5b0ccd3496b19dc31968042f03e6124738a030d1fb3f"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2602.03429",
    "kind": "arxiv",
    "version": 2
  }
}