The Provenance Paradox in Multi-Agent LLM Routing: Delegation Contracts and Attested Identity in LDP
Fuente:
arXiv
Gespeichert in:
| 1. Verfasser: | |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908899609673728 |
|---|---|
| author | Prakash, Sunil |
| author_facet | Prakash, Sunil |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_18043 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | The Provenance Paradox in Multi-Agent LLM Routing: Delegation Contracts and Attested Identity in LDP Prakash, Sunil Multiagent Systems Artificial Intelligence 68T42 I.2.11 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. |
| title | The Provenance Paradox in Multi-Agent LLM Routing: Delegation Contracts and Attested Identity in LDP |
| topic | Multiagent Systems Artificial Intelligence 68T42 I.2.11 |
| url | https://arxiv.org/abs/2603.18043 |