Sakana AI

company

Verified

https://sakana.ai/

AI & ML interests

We are a Tokyo-based R&D company on a quest to create a new kind of foundational AI model based on nature-inspired intelligence.

Recent Activity

speed authored a paper 6 days ago

QD-Rec: Open-Ended Evolution of Recommendations via Quality-Diversity

speed authored a paper 6 days ago

Harbor Adapters and Harbor-Index: Infrastructure and a Curated Meta-Dataset for Large-Scale Agentic Evaluation

tksii authored a paper 6 days ago

QD-Rec: Open-Ended Evolution of Recommendations via Quality-Diversity

View all activity

Papers

QD-Rec: Open-Ended Evolution of Recommendations via Quality-Diversity

Recursive Harness Self-Improvement

View all Papers

authored 2 papers 6 days ago

QD-Rec: Open-Ended Evolution of Recommendations via Quality-Diversity

Paper • 2610.23470 • Published 10 days ago • 6

Harbor Adapters and Harbor-Index: Infrastructure and a Curated Meta-Dataset for Large-Scale Agentic Evaluation

Paper • 2609.04298 • Published Sep 9 • 1

authored a paper 6 days ago

QD-Rec: Open-Ended Evolution of Recommendations via Quality-Diversity

Paper • 2610.23470 • Published 10 days ago • 6

submitted a paper to Daily Papers 6 days ago

QD-Rec: Open-Ended Evolution of Recommendations via Quality-Diversity

Paper • 2610.23470 • Published 10 days ago • 6

authored a paper 11 days ago

ProbabilityBench: Model Evaluation and Calibration with Exact Ground-Truth Uncertainty

Paper • 2610.17016 • Published 14 days ago • 14

submitted a paper to Daily Papers 11 days ago

ProbabilityBench: Model Evaluation and Calibration with Exact Ground-Truth Uncertainty

Paper • 2610.17016 • Published 14 days ago • 14

authored a paper 4 months ago

CoffeeBench: Benchmarking Long-Horizon LLM Agents in Heterogeneous Multi-Agent Economies

Paper • 2606.16613 • Published Jun 15 • 11

submitted a paper to Daily Papers 4 months ago

CoffeeBench: Benchmarking Long-Horizon LLM Agents in Heterogeneous Multi-Agent Economies

Paper • 2606.16613 • Published Jun 15 • 11

authored a paper 4 months ago

CoffeeBench: Benchmarking Long-Horizon LLM Agents in Heterogeneous Multi-Agent Economies

Paper • 2606.16613 • Published Jun 15 • 11

authored 3 papers 5 months ago

Mitigating Reward Hacking in RLHF via Advantage Sign Robustness

Paper • 2604.02986 • Published Apr 3 • 3

LLM Routing with Dueling Feedback

Paper • 2510.00841 • Published Oct 1, 2025

Do Coding Agents Deceive Us? Detecting and Preventing Cheating via Capped Evaluation with Randomized Tests

Paper • 2606.07379 • Published Jun 5 • 6

authored a paper 5 months ago

HakushoBench: A Japanese Chart and Table VQA Benchmark from Governmental White Papers

Paper • 2606.01132 • Published May 31 • 3

submitted a paper to Daily Papers 5 months ago

HakushoBench: A Japanese Chart and Table VQA Benchmark from Governmental White Papers

Paper • 2606.01132 • Published May 31 • 3

authored 2 papers 7 months ago

JAMMEval: A Refined Collection of Japanese Benchmarks for Reliable VLM Evaluation

Paper • 2604.00909 • Published Apr 1 • 1

Jagle: Building a Large-Scale Japanese Multimodal Post-Training Dataset for Vision-Language Models

Paper • 2604.02048 • Published Apr 2 • 1

authored 2 papers 8 months ago

EDINET-Bench: Evaluating LLMs on Complex Financial Tasks using Japanese Financial Statements

Paper • 2506.08762 • Published Jun 10, 2025 • 1

How Can I Publish My LLM Benchmark Without Giving the True Answers Away?

Paper • 2505.18102 • Published May 23, 2025 • 2

authored 2 papers 8 months ago

WAON: Large-Scale and High-Quality Japanese Image-Text Pair Dataset for Vision-Language Models

Paper • 2510.22276 • Published Oct 25, 2025 • 3

Llama-Mimi: Speech Language Models with Interleaved Semantic and Acoustic Tokens

Paper • 2509.14882 • Published Sep 18, 2025 • 2