Daily AI Papers Briefing (2026-01-21)

ずんだもんのHugging Faceニュース · Jan 20, 2026 · 4m

【本日の論文】

1. ABC-Bench: Benchmarking Agentic Backend Coding in Real-World Development

https://huggingface.co/papers/2601.11077

2. Multiplex Thinking: Reasoning via Token-wise Branch-and-Merge

https://huggingface.co/papers/2601.08808

3. Medical SAM3: A Foundation Model for Universal Prompt-Driven Medical Image Segmentation

https://huggingface.co/papers/2601.10880

4. NAACL: Noise-AwAre Verbal Confidence Calibration for LLMs in RAG Systems

https://huggingface.co/papers/2601.11004

5. Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMs…