PulseAugur
EN
LIVE 07:48:50

New AI agent Marathoner masters ultra-long-horizon tasks

By PulseAugur Editorial · [1 sources] ·

Researchers have developed Marathoner, an autonomous agentic model designed for ultra-long-horizon task execution. The model utilizes a post-training pipeline that synthesizes challenging tasks from large GitHub pull requests and chains them together to achieve frontier-level difficulty. Marathoner incorporates a novel reward strategy, Later Stage Bonus Reward, to encourage sustained effort and has demonstrated consistent performance improvements over base models and even proprietary models on benchmarks requiring extended execution times and numerous tool calls. AI

IMPACT This research could enable AI agents to tackle complex, long-term projects previously only achievable by humans.

RANK_REASON The cluster describes a new research paper detailing an AI model and its methods. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

New AI agent Marathoner masters ultra-long-horizon tasks

How we ranked this

Signal score
27 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
The cluster describes a new research paper detailing an AI model and its methods. [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, model release
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. arXiv cs.CV TIER_1 English(EN) · Ruiyang Zhang, Jinpeng Ou, Yifan Xie, Jingang Zhou, Lirui Pan, Qingpei Guo, Zhedong Zheng ·

    Marathoner: Ultra-Long-Horizon Autonomous Intelligence

    arXiv:2609.34378v2 Announce Type: replace Abstract: Humans naturally possess the ability to work persistently toward long-term goals. Given a challenging task, humans can continuously work for months or even years to accomplish a specific objective. In this paper, we propose Mara…

RELATED ENTITIES

RELATED TOPICS