StartupBench: Benchmarking General-Purpose Agents on Market-Validated End-to-End Workflows
Paper • 2608.17800 • Published • 9
Harmony.ai
non-profit
AI & ML interests
None defined yet.
Recent Activity
View all activity
zhangysk
authored 11
papers 10 days ago
Knowledge Index of Noah's Ark
Paper • 2606.05104 • Published
EdgeBench: Unveiling Scaling Laws of Learning from Real-World Environments
Paper • 2607.05155 • Published • 18
MSQA: A Natively Sourced Multilingual and Multicultural SimpleQA Benchmark
Paper • 2607.00724 • Published
Workflow-GYM: Towards Long-Horizon Evaluation of Computer-use Agentic tasks in Real-World Professional Fields
Paper • 2606.11042 • Published • 22
MARBLE: Music Audio Representation Benchmark for Universal Evaluation
Paper • 2306.10548 • Published
Balanced Aggregation: Understanding and Fixing Aggregation Bias in GRPO
Paper • 2605.04077 • Published • 7
In-Place Test-Time Training
Paper • 2604.06169 • Published • 30
Xpertbench: Expert Level Tasks with Rubrics-Based Evaluation
Paper • 2604.02368 • Published • 12
The Optimal Token Baseline: Variance Reduction for Long-Horizon LLM-RL
Paper • 2602.07078 • Published • 1
Reformulation for Pretraining Data Augmentation
Paper • 2502.04235 • Published • 23
zhangysk
authored 4
papers 6 months ago
VeRA: Verified Reasoning Data Augmentation at Scale
Paper • 2602.13217 • Published
Search More, Think Less: Rethinking Long-Horizon Agentic Search for Efficiency and Generalization
Paper • 2602.22675 • Published • 23
\$OneMillion-Bench: How Far are Language Agents from Human Experts?
Paper • 2603.07980 • Published • 27
Understanding by Reconstruction: Reversing the Software Development Process for LLM Pretraining
Paper • 2603.11103 • Published • 9
zhangysk
authored 4
papers 7 months ago
BABE: Biology Arena BEnchmark
Paper • 2602.05857 • Published • 10
Context Forcing: Consistent Autoregressive Video Generation with Long Context
Paper • 2602.06028 • Published • 36
Retrieval-Infused Reasoning Sandbox: A Benchmark for Decoupling Retrieval and Reasoning Capabilities
Paper • 2601.21937 • Published • 20
ConceptMoE: Adaptive Token-to-Concept Compression for Implicit Compute Allocation
Paper • 2601.21420 • Published • 42
zhangysk
authored a
paper 8 months ago