agent/papers/items/2026-2606-07682-swe-marathon-can-agents-autonomously-complete-ultra-long-horizon-software-work.md

Paper: SWE-Marathon: Can Agents Autonomously Complete Ultra-Long-Horizon Software Work?

---

type: paper title: "SWE-Marathon: Can Agents Autonomously Complete Ultra-Long-Horizon Software Work?" authors: Rishi Desai, Jesse Hu, Joan Cabezas, Neel Harsola, Pratyush Shukla, Roey Ben Chaim, Adnan El Assadi, Omkaar Mukund Kamath, et al. year: 2026 venue: arXiv url: https://arxiv.org/abs/2606.07682 code_url: source: arxiv collected_at: 2026-07-08 published_at: 2026-06-05 updated_at: 2026-06-05 status: queued relevance: high topics:

• agent-evaluation
• coding-agent
• memory
• planning
• rag
• reasoning
• workflow-agent methods:

benchmarks:

models:

datasets:

• cs.SE
• cs.AI related_concepts:

related_jobs:

related_experiments:

related_projects:

collection_score: 17 collection_queries: agent-evaluation

One-line Takeaway

Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.

Why Collected

• matched queries: agent-evaluation
• inferred topics: agent-evaluation, coding-agent, memory, planning, rag, reasoning, workflow-agent
• arXiv categories: cs.SE, cs.AI
• collection score: 17

Review Checklist

• Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
• Does it include a benchmark, dataset, code, or reproducible experimental setup?
• Should it be promoted from queued to skimmed or summarized?

Links

• arXiv: https://arxiv.org/abs/2606.07682