Pith Number

pith:EYGETUQ3

pith:2026:EYGETUQ36HEDM3ITQT66ERFYH5

not attested not anchored not stored refs pending

Terminus-4B: Can a Smaller Model Replace Frontier LLMs at Agentic Execution Tasks?

Spandan Garg, Vikram Nitin, Yufan Huang

A 4B model can match frontier LLMs at agentic terminal execution tasks

arxiv:2605.03195 v2 · 2026-05-04 · cs.AI · cs.SE

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{EYGETUQ36HEDM3ITQT66ERFYH5}

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

Terminus-4B is able to reduce the token usage of the main agent by up to ~30% compared to the No Subagent baseline with no impact to agent performance on benchmarks like SWE-Bench Pro and our internal SWE-Bench C# benchmark... Furthermore, Terminus-4B improves key metrics showing the main agent relying on the outputs of the subagent and doing fewer terminal execution tasks by itself. We see that our model not only closes the gap between the Vanilla Qwen model and frontier models like Claude Sonnet / Opus / GPT-5.3-Codex, but often even exceeds their performance.

C2weakest assumption

That the rubric-based LLM-as-judge reward produces training signals that generalize beyond the specific benchmarks and do not embed biases from the judge model itself.

C3one line summary

A fine-tuned 4B model matches or exceeds frontier LLMs in terminal execution subagent tasks for coding agents, reducing main agent token usage by 30% with no performance loss.

Formal links

2 machine-checked theorem links

Cited by

1 paper in Pith

Think Big, Search Small: Where Capacity Matters in Hierarchical Search Agents?

Receipt and verification

First computed	2026-07-09T00:19:14.001205Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

260c49d21bf1c8366d1384fde244b83f60daf6bc5e7c31f4090949de478dc2c6

Aliases

arxiv: 2605.03195 · arxiv_version: 2605.03195v2 · doi: 10.48550/arxiv.2605.03195 · pith_short_12: EYGETUQ36HED · pith_short_16: EYGETUQ36HEDM3IT · pith_short_8: EYGETUQ3

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/EYGETUQ36HEDM3ITQT66ERFYH5 \
  | 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: 260c49d21bf1c8366d1384fde244b83f60daf6bc5e7c31f4090949de478dc2c6

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "a160c8cbab67bd12133a831288435df182caf357b5934e2c8b64a41a4d856371",
    "cross_cats_sorted": [
      "cs.SE"
    ],
    "license": "http://creativecommons.org/licenses/by-nc-nd/4.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-05-04T22:24:24Z",
    "title_canon_sha256": "56f945d5cd08749c7fd37a09ea400d0fdaedbf6db6dddc849eb9664f373dd95c"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.03195",
    "kind": "arxiv",
    "version": 2
  }
}