arXiv:2607. 01767v1 Announce Type: new Abstract: As agent planning moves from short tool chains toward persistent workflows with thousands or tens of thousands of steps, failures will occur inside large planning graphs rather than in isolated predictions.
Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.
arXiv:2607. 18859v1 Announce Type: new Abstract: While Large Language Models have greatly advanced automated issue resolution, existing agent-based methods exhibit a fundamental limitation in their insufficient exploration of repair strategies.
arXiv:2607. 13884v1 Announce Type: new Abstract: Large Language Model (LLM) agents have shown remarkable capabilities in autonomous decision-making by generating sequential trajectories of states, actions, and observations.
arXiv:2607. 29055v1 Announce Type: cross Abstract: Multi-agent systems (MAS) are increasingly deployed to solve complex tasks.
arXiv:2606. 05806v1 Announce Type: new Abstract: Existing benchmarks evaluate Tool-Integrated Reasoning (TIR) in LLMs on idealized ''happy paths'', largely overlooking real-world tool failures.
arXiv:2606. 27780v1 Announce Type: new Abstract: World models are often used for planning by rolling learned dynamics forward.
arXiv:2605. 03117v2 Announce Type: replace-cross Abstract: Automated program repair at repository scale requires an agent to locate a fault among thousands of files and synthesize a correct patch.