5 citations · 7 across the 17 of their papers we have counts for
7 papers · 1 filter
Harbor Adapters and Harbor-Index: Infrastructure and a Curated Meta-Dataset for Large-Scale Agentic Evaluation
Lin Shi, Haowei Lin, Zixuan Zhu +123
Evaluating agents on the growing number of agentic benchmarks is challenging because they often require complex environments and agent integrations. We introduce Harbor Adapters, a…
Settling the Optimal Exponent Relating Sumsets and Difference Sets
Haowei Lin, Shanda Li
For a finite nonempty subset of an abelian group, let and . The classical sum-difference inequalities state that $$σ(A)^{1/2}\leqδ(A)\leqσ(A)^2…
ReproRepo: Scaling Reproducibility Audits with GitHub Repository Issues
Shanda Li, Qiuhong Anna Wei, Jingwu Tang +5
Reproducing research results from papers and released code is central to scientific progress. Existing works have introduced benchmarks to evaluate whether LLM agents can assist wi…
Human agency in initial human-AI proof formalization workflows
Katherine M. Collins, Simon Frieder, Jonas Bayer +14
For centuries, human mathematicians have written proofs to substantiate their mathematical arguments; yet, the ability to automatically verify the validity of proofs has long been…
Spend Less, Fit Better: Budget-Efficient Scaling Law Fitting via Active Experiment Selection
Sijie Li, Shanda Li, Haowei Lin +3
Scaling laws are used to plan multi-million-dollar training runs, but fitting those laws can itself cost millions. In modern large-scale workflows, assembling a sufficiently inform…
Learn Hard Problems During RL with Reference Guided Fine-tuning
Yangzhen Wu, Shanda Li, Zixin Wen +5
Reinforcement learning (RL) for mathematical reasoning can suffer from reward sparsity: for challenging problems, LLM fails to sample any correct trajectories, preventing RL from r…
Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces
Mike A. Merrill, Alexander G. Shaw, Nicholas Carlini +82
AI agents may soon become capable of autonomously completing valuable, long-horizon tasks in diverse domains. Current benchmarks either do not measure real-world tasks, or are not…