AgentRewind: Recoverable Execution for Long-Horizon LLM Agents

• URL: http://arxiv.org/abs/2608.14380v1
• Date: Fri, 14 Aug 2026 15:20:35 GMT
• Title: AgentRewind: Recoverable Execution for Long-Horizon LLM Agents
• Abstract summary: We present AgentRewind, a runtime recovery framework that records aligned checkpoints of the agent context and controlled environment.<n>We also construct MettleBench, a benchmark for evaluating task completion and partial progress on long-horizon engineering assignments.
• Score: 32.44158037765297
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Many real-world tasks require LLM agents to interact with their environments over long execution horizons. Errors that occur early in execution may propagate through both the agent context and environment state, and their effects may be difficult to reverse through subsequent actions. Existing methods mainly seek to reduce such errors through plan refinement and safety checks but provide little support after errors occur. To enable recovery during long-horizon execution, we present AgentRewind, a runtime recovery framework that records aligned checkpoints of the agent context and controlled environment, allowing agents to return to an earlier state and resume execution with information from previous attempts. We also construct MettleBench, a benchmark for evaluating task completion and partial progress on long-horizon engineering assignments containing a series of related requirements. Experiments across tasks, multiple models, execution strategies, and agent harnesses show that AgentRewind improves task success rate and average checklist progress over the compared baselines.

Related papers

• ParaRecover: A Process-Level Benchmark for Error Localization and Recovery in Parallel Tool-Use Agents [9.426759720914623]
  ParaRecover is a process-level benchmark for evaluating error localization and recovery in multi-turn parallel tool-use agents.<n>Built upon a fine-grained taxonomy of 14 error types covering planning dependencies, tool selection, and argument matching, the benchmark comprises 10,626 instances spanning two difficulty levels.<n>Experiments reveal that even state-of-the-art models still struggle with multi-turn error propagation,implicit tool-use failures, and precise replanning.
  arXiv  Detail & Related papers  (2026-09-11T02:09:33Z)
• AgentR A Stateful and Recovery-Aware Software Architecture for LLM-based Auditable Workflows [14.042464830509864]
  AgentR represents research intent, generated queries, candidate paper assessments and gap analyses as durable workflow artifacts.<n>The design includes explicit processing state transitions, retries with exponential backoff, credit-aware pre-checks, ACID token-cost logging, and Type-2 slowly changing pricing records.<n>At the LLM stage, the system achieves 99.2% job completion, and mean latencies of 9.0 s, 18.9 s, and 25.4 s for intent decomposition, query generation, and paper scoring.
  arXiv  Detail & Related papers  (2026-08-15T14:51:43Z)
• PAST-Bench: Benchmarking the Foundations of Recursive Self-Improvement in Personal Agents [50.9061759859778]
  PAST-Bench is a benchmark designed to isolate whether retained experience actually improves agents over time.<n>We report both later-task gains and whether those gains follow the intended save, retrieve, and update pathway.<n>We develop Hermes+, which extends Hermes with five targeted interventions across stages of the agent loop.
  arXiv  Detail & Related papers  (2026-08-04T17:58:05Z)
• OneDayAgent: Towards a Long-Horizon Harness for Autonomous Agents [52.15259607762389]
  We present OneDayAgent, a long-horizon harness for autonomous agents.<n>OneDayAgent turns an open-ended request into a managed execution process.<n>We evaluate OneDayAgent on AgentIF-OneDay across 104 tasks.
  arXiv  Detail & Related papers  (2026-08-04T17:55:41Z)
• PhyAgentOS: A Self-Evolving Operating System for Embodied Agents with Decoupled Cognitive Planning and Physical Execution [49.776611937968]
  We present PhyAgentOS, a foundation delivering scheduling, verification, memory, benchmarking, and safety as system-level services.<n>Its Session-Centered treats a session, not an action, as the minimum unit of scheduling, compatibility, supervised execution, evidence collection, and acceptance.<n>SessionVerifier distinguishes execution termination from semantic task completion via evidence-grounded verdicts of success, failure, or replan.<n> Benchmarking reuses the deployment session and verification path, so results trace to real execution.
  arXiv  Detail & Related papers  (2026-07-18T04:46:53Z)
• Meta-Agent: From Task Descriptions to Verified Multi-Agent Systems [36.485119937780524]
  We present Meta-Agent, a two-phase framework that automatically constructs and executes specialized multi-agent systems.<n>We introduce a three-level error attribution mechanism that distinguishes local, upstream, and structural failures.<n>Experiments against strong multi-agent baselines and ablation studies demonstrate consistent improvements in task success rate, error recovery, and workflow stability.
  arXiv  Detail & Related papers  (2026-05-24T19:38:54Z)
• From Reaction to Anticipation: Proactive Failure Recovery through Agentic Task Graph for Robotic Manipulation [45.37258918150899]
  We introduce AgentChord, an agentic system that models a manipulation task as a directed task graph.<n>Before execution, this graph is enriched with anticipatory recovery branches that specify context-aware corrective behaviors.<n> Empirical studies on diverse long-horizon bimanual manipulation tasks demonstrate that AgentChord substantially improves success rates and execution efficiency.
  arXiv  Detail & Related papers  (2026-05-12T11:00:45Z)
• Claw-Eval-Live: A Live Agent Benchmark for Evolving Real-World Workflows [67.92316850084575]
  We introduce Claw-Eval-Live, a live benchmark for workflow agents.<n>Each release is constructed from public workflow-demand signals.<n>Claw-Eval-Live records execution traces, audit logs, service state, and post-run workspace artifacts.
  arXiv  Detail & Related papers  (2026-04-30T17:23:19Z)
• CodeTracer: Towards Traceable Agent States [40.51936201889185]
  We present CodeTracer, a tracing architecture that parses heterogeneous run artifacts through evolving extractors.<n>CodeTracer reconstructs the full state transition history as a hierarchical trace tree with persistent memory.<n>It performs failure onset localization to pinpoint the failure origin and its downstream chain.
  arXiv  Detail & Related papers  (2026-04-13T15:52:03Z)
• AgentSentry: Mitigating Indirect Prompt Injection in LLM Agents via Temporal Causal Diagnostics and Context Purification [25.817251923574286]
  We propose a novel inference-time detection and mitigation framework for large language model (LLM) agents.<n>AgentSentry is the first inference-time defense to model multi-turn IPI as a temporal causal takeover.<n>We evaluate AgentSentry on the textscAgentDojo benchmark across four task suites, three IPI attack families, and multiple black-box LLMs.
  arXiv  Detail & Related papers  (2026-02-26T07:59:10Z)
• LongCLI-Bench: A Preliminary Benchmark and Study for Long-horizon Agentic Programming in Command-Line Interfaces [65.11019654023978]
  LongCLI-Bench is a benchmark designed to evaluate agentic capabilities across long-horizon, realistic tasks.<n>We curated 20 high-quality, long-horizon tasks from over 1,000 computer science assignments and real-world tasks.<n>Experiments reveal that even state-of-the-art agents achieve pass rates below 20% in LongCLI-Bench.
  arXiv  Detail & Related papers  (2026-02-15T23:12:57Z)
• AgentPRM: Process Reward Models for LLM Agents via Step-Wise Promise and Progress [71.02263260394261]
  Large language models (LLMs) still encounter challenges in multi-turn decision-making tasks.<n>We build process reward models (PRMs) to evaluate each decision and guide the agent's decision-making process.<n>AgentPRM captures both the interdependence between sequential decisions and their contribution to the final goal.
  arXiv  Detail & Related papers  (2025-11-11T14:57:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.