--- title: Scaling to Long Horizons — Ross Taylor & Chengxi Taylor,... description: Ross Taylor (CEO of General Reasoning, formerly Meta AI reasoning lead) and Chengxi Taylor (co-founder) discuss scaling AI agents to long-horizon tasks. Ross... canonical: https://daily.dev/posts/scaling-to-long-horizons-ross-taylor-chengxi-taylor-general-reasoning-6t9o0suxh twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Scaling to Long Horizons — Ross Taylor & Chengxi Taylor, General Reasoning | daily.dev og:description: Ross Taylor (CEO of General Reasoning, formerly Meta AI reasoning lead) and Chengxi Taylor (co-founder) discuss scaling AI agents to long-horizon tasks. Ross... og:url: https://daily.dev/posts/scaling-to-long-horizons-ross-taylor-chengxi-taylor-general-reasoning-6t9o0suxh og:image: https://api.daily.dev/og/posts/6T9O0suxH.png og:image:alt: Scaling to Long Horizons — Ross Taylor & Chengxi Taylor, General Reasoning og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Scaling to Long Horizons — Ross Taylor & Chengxi Taylor, General Reasoning **[AI Engineer](https://daily.dev/sources/aidotengineer)** · 18 min read · 0 upvotes · 0 comments ## Summary Ross Taylor (CEO of General Reasoning, formerly Meta AI reasoning lead) and Chengxi Taylor (co-founder) discuss scaling AI agents to long-horizon tasks. Ross recounts the history of Galactica vs ChatGPT as an early natural experiment showing RLHF's importance over base models alone, and describes an unpublished Meta recipe using PPO with verifiable rewards that anticipated DeepSeek R1. Chengxi then covers the technical challenges of long-horizon RL: sparse rewards, gradient variance, credit assignment, and GPU utilization trade-offs. Solutions discussed include value models for variance reduction and bootstrapping, context compaction, pipeline RL, and file system/self-search tools. They introduce their Kelly Bench benchmark (where all frontier models lost money trading Premier League football) and their OpenReview platform hosting 350+ RL environments. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [How Production LLMs Reason Better At Inference Time](https://daily.dev/posts/how-production-llms-reason-better-at-inference-time-weygdosue) · Daily Dose of Data Science \| Avi Chawla \| Substack · 1 upvotes · 0 comments --- Tags: [#llm](https://daily.dev/tags/llm), [#ai-agents](https://daily.dev/tags/ai-agents), [#reinforcement-learning](https://daily.dev/tags/reinforcement-learning) [View this post on daily.dev](https://daily.dev/posts/scaling-to-long-horizons-ross-taylor-chengxi-taylor-general-reasoning-6t9o0suxh) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Scaling to Long Horizons — Ross Taylor & Chengxi Taylor, General Reasoning","url":"https://daily.dev/posts/scaling-to-long-horizons-ross-taylor-chengxi-taylor-general-reasoning-6t9o0suxh","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/scaling-to-long-horizons-ross-taylor-chengxi-taylor-general-reasoning-6t9o0suxh"},"datePublished":"2026-07-31T21:31:42.944Z","dateModified":"2026-07-31T21:57:30.174Z","description":"Ross Taylor (CEO of General Reasoning, formerly Meta AI reasoning lead) and Chengxi Taylor (co-founder) discuss scaling AI agents to long-horizon tasks. Ross...","image":"https://i.ytimg.com/vi/2bvtay8wGYI/sddefault.jpg","thumbnailUrl":"https://i.ytimg.com/vi/2bvtay8wGYI/sddefault.jpg","isAccessibleForFree":true,"articleSection":"AI Engineer","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"AI Engineer","logo":"https://media.daily.dev/image/upload/s--u5PucxNT--/f_auto/v1724338940/logos/aidotengineer","url":"https://daily.dev/sources/aidotengineer"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/scaling-to-long-horizons-ross-taylor-chengxi-taylor-general-reasoning-6t9o0suxh","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"llm,ai-agents,reinforcement-learning","timeRequired":"PT18M","video":{"@type":"VideoObject","name":"Scaling to Long Horizons — Ross Taylor & Chengxi Taylor, General Reasoning","description":"Ross Taylor (CEO of General Reasoning, formerly Meta AI reasoning lead) and Chengxi Taylor (co-founder) discuss scaling AI agents to long-horizon tasks. Ross...","thumbnailUrl":"https://i.ytimg.com/vi/2bvtay8wGYI/sddefault.jpg","uploadDate":"2026-07-31T21:31:42.944Z","duration":"PT18M","url":"https://api.daily.dev/r/6T9O0suxH","embedUrl":"https://www.youtube.com/embed/2bvtay8wGYI"}} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"AI Engineer","item":"https://daily.dev/sources/aidotengineer"},{"@type":"ListItem","position":3,"name":"Scaling to Long Horizons — Ross Taylor & Chengxi Taylor, General Reasoning"}]} ```