Shengnan An

ShengnanAn's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

commented a paper 12 days ago

Long-horizon Reasoning Agent for Olympiad-Level Mathematical Problem Solving

Paper • 2512.10739 • Published 17 days ago • 45 •

4

New activity in deepseek-ai/DeepSeek-V3.2 19 days ago

Default system prompt can hinder thinking-mode performance

#31 opened 19 days ago by

ShengnanAn

New activity in deepseek-ai/DeepSeek-V3.2 23 days ago

Should the thinking mode in DS v3.2 use the default system prompt?

1

#24 opened 23 days ago by

ShengnanAn

New activity in moonshotai/Kimi-K2-Thinking about 2 months ago

Awesome work! Do you want to try AMO-Bench, the most challenging MO-level benchmark?

#3 opened about 2 months ago by

ShengnanAn

New activity in meituan-longcat/AMO-Bench about 2 months ago

Problem 35: Official solution misuses “positive integers”, final count should be 7656 (not 7657)

4

#4 opened about 2 months ago by

applesilicon

Improve dataset card: Add task category, paper, project page, code, abstract, features, leaderboard, and sample usage

👍 1

1

#2 opened about 2 months ago by

nielsr

Problem 26 seems identical to Berkeley Math Circle 2014–2015 Monthly Contest 3, Problem 4

1

#3 opened about 2 months ago by

applesilicon

commented a paper about 2 months ago

AMO-Bench: Large Language Models Still Struggle in High School Math Competitions

Paper • 2510.26768 • Published Oct 30 • 33 •

1

commented a paper about 2 years ago

Learning From Mistakes Makes LLM Better Reasoner

Paper • 2310.20689 • Published Oct 31, 2023 • 29 •

4