mlsanityData to 14 Oct 2026

Do Not Restart: Residual Completion for Stateful Agent Handoffs

arXiv 2609.13800 ↗First posted 12 Sep 2026cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

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 22.0% to 34.6% mean per-surface cost, with additional cross-provider results demonstrating broader transfer.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 26 of its 32 references that are in the map. First posted on arXiv 12 Sep 2026.

Builds on

26 of 32 references.

References · 26

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  2. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  3. 2024τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domainscited by 1,402
  4. 2023FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performancecited by 853
  5. 2024RouteLLM: Learning to Route LLMs with Preference Datacited by 682
  6. 2025τ2-Bench: Evaluating Conversational Agents in a Dual-Control Environmentcited by 627
  7. 2024AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agentscited by 401
  8. 2024Agent Workflow Memorycited by 383
  9. 2025Defeating Prompt Injections by Designcited by 297
  10. 2024ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilitiescited by 295
  11. 2025AgentSpec: Customizable Runtime Enforcement for Safe and Reliable LLM Agentscited by 223
  12. 2025Enforcing Temporal Constraints for LLM Agentscited by 34
14 more
  1. 2024GoEX: Perspectives and Designs Towards a Runtime for Autonomous LLM Applicationscited by 23
  2. 2026Cordon: Semantic Transactions for Tool-Using LLM Agentscited by 22
  3. 2026VIGIL: Defending LLM Agents Against Tool Stream Injection via Verify-Before-Commitcited by 17
  4. 2026ToolGate: Contract-Grounded and Verified Tool Execution for LLMscited by 15
  5. 2026From Confident Closing to Silent Failure: Characterizing False Success in LLM Agentscited by 15
  6. 2026Agent-Diff: Benchmarking LLM Agents on Enterprise API Tasks via Code Execution with State-Diff-Based Evaluationcited by 13
  7. 2026The Granularity Mismatch in Agent Security: Argument-Level Provenance Solves Enforcement and Isolates the LLM Reasoning Bottleneckcited by 11
  8. 2026SWE-Router: Routing in Multi-turn Agentic Software Engineering Taskscited by 11
  9. 2026MTRouter: Cost-Aware Multi-Turn LLM Routing with History-Model Joint Embeddingscited by 10
  10. 2026Step-level Optimization for Efficient Computer-use Agentscited by 7
  11. 2026Can Agent Benchmarks Support Their Scores? Evidence-Supported Bounds for Interactive-Agent Evaluationcited by 5
  12. 2026Is Escalation Worth It? On the Depth of LLM Cascadescited by 4
  13. 2026Agentic Routing: The Harness-Native Data Flywheelcited by 4
  14. 2026Handoff Debt: The Rediscovery Cost When Coding Agents Take Over Interrupted Taskscited by 3

Built on by

Not cited yet.