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.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Chen, H., Ye, B., Zhang, Y., & Yu, J. (2026). Auditing Action Settlement in LLM Agent Environments: Order, Progress, and Replay. https://omanscience.com/en/articles/auditing-action-settlement-in-llm-agent-environments-order-progress-and-replay
MLA 9
Chen, Haotian, et al. "Auditing Action Settlement in LLM Agent Environments: Order, Progress, and Replay." https://omanscience.com/en/articles/auditing-action-settlement-in-llm-agent-environments-order-progress-and-replay.
Chicago (author–date)
Chen, Haotian, Bowen Ye, Yuning Zhang, and Jingkun Yu. 2026. "Auditing Action Settlement in LLM Agent Environments: Order, Progress, and Replay." https://omanscience.com/en/articles/auditing-action-settlement-in-llm-agent-environments-order-progress-and-replay.
Harvard
Chen, H., Ye, B., Zhang, Y. and Yu, J. (2026) 'Auditing Action Settlement in LLM Agent Environments: Order, Progress, and Replay', Available at: https://omanscience.com/en/articles/auditing-action-settlement-in-llm-agent-environments-order-progress-and-replay.
Vancouver
Chen H, Ye B, Zhang Y, Yu J. Auditing Action Settlement in LLM Agent Environments: Order, Progress, and Replay. https://omanscience.com/en/articles/auditing-action-settlement-in-llm-agent-environments-order-progress-and-replay
IEEE
H. Chen, B. Ye, Y. Zhang, and J. Yu, "Auditing Action Settlement in LLM Agent Environments: Order, Progress, and Replay," https://omanscience.com/en/articles/auditing-action-settlement-in-llm-agent-environments-order-progress-and-replay.