Do Not Restart: Residual Completion for Stateful Agent Handoffs
Runzhi Deng and colleagues at Nanjing University and Singapore Management University treat handing a partly finished tool-agent task from one model to another as commitment-constrained residual completion, and introduce CFRC, which lets the successor finish only the remaining work without redoing or contradicting accepted steps.
Ask this paper
Problem: Routing and cascades cut cost by moving control between models, but a stateful handoff must keep accepted choices, effects that already happened and unfinished obligations.
Three ordering rules: CFRC fixes the target before any proposal, requires the whole proposal before granting authority, and requires live evidence before declaring success.
Mechanism: It freezes a residual contract from accepted progress, has the successor write its continuation as a closed evidence-linked graph, and admits execution only when the remainder is covered, with live receipts discharging each obligation.
Results: Across five environments and two same-provider model pairs, CFRC matches the macro accuracy of strong full-task agents at 22.0% to 34.6% of their inference cost, with additional cross-provider results.
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.