Pith Number

pith:WPYOEUJU

pith:2026:WPYOEUJUCS3Y3LBJVJUDLPDCP7

not attested not anchored not stored refs resolved

AgentStop: Terminating Local AI Agents Early to Save Energy in Consumer Devices

Ali Shahin Shamsabadi, Dzung Pham, Hamed Haddadi, Kleomenis Katevas

Local LLM agents can stop themselves early using token log probabilities to cut wasted energy by 15-20% on consumer devices.

arxiv:2605.15206 v1 · 2026-05-01 · cs.LG · cs.AI · cs.DC

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{WPYOEUJUCS3Y3LBJVJUDLPDCP7}

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

Leveraging low-cost execution signals such as token-level log probabilities, AgentStop can reduce wasted energy by 15-20% with minimal impact on task performance (<5% utility drop) for challenging web-based question answering and coding benchmarks.

C2weakest assumption

That token-level log probabilities and similar low-cost signals during execution are sufficiently predictive of ultimate task failure to allow early termination without introducing many harmful false positives that degrade overall utility.

C3one line summary

AgentStop uses execution signals to early-terminate failing local LLM agent trajectories, cutting energy use 15-20% with minimal utility loss.

References

58 extracted · 58 resolved · 4 Pith anchors

[1] Anthropic. 2026. Claude API Pricing. https://platform.claude.com/docs/en/about- claude/pricing. Accessed: 2026-02-28 2026

[2] Small Language Models are the Future of Agentic AI 2025 · arXiv:2506.02153

[3] Why Should I Trust You? 2016

[4] Measuring the environmental impact of delivering AI at google scale 2025

[5] ggml.ai. n.d.. Llama.cpp. https://github.com/ggml-org/llama.cpp

Formal links

1 machine-checked theorem link

Receipt and verification

First computed	2026-05-20T00:00:46.051207Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

b3f0e2513414b78dac29aa6835bc627fff91fc66a8cd66f2598f3798e949479b

Aliases

arxiv: 2605.15206 · arxiv_version: 2605.15206v1 · doi: 10.48550/arxiv.2605.15206 · pith_short_12: WPYOEUJUCS3Y · pith_short_16: WPYOEUJUCS3Y3LBJ · pith_short_8: WPYOEUJU

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/WPYOEUJUCS3Y3LBJVJUDLPDCP7 \
  | 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: b3f0e2513414b78dac29aa6835bc627fff91fc66a8cd66f2598f3798e949479b

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "6dd79ec1b2806626a527bc7c0a30333a3f874b06d1dad3060f1207494846640c",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.DC"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-01T14:45:37Z",
    "title_canon_sha256": "3567ce10ea6e5489677de443cb3d2df6c721c84cf4302d53e421faa611400dd8"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.15206",
    "kind": "arxiv",
    "version": 1
  }
}