Pith Number

pith:P3PYPFER

pith:2026:P3PYPFERJSGTVII6LVKW3ZJZQY

not attested not anchored not stored refs resolved

Latency-Quality Routing for Functionally Equivalent Tools in LLM Agents

Dawei Xiang, Kexin Chu, Wei Zhang

LQM-ContextRoute routes LLM agents to equivalent tool providers by expected answer quality per service cycle rather than additive rewards.

arxiv:2605.14241 v1 · 2026-05-14 · 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{P3PYPFERJSGTVII6LVKW3ZJZQY}

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

On the main web-search load benchmark, LQM-ContextRoute improves F1 by +2.18 pp over SW-UCB while staying on the latency-quality frontier; in high-heterogeneity StrategyQA it improves accuracy by up to +18 pp.

C2weakest assumption

That LLM-as-judge feedback provides a sufficiently reliable and unbiased signal for online adaptation without gold labels at deployment time.

C3one line summary

LQM-ContextRoute routes tool calls by expected quality per service cycle using contextual bandits and LLM-as-judge feedback, yielding +2.18 pp F1, up to +18 pp accuracy, and +2.91-3.22 pp NDCG gains over SW-UCB on web-search, StrategyQA, and retriever benchmarks.

References

25 extracted · 25 resolved · 7 Pith anchors

[1] 1966.Lectures on Functional Equations and Their Applications, volume 19 ofMathematics in Science and Engineering 1966

[2] Learning to route llms from bandit feedback 2025

[3] https://modelcontextprotocol 2026

[4] https://docs.litellm 2026

[5] Thompson Sampling contextual bandit over heterogeneous tools (PubMed, drug DBs, calculator, web) with composite reward including latency

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-17T23:39:10.652061Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

7edf8794914c8d3aa11e5d556de539861ab87e6e56d9c2d1c54fc173e7e939e5

Aliases

arxiv: 2605.14241 · arxiv_version: 2605.14241v1 · doi: 10.48550/arxiv.2605.14241 · pith_short_12: P3PYPFERJSGT · pith_short_16: P3PYPFERJSGTVII6 · pith_short_8: P3PYPFER

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/P3PYPFERJSGTVII6LVKW3ZJZQY \
  | 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: 7edf8794914c8d3aa11e5d556de539861ab87e6e56d9c2d1c54fc173e7e939e5

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "6b6e059beb8ebaf5be0d45f8ca29c91516a7f02007538bcd7d1edb1a042b33d0",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-14T01:14:13Z",
    "title_canon_sha256": "72e3c916ef91215572d0807945b610eab9e934e5001a15dbb1d7955becae2a2b"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.14241",
    "kind": "arxiv",
    "version": 1
  }
}