arXiv:2606. 02875v1 Announce Type: new Abstract: Coding-agent benchmarks evaluate whether a single uninterrupted agent can resolve a repository issue.
Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.
arXiv:2608. 16055v1 Announce Type: new Abstract: Existing agent benchmarks ask whether the agent finished the task.
arXiv:2606. 22504v1 Announce Type: cross Abstract: Coding agents often receive broad tool access for an entire task, even when a resource is needed only for one subgoal.
arXiv:2608. 16630v1 Announce Type: cross Abstract: Repository-scale coding requires an agent to keep tests, imports, configuration, and migration rules consistent within a bounded context window.
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.
Software engineering (SWE) agents resolve repository-level issues through long trajectories that grow increasingly expensive as context accumulates. Failed runs tend to be longer and exhibit redundant exploration or looping, suggesting that some failures may be detectable before completion.
arXiv:2608. 07855v1 Announce Type: new Abstract: Multi-turn Reasoning-and-Acting (ReAct) agents accumulate growing trajectories of reasoning, tool calls, and observations.