Daily AI Papers Briefing (2026-01-16)

ずんだもんのHugging Faceニュース · Jan 15, 2026 · 3m

【本日の論文】

・1. Controlled Self-Evolution for Algorithmic Code Optimization

・2. DeepResearchEval: An Automated Framework for Deep Research Task Construction and Agentic Evaluation

・3. MAXS: Meta-Adaptive Exploration with LLM Agents

・4. A^3-Bench: Benchmarking Memory-Driven Scientific Reasoning via Anchor and Attractor Activation

・5. Distribution-Aligned Sequence Distillation for Superior Long-CoT Reasoning

【参考リンク】

Controlled Self-Evolution for Algorithmic Code Optimization: https://huggingface.co/papers/2601.07348

DeepResearchEval: An Automated Framework for Deep Research Task Construction and…