Paradigma released Limit 1B Violetto, a 1 billion parameter dense transformer math-specialist model trained from scratch on under 300 billion curated tokens with a 131k context window, under Apache 2.…
BottleCap AI released ThinkingCap-Qwen3.8-27B, a fine-tune of Qwen3.8-27B that cuts thinking tokens by an average of 37.2% across 12 benchmarks while macro-average accuracy falls 0.86 percentage point…
A new arXiv paper (2609.22682v1) introduces Self-Organizing Agent Teams (SAT), fixed teams of AI agents that learn reusable collaboration strategies from prior interactions to organize roles, conversa…
A developer community analysis argues that 2026's leading large language models are deliberately trained to minimize stored factual knowledge in favor of compact, reusable reasoning procedures, citing…
Edge0-35B-A3B, a 35B-parameter sparse mixture-of-experts model built on Qwen3.5-MoE, loses an average of 3.9 points across five benchmarks when quantized to 4-bit through its edge0 inference pipeline …
A new arXiv paper (2609.11061v1) proposes belief-shift branching, a fork-placement method for tree-structured reinforcement learning with verifiable rewards that forks a chain just before the step whe…
IFM released K2 Horizon, a fleet of six open-source AI models (375B-A23B, 36B-A4B, 32B, 7B, 3.7B, and 0.9B) that deliver state-of-the-art performance in their size classes, with the 0.9B model scoring…
A preregistered study of Anthropic's Sonnet 5 found that explicitly requesting high reasoning effort increased mean delivered cost by $0.01031 per call compared with omitting the effort term, while ac…
Microsoft introduced MAI-Thinking-1, a 35B-active, ~1T-total parameter sparse Mixture of Experts reasoning model that matches leading models on software engineering benchmarks and is preferred to Sonn…
Google DeepMind released DiffusionGemma, an experimental open-weight model that converts the Gemma 4 architecture into a discrete text-diffusion system using less than 10% of Gemma 4's original traini…
A new arXiv paper, Ring-Zero: Scaling Zero RL to a Trillion Parameters for Emergent Reasoning, reports a 1T-parameter mixture-of-experts reasoning model trained with reinforcement learning from verifi…