Sakana AI released Fugu Ultra v2, a model that orchestrates tasks across multiple specialized models rather than relying on a single monolithic architecture. It's designed for complex reasoning, autonomous research, and software development with a 1M token context window and costs $5/$30 per million input/output tokens.

• Fugu Ultra v2 uses learned multi-agent orchestration to route work across open and specialized models, avoiding dependence on proprietary frontier models
• The model supports configurable reasoning effort levels, function calling, structured outputs, and integrated web search
• Real-world performance shows 31 tokens/second throughput, 10.6 second latency, and 87.47% availability across providers over the past 3 days

This paper explores how large language models make decisions during reasoning. It demonstrates that these models often encode their choices before generating text, influencing their subsequent thought processes. The research shows that altering initial decisions can change reasoning outcomes significantly.

• A linear probe can decode whether a model will call a tool from its activations before it generates any reasoning text, sometimes before any tokens at all
• Artificially flipping this early "decision direction" causes the model to switch its tool-use behavior in 7% to 79% of cases depending on model/benchmark
• When steered toward a different decision, the model's subsequent reasoning rationalizes the new choice rather than resisting or correcting it, suggesting the "thinking" is post-hoc justification rather than genuine deliberation

This article explores how advanced AI models can generate detailed image descriptions and reasoning without actual image input, a phenomenon called mirage reasoning. It highlights vulnerabilities in these models, particularly in medical contexts, and introduces B-Clean, a method for better evaluating multimodal AI systems by minimizing non-visual inference.

• A model topped a chest X-ray QA benchmark while being completely blind to the actual images, exposing "mirage reasoning" where models fabricate plausible visual descriptions from text priors alone.
• Explicitly prompting models to guess without assuming an image was present caused performance to drop sharply, showing benchmark scores were inflated by non-visual inference rather than real image understanding.
• The proposed B-Clean method strips out textual cues that let models cheat their way to correct answers, aiming to force genuine visual grounding in evaluations—critical for high-stakes fields like medical AI.

The article discusses the importance of data activation in enhancing the performance of large language models (LLMs), particularly in the healthcare sector. It highlights recent advancements in transforming structured medical data into usable formats for LLMs, emphasizing the need for effective reasoning methods to fully leverage the potential of healthcare data.

• Having proprietary data is no longer enough—the real advantage comes from "activating" it into forms LLMs can actually use before competitors catch up
• Tables2Traces converts structured medical data into reasoning traces via contrastive reasoning, notably boosting LLM performance on medical tasks
• Doctors have questioned the fidelity of these synthetic reasoning traces, and gains so far appear mainly in weaker models, raising doubts about scalability
• Despite heavy healthcare-focused LLM investment from OpenAI and Anthropic, the field is fragmented and the best method for transforming healthcare data (knowledge graphs, ontology grounding, etc.) is still unsettled

Deep Think with Confidence (DeepConf) is introduced as a method to improve reasoning efficiency and performance in large language models by using internal confidence signals to filter out low-quality reasoning traces. It requires no additional training or tuning and can be easily integrated into existing systems. Evaluations show significant accuracy improvements and a reduction in generated tokens on various reasoning tasks.

• DeepConf uses internal confidence signals to filter out low-quality reasoning traces without any additional training or tuning
• It integrates easily into existing LLM systems
• Evaluations show significant accuracy improvements alongside a reduction in generated tokens across various reasoning tasks

The article reviews significant trends and developments in the LLM space throughout 2025, highlighting breakthroughs in reasoning, the rise of coding agents, and the increasing use of LLMs in command-line interfaces. It notes the evolution of tools and models, including the impact of asynchronous coding agents and the normalization of YOLO mode for improved efficiency.

• Reasoning models became mainstream in 2025, significantly boosting LLM performance on complex tasks
• Coding agents surged in popularity, with asynchronous agents enabling developers to offload larger chunks of work
• "YOLO mode" (letting agents run commands without manual approval) went from risky novelty to normalized practice for efficiency
• LLMs increasingly moved into command-line interfaces, embedding AI more directly into developer workflows