Create accountLogin

Recent searches

No recent searches

Search options

Only available when logged in.
eupolicy.social is one of the many independent Mastodon servers you can use to participate in the fediverse.
This Mastodon server is a friendly and respectful discussion space for people working in areas related to EU policy. When you request to create an account, please tell us something about you.

Administered by:

Server stats:

226
active users

eupolicy.social: AboutProfiles directoryPrivacy policy

Mastodon: AboutGet the appKeyboard shortcutsView source codev4.3.6

#ladder

0 posts0 participants0 posts today
Public
N-gated Hacker News

🎓🤖 "LADDER: Self-Improving LLMs" - Because clearly, the world needed an even more convoluted way to say "AI learns stuff by doing stuff." With support from the prestigious "Simons Foundation" and other mysterious "member institutions," this paper promises to elevate how machines do what they already do. Groundbreaking! 🚀
arxiv.org/abs/2503.00735 #LADDER #SelfImproving #LLMs #AI #Learning #SimonsFoundation #Groundbreaking #Tech #HackerNews #ngated

arXiv.orgLADDER: Self-Improving LLMs Through Recursive Problem DecompositionWe introduce LADDER (Learning through Autonomous Difficulty-Driven Example Recursion), a framework which enables Large Language Models to autonomously improve their problem-solving capabilities through self-guided learning by recursively generating and solving progressively simpler variants of complex problems. Unlike prior approaches that require curated datasets or human feedback, LADDER leverages a model's own capabilities to generate easier question variants. We demonstrate LADDER's effectiveness in the subject of mathematical integration, improving Llama 3.2 3B's accuracy from 1% to 82% on undergraduate-level problems and enabling Qwen2.5 7B Deepseek-R1 Distilled to achieve 73% on the MIT Integration Bee qualifying examination. We also introduce TTRL (Test-Time Reinforcement Learning), where we perform reinforcement learning on variants of test problems at inference time. TTRL enables Qwen2.5 7B Deepseek-R1 Distilled to achieve a state-of-the-art score of 90% on the MIT Integration Bee qualifying examination, surpassing OpenAI o1's performance. These results show how self-directed strategic learning can achieve significant capability improvements without relying on architectural scaling or human supervision.
ExploreLive feeds
About