mlsanityData to 14 Oct 2026

Fault-Tolerant Budget Conservation in Distributed Multi-Agent Delegation

arXiv 2610.00349 ↗First posted 29 Sep 2026cs.AI cs.CR cs.DCcited by 0

Not on the map. Why?

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.

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

25 of 54 references.

References · 25

  1. 2026Atomix: Timely, Transactional Tool Use for Reliable Agentic Workflowscited by 30
  2. 2026Temporary Authority, Permanent Effects: Commit-Time Authorization for LLM Agentscited by 18
  3. 2026Agent Contracts: A Formal Framework for Resource-Bounded Autonomous AI Systemscited by 16
  4. 2026MAS-FIRE: Fault Injection and Reliability Evaluation for LLM-Based Multi-Agent Systemscited by 16
  5. 2026AIP: Agent Identity Protocol for Verifiable Delegation Across MCP and A2Acited by 11
  6. 2026Context-to-Execution Integrity for LLM Agentscited by 10
  7. 2026Beyond Single-Use Tokens: Durable Authorization State for Replay-Resistant LLM Agent Actionscited by 7
  8. 2026HDP: A Lightweight Cryptographic Protocol for Human Delegation Provenance in Agentic AI Systemscited by 6
  9. 2026Token Budgets: An Empirical Catalog of 63 LLM-Agent Budget-Overrun Incidents, with an Affine-Typed Rust Mitigation as a Case Studycited by 6
  10. 2026Beyond OAuth: Task-Scoped Authorization for AI Agents via Natural Language Slicescited by 5
  11. 2026Overlaying Governance: A Compositional Authorization Framework for Delegation and Scope in Agentic AIcited by 5
  12. 2026Intent-Governed Tool Authorization for AI Agentscited by 5
13 more
  1. 2026OpenPort Protocol: A Security Governance Specification for AI Agent Tool Accesscited by 4
  2. 2026Where Does Exactly-Once Live? Model, Harness, and Tool-Contract Effects on Duplicate Side Effects in LLM Agentscited by 3
  3. 2019Delivery, consistency, and determinism: rethinking guarantees in distributed stream processingcited by 2
  4. 2026Aegon: Auditable AI Content Access with Ledger-Bound Tokens and Hardware-Attested Mobile Receiptscited by 2
  5. 2026MPAC: A Multi-Principal Agent Coordination Protocol for Interoperable Multi-Agent Collaborationcited by 2
  6. 2026Attacks and Mitigations for Distributed Governance of Agentic AI under Byzantine Adversariescited by 2
  7. 2026Explanation-Bound Tool Execution for AI Agents: Server-Verified Action Claims Without Trusting Model Rationalescited by 2
  8. 2026Complete CALM: A Coordination Criterion for Specificationscited by 1
  9. 2026The Bureaucracy of Speed: Structural Equivalence Between Memory Consistency Models and Multi-Agent Authorization Revocationcited by 1
  10. 2026EpochX: Building the Infrastructure for an Emergent Agent Civilizationcited by 1
  11. 2026Behavioral Governance for Autonomous AI Agents: The AgentBound Frameworkcited by 1
  12. 2026Machine-Checked Dual-Write Recovery from a Commit Logcited by 1
  13. 2026Versioned Transitive Dependency-Closure Binding and Operation-Time Effect Governance for Agent Skills: ClosureBoundcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Runtime Authorization for Resources Acquired by AI Agents
  2. 2026NostrAgent: A Decentralized Identity and Delegation Architecture for Sovereign Agentic Systems
  3. 2026Delegation Without Trust: An Empirical Gap Analysis of Identity, Authorization, and Runtime Governance in Multi-Agent LLM Systems
  4. 2026DecisionBench: A Benchmark for Emergent Delegation in Long-Horizon Agentic Workflows
  5. 2026The Provenance Paradox in Multi-Agent LLM Routing: Delegation Contracts and Attested Identity in LDP
  6. 2026Authorization Propagation in Multi-Agent AI Systems: Identity Governance as Infrastructure
  7. 2026A Policy Algebra for Trust-Preserving Agentic AI Execution
  8. 2026Agent Behavioral Contracts: Formal Specification and Runtime Enforcement for Reliable Autonomous AI Agents