Auditing Action Settlement in LLM Agent Environments: Order, Progress, and Replay

arXiv:2610.01138v1 Announce Type: new Abstract: Concurrent actions in large language model (LLM) agent environments require arbitration even when each proposal is individually valid. We implement a typed snapshot-settlement contract and audit three distinct properties: order sensitivity, useful progress, and replay consistency. Five settlement policies are tested in 28,800 exhaustive permutation trials and 2,160 scripted multistep episodes. Joint policies are spatially order-invariant conditional on fixed priorities, yet conservative rejection completes only 31.25% of agents in a six-agent doorway task versus 90.28% for random tickets; the paired improvement is 59.03 percentage points (95% bootstrap interval: 50.00-68.06). All policies preserve the tested spatial constraints, and priority arbitration still misses the independent small-instance optimum. A separate full-state journal audit exactly replays 156 checkpoints and rejects 1,332 constructed corruptions with a retained terminal anchor. The evidence concerns execution semantics, not human realism or long-run fairness.

Related

• From Proposal to Verified Effect: Praxa, an Evidence-Bound Harness for Governed AI Agent Execution
• When 'Must' Becomes 'Maybe': Constraint Weakening in LLM Agent Workflows
• SafeMCP: Proactive Power Regulation for LLM Agent Defense via Environment-Grounded Look-Ahead Reasoning
• ActGov: Governing LLM Agent Actions via Policy-Constrained Validation

Source: arXiv cs.AI | 2026-10-02