Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

The Provenance Paradox in Multi-Agent LLM Routing: Delegation Contracts and Attested Identity in LDP

Sunil Prakash

Abstract

Multi-agent LLM systems delegate tasks across trust boundaries, but current protocols do not govern delegation under unverifiable quality claims. We show that when delegates can inflate self-reported quality scores, quality-based routing produces a provenance paradox: it systematically selects the worst delegates, performing worse than random. We extend the LLM Delegate Protocol (LDP) with delegation contracts that bound authority through explicit objectives, budgets, and failure policies; a claimed-vs-attested identity model that distinguishes self-reported from verified quality; and typed failure semantics enabling automated recovery. In controlled experiments with 10 simulated delegates and validated with real Claude models, routing by self-claimed quality scores performs worse than random selection (simulated: 0.55 vs. 0.68; real models: 8.90 vs. 9.30), while attested routing achieves near-optimal performance (d = 9.51, p < 0.001). Sensitivity analysis across 36 configurations confirms the paradox emerges reliably when dishonest delegates are present. All extensions are backward-compatible with sub-microsecond validation overhead.

The Provenance Paradox in Multi-Agent LLM Routing: Delegation Contracts and Attested Identity in LDP

Abstract

Multi-agent LLM systems delegate tasks across trust boundaries, but current protocols do not govern delegation under unverifiable quality claims. We show that when delegates can inflate self-reported quality scores, quality-based routing produces a provenance paradox: it systematically selects the worst delegates, performing worse than random. We extend the LLM Delegate Protocol (LDP) with delegation contracts that bound authority through explicit objectives, budgets, and failure policies; a claimed-vs-attested identity model that distinguishes self-reported from verified quality; and typed failure semantics enabling automated recovery. In controlled experiments with 10 simulated delegates and validated with real Claude models, routing by self-claimed quality scores performs worse than random selection (simulated: 0.55 vs. 0.68; real models: 8.90 vs. 9.30), while attested routing achieves near-optimal performance (d = 9.51, p < 0.001). Sensitivity analysis across 36 configurations confirms the paradox emerges reliably when dishonest delegates are present. All extensions are backward-compatible with sub-microsecond validation overhead.
Paper Structure (21 sections, 1 theorem, 5 figures, 3 tables)

This paper contains 21 sections, 1 theorem, 5 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Relationship to Prior Work
  3. Background and Motivation
  4. Layer 1: Communication and Routing
  5. Layer 2: Delegation Needs Explicit Expectations
  6. Layer 3: Self-Claims Create Manipulable Routing
  7. Protocol Extensions
  8. Delegation Contracts
  9. Claimed vs. Attested Identity
  10. Typed Failure Semantics
  11. Verification Status and Lineage
  12. Implementation
  13. Evaluation
  14. The Provenance Paradox
  15. E3: Simulated Routing Experiment
  16. ...and 6 more sections

Key Result

Proposition 1

In routing regimes that monotonically prefer reported quality, strategic inflation of self-reported scores can produce misallocation severe enough to underperform uninformed (random) routing.

Figures (5)

  • Figure 1: Trust model for quality claims. Routers weight claims by attestation level---filtering out self_claimed scores eliminates the provenance paradox.
  • Figure 2: Delegation lifecycle: contract submission, execution, client-side validation, and branching failure policy (fail_closed vs. fail_open).
  • Figure 3: Simulated routing results. (a) Self-claimed routing is worse than random; attested achieves near-optimal. (b) Only attested routing selects the best delegate. $^{***}p < 0.001$.
  • Figure 4: Output quality vs. dishonest delegate fraction (pool size 10, medium inflation). The shaded region marks the "paradox zone" where self-claimed routing underperforms random.
  • Figure 5: Protocol overhead. Message-level overhead is noticeable; workload-level overhead is negligible.

Theorems & Definitions (1)

  • Proposition 1: Routing under strategic inflation