arXiv AI
2d ago
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.
StructAgent: Harness Long-horizon Digital Agents with Unified Causal Structure
arXiv:2607. 11388v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) and vision-language models (VLMs) have enabled increasingly capable digital agents for computer use.
Related stories
arXiv AI
Jul 29
Desktop-Delta Bench: Do Computer-Use Models Understand Desktop GUI Transitions?
arXiv:2607. 26041v1 Announce Type: new Abstract: Computer-use agents (CUAs) increasingly act through desktop GUIs to complete long-horizon tasks.
arXiv AI
Aug 11
ROM: Real-time Overthinking Mitigation via Streaming Detection and Intervention
arXiv:2603. 22016v3 Announce Type: replace-cross Abstract: Large Reasoning Models (LRMs) often reach a correct solution before their long Chain-of-Thought trace ends, yet continue with redundant verification, repeated attempts, or unnecessary exploration that wastes computation and can even overturn the correct answer.
arXiv Machine Learning
Aug 4
Qwen-CUA: Native Computer Use for (almost) Everything
arXiv:2608. 02352v1 Announce Type: new Abstract: Native computer use offers a general interface for agents to operate almost any software available to people, but requires long-horizon state tracking, large-scale interactive experience, and learning from sparse yet verifiable outcomes.
arXiv AI
Jun 2
Causal state binding predicts action control in language agents
arXiv:2605. 09692v3 Announce Type: replace Abstract: Autonomous language agents increasingly expose traces, memories, plans and constraints, but existing evaluations rarely test whether these state variables are bound to final actions.
arXiv AI
Jun 24
LemonHarness Technical Report
arXiv:2606. 24311v1 Announce Type: new Abstract: As large language model (LLM) agents are applied to longer tasks, they increasingly modify workspace state across multiple rounds of iteration.
arXiv AI
Aug 5
Verifiable Memory: Learning Unified Memory Management with Local and Global Verifiers for Large Language Model Agents
arXiv:2608. 03137v1 Announce Type: new Abstract: Large language model (LLM) agents must retain reusable information, control a bounded active context, and recover earlier evidence during long-horizon interaction.
arXiv AI
Aug 11
TempoBench: Reasoning Execution Without Causal Attribution Is Just Simulation
arXiv:2510. 27544v3 Announce Type: replace Abstract: Current training paradigms, optimized for long-horizon reasoning trace execution, have made Large Language Models (LLMs) excel at pattern matching and forward simulation of reasoning, but underperform at counterfactual causal understanding and reasoning.
arXiv AI
Jun 4
Plan, Watch, Recover: A Benchmark and Architectures for Proactive Procedural Assistance
arXiv:2606. 04970v1 Announce Type: cross Abstract: We envision a proactive multi-modal assistant system which gives users real-time step-by-step guidance on a procedural task, autonomously deciding \textit{when} to interrupt, and \textit{how} to coach.
arXiv AI
Jul 15
Do AI Agents Know When a Task Is Simple? Toward Complexity-Aware Reasoning and Execution
arXiv:2607. 13034v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly automate multi-step engineering and informatics workflows, yet they rarely ask how much effort a task actually requires.
arXiv AI
Jun 9
Where Instruction Hierarchy Breaks: Diagnosing and Repairing Failures in Reasoning Language Models
arXiv:2606. 07808v1 Announce Type: new Abstract: Reasoning language models deployed in agentic workflows must follow an instruction hierarchy: when instructions from different sources conflict, the model should obey the highest-privilege applicable instruction.
arXiv AI
1d ago
AstronOS: A Unified Execution Model and Runtime for Long-Horizon Agentic Systems
arXiv:2608. 16381v1 Announce Type: new Abstract: Agentic systems often organize execution and state around a single conversation, model invocation, or agent instance, even when real work spans many calls and stages.