Tootfinder

Here's a sort of rebuttal to AI 2027 that feels more informed than most of the ones I've read:
https://www.lesswrong.com/posts/XiMRyQcEyKCryST8T/slowdown-after-2028-compute-rlvr-uncertainty-moe-data-wall…

This https://arxiv.org/abs/2505.19914 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

Enigmata: Scaling Logical Reasoning in Large Language Models with Synthetic Verifiable Puzzles
Large Language Models (LLMs), such as OpenAI's o1 and DeepSeek's R1, excel at advanced reasoning tasks like math and coding via Reinforcement Learning with Verifiable Rewards (RLVR), but still struggle with puzzles solvable by humans without domain knowledge. We introduce Enigmata, the first comprehensive suite tailored for improving LLMs with puzzle reasoning skills. It includes 36 tasks across seven categories, each with 1) a generator that produces unlimited examples with controllable diffic…

🇺🇦 Auf radioeins läuft...
R. L. Burnside:
🎵 It's Bad You Know
#NowPlaying #RLBurnside
https://flamingomix.bandcamp.com/track/r-l-burnside-its-bad-you-know-flamingo-edit
https://open.spotify.com/track/1AcvqJhm4CXOFJ7INbR5rR

This https://arxiv.org/abs/2506.05850 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

Cross-lingual Collapse: How Language-Centric Foundation Models Shape Reasoning in Large Language Models
We identify \textbf{Cross-lingual Collapse}, a systematic drift in which the chain-of-thought (CoT) of a multilingual language model reverts to its dominant pre-training language even when the prompt is expressed in a different language. Recent large language models (LLMs) with reinforcement learning with verifiable reward (RLVR) have achieved strong logical reasoning performances by exposing their intermediate reasoning traces, giving rise to large reasoning models (LRMs). However, the mechani…

🇺🇦 #NowPlaying on BBCRadio3's #Breakfast
Ermanno Wolf‐Ferrari, Royal Liverpool Philharmonic Orchestra & Domingo Hindoyan:
🎵 Il Segreto di Susanna: Overture
#ErmannoWolfFerrari #RoyalLiverpoolPhilharmonicOrchestra #DomingoHindoyan

CRScore : Reinforcement Learning with Verifiable Tool and AI Feedback for Code Review
Manav Nitin Kapadnis, Atharva Naik, Carolyn Rose
https://arxiv.org/abs/2506.00296

CRScore++: Reinforcement Learning with Verifiable Tool and AI Feedback for Code Review
Reinforcement learning (RL) to improve code review comment generation requires handling unstructured outputs, making reinforcement learning (RL) feedback challenging. The two main RL approaches, namely RL with Verifiable Feedback (RLVR) and RL with AI Feedback (RLAIF), offer trade-offs: RLVR provides reliable feedback for structured tasks like code generation, while RLAIF works for unstructured outputs but is subjective. We bridge this gap with CRScore++, an RL framework that leverages both LLM…

🇺🇦 #NowPlaying on BBCRadio3's #Radio3InConcert
Ludwig van Beethoven, Royal Liverpool Philharmonic Orchestra & Dinis Sousa:
🎵 Symphony no.6 in F major, Op.68 'Pastoral'
#LudwigvanBeethoven #RoyalLiverpoolPhilharmonicOrchestra #DinisSousa

🇺🇦 #NowPlaying on BBCRadio3's #InTune
Pyotr Ilyich Tchaikovsky, Royal Liverpool Philharmonic Orchestra & Vasily Petrenko:
🎵 Symphony no.4 in F minor Op.36 (3rd mvt)
#PyotrIlyichTchaikovsky #RoyalLiverpoolPhilharmonicOrchestra #VasilyPetrenko

Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning
Shenzhi Wang, Le Yu, Chang Gao, Chujie Zheng, Shixuan Liu, Rui Lu, Kai Dang, Xionghui Chen, Jianxin Yang, Zhenru Zhang, Yuqiong Liu, An Yang, Andrew Zhao, Yang Yue, Shiji Song, Bowen Yu, Gao Huang, Junyang Lin
https://arx…

Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning
Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a powerful approach to enhancing the reasoning capabilities of Large Language Models (LLMs), while its mechanisms are not yet well understood. In this work, we undertake a pioneering exploration of RLVR through the novel perspective of token entropy patterns, comprehensively analyzing how different tokens influence reasoning performance. By examining token entropy patterns in Chain-of-Thought (CoT) reasoning, we observe that o…

🇺🇦 #NowPlaying on BBCRadio3's #Breakfast
Edward Elgar, Royal Liverpool Philharmonic Orchestra & Vasily Petrenko:
🎵 Serenade for strings in E minor, Op.20
#EdwardElgar #RoyalLiverpoolPhilharmonicOrchestra #VasilyPetrenko