# Fault-Tolerant Budget Conservation in Distributed Multi-Agent Delegation

arXiv: https://arxiv.org/abs/2610.00349 · HTML: https://mlsanity.com/paper/2610.00349/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 54 references that are in the map.
- First posted on arXiv 29 Sep 2026.

## Builds on (most cited first, 25 of 25)

- [Atomix: Timely, Transactional Tool Use for Reliable Agentic Workflows](https://mlsanity.com/paper/2602.14849/) (2026)
- [Temporary Authority, Permanent Effects: Commit-Time Authorization for LLM Agents](https://mlsanity.com/paper/2607.10487/) (2026)
- [Agent Contracts: A Formal Framework for Resource-Bounded Autonomous AI Systems](https://mlsanity.com/paper/2601.08815/) (2026)
- [MAS-FIRE: Fault Injection and Reliability Evaluation for LLM-Based Multi-Agent Systems](https://mlsanity.com/paper/2602.19843/) (2026)
- [AIP: Agent Identity Protocol for Verifiable Delegation Across MCP and A2A](https://mlsanity.com/paper/2603.24775/) (2026)
- [Context-to-Execution Integrity for LLM Agents](https://mlsanity.com/paper/2607.06000/) (2026)
- [Beyond Single-Use Tokens: Durable Authorization State for Replay-Resistant LLM Agent Actions](https://mlsanity.com/paper/2608.01710/) (2026)
- [HDP: A Lightweight Cryptographic Protocol for Human Delegation Provenance in Agentic AI Systems](https://mlsanity.com/paper/2604.04522/) (2026)
- [Token Budgets: An Empirical Catalog of 63 LLM-Agent Budget-Overrun Incidents, with an Affine-Typed Rust Mitigation as a Case Study](https://mlsanity.com/paper/2606.04056/) (2026)
- [Beyond OAuth: Task-Scoped Authorization for AI Agents via Natural Language Slices](https://mlsanity.com/paper/2603.17170/) (2026)
- [Overlaying Governance: A Compositional Authorization Framework for Delegation and Scope in Agentic AI](https://mlsanity.com/paper/2606.03518/) (2026)
- [Intent-Governed Tool Authorization for AI Agents](https://mlsanity.com/paper/2606.22916/) (2026)
- [OpenPort Protocol: A Security Governance Specification for AI Agent Tool Access](https://mlsanity.com/paper/2602.20196/) (2026)
- [Where Does Exactly-Once Live? Model, Harness, and Tool-Contract Effects on Duplicate Side Effects in LLM Agents](https://mlsanity.com/paper/2609.29095/) (2026)
- [Delivery, consistency, and determinism: rethinking guarantees in distributed stream processing](https://mlsanity.com/paper/1907.06250/) (2019)
- [Aegon: Auditable AI Content Access with Ledger-Bound Tokens and Hardware-Attested Mobile Receipts](https://mlsanity.com/paper/2604.06693/) (2026)
- [MPAC: A Multi-Principal Agent Coordination Protocol for Interoperable Multi-Agent Collaboration](https://mlsanity.com/paper/2604.09744/) (2026)
- [Attacks and Mitigations for Distributed Governance of Agentic AI under Byzantine Adversaries](https://mlsanity.com/paper/2605.12364/) (2026)
- [Explanation-Bound Tool Execution for AI Agents: Server-Verified Action Claims Without Trusting Model Rationales](https://mlsanity.com/paper/2607.25364/) (2026)
- [Complete CALM: A Coordination Criterion for Specifications](https://mlsanity.com/paper/2602.09435/) (2026)
- [The Bureaucracy of Speed: Structural Equivalence Between Memory Consistency Models and Multi-Agent Authorization Revocation](https://mlsanity.com/paper/2603.09875/) (2026)
- [EpochX: Building the Infrastructure for an Emergent Agent Civilization](https://mlsanity.com/paper/2603.27304/) (2026)
- [Behavioral Governance for Autonomous AI Agents: The AgentBound Framework](https://mlsanity.com/paper/2606.30970/) (2026)
- [Machine-Checked Dual-Write Recovery from a Commit Log](https://mlsanity.com/paper/2608.00501/) (2026)
- [Versioned Transitive Dependency-Closure Binding and Operation-Time Effect Governance for Agent Skills: ClosureBound](https://mlsanity.com/paper/2609.05920/) (2026)

## Abstract (arXiv)

Resource limits are becoming an authorization boundary for AI agents that delegate work across concurrent and failure-prone workers. Parent-child allocation constraints, affine objects, and distributed escrow do not by themselves prevent overspend when replies are lost, effects complete after timeout, messages repeat, branches partition, or DAG joins alias one lineage. We formalize fault-tolerant budget conservation for distributed multi-agent delegation. Budgets are quantized resource vectors represented by exclusive escrow credits that move through a delegation DAG. Before dispatch, a branch converts credit into an operation reservation bound to lineage, epoch, normalized effect, maximum charge, receiver, and idempotency key. It persists a signed dispatch permit with quarantine; the gateway verifies that permit before first acceptance. Uncertain effects remain charged until authenticated settlement, a fenced authoritative no-effect proof, or permanent retirement. We prove ownership partition, ledger and effect conservation, descendant non-amplification, at-most-once settlement, late-completion safety, and partition confinement under explicit mediation, durability, authentication, normalization, and gateway assumptions. An indistinguishability result shows that partition-local availability requires exclusive preallocation. Bounded TLA+ checking, an independent JavaScript explorer, and crash-injected two-process SQLite experiments exercise the declared scope and detect timeout-refund and historical-certificate-validation mutants. The mechanism preserves the issued budget bound across the evaluated crash, retry, duplicate, partition, join, and late-completion schedules.