arXiv AI
Lost in Recovery: Demystifying Recovery Behavior of Computer-Use Agents via Goal-Oriented Action Replay
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Aug 17
AgentRewind: Recoverable Execution for Long-Horizon LLM Agents
arXiv:2608. 14380v1 Announce Type: new Abstract: Many real-world tasks require LLM agents to interact with their environments over long execution horizons.
arXiv AI
Sep 15
Recoverability as a System Primitive for Long-Horizon AI Agents
arXiv:2609.13672v1 Announce Type: new Abstract: AI agents can be interrupted while editing files, calling tools, or carrying out multi-step tasks. Restarting repeats completed work, but continuing fr...
arXiv AI
Oct 15
TRAP: Tool-result Replay Attack for Probing Misbinding in LLM Agents
arXiv:2610.16333v1 Announce Type: new Abstract: As AI agents increasingly act through external tools, tool results are no longer simple outputs but execution artifacts that must remain correctly asso...
arXiv AI
Oct 5
Recoverability Has a Law: The ERR Measure for Tool-Augmented Agents
arXiv:2601.22352v2 Announce Type: replace-cross Abstract: Language model agents often appear capable of self-recovery after failing tool call executions, yet this behavior lacks a formal explanation....
arXiv AI
Sep 21
DENSE: Distilling Agent Trajectories into Evidence-Grounded Shortcut Trees for Self-Refinement
arXiv:2609.21423v1 Announce Type: new Abstract: Online agent deployments produce abundant execution traces, while task-specific verification and expert annotation are costly to scale. We study how to...
arXiv Computation and Language
Sep 17
Rollback the World, Keep the Reflection: Rollback-Induced Reflection for Long-Horizon LLM Agents
arXiv:2609.18304v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly tackle long-horizon tasks through multi-step environment interaction, yet a single erroneous action can...