September 2–8: 8 frontier papers out of 1,459 read.
Papers rated as moving the field
How we choose“Experiments on GSM8K and MATH show that RePro's retained rewritten instances achieve 100% well-definedness, feasibility, and answer correctness, while existing methods still produce invalid or incorrect instances.”
The authors, in the abstract
Proof-Verified Benchmark Rewriting for Reliable Evaluation of LLM Mathematical Problem Solving
“On the DevRev NL2SQL benchmark the system attains 91.7% answer correctness, a margin of 54.6 percentage points over the next-best baseline; on the Spider 2.0 Snowflake public dataset, it is competitive with leading systems at a single-generation operating point.”
“We instantiate this threat in agentic commerce and software dependency use, with SkillShift achieving attacker-favored selection rates of 81.33% and 63.33% while maintaining a 100% utility-preserving rate.”
Sep 2–8: 135 cleared, 8 frontier
The week’s papers have not been sorted into fields yet.
Papers this week that name the model
Papers this week with an author at the lab
127 papers