Stateful agent handoffs cut costs without losing progress
Do Not Restart: Residual Completion for Stateful Agent Handoffs
Artificial Intelligence
Summary
When AI tools hand off tasks between different models, it's important to keep all the work done so far, like choices made or jobs still in progress. The authors created a method called Commitment-Frontier Residual Completion (CFRC) that carefully tracks and preserves these partial tasks so the next model can continue without starting over. Their method saves time and computing power while keeping accuracy close to full-process agents. They tested CFRC in several scenarios and showed it also works across different providers.
What this means in practice
- •For ai system engineers: Reduce compute cost by handing off stateful agent tasks while preserving progress and obligations across models.
- •For cloud service operators: Enable efficient routing of AI requests among models from different providers without losing intermediate results.
Authors
Runzhi Deng, Yiming Zhong, Fang Zhao, Pan Zhou
Abstract
Routing and cascades reduce tool-agent cost by transferring control across models, but stateful handoffs must preserve accepted choices, realized effects, and unfinished obligations. We formulate this as commitment-constrained residual completion and introduce Commitment-Frontier Residual Completion (CFRC). CFRC enforces target-before-proposal, whole-proposal-before-authority, and live-evidence-before-success: it freezes a residual contract from accepted progress, closes the successor continuation into an evidence-linked graph, and admits execution only when the remainder is covered, with live receipts discharging obligations. We establish contract-relative partial correctness, which extends to the original residual request under complete contract construction. Across five environments and two same-provider model pairs, CFRC achieves comparable macro accuracy to strong full-task agents at only 22.0%-34.6% of their inference cost, with additional cross-provider results demonstrating broader transfer.