Generalized Agent Iteration: One Formal Framework for Iterative Policy Improvement and Recursive Self-Improvement
Paper • 2609.13406 • Published • 110
Amy Frazier
AmyFrazier90
AI & ML interests
Research on LLM agents and evaluation.
Recent Activity
upvoted a paper 1 day ago
Player-1: Learning to Play from Synthetic ExperienceOrganizations
None yet
upvoted 17
papers 1 day ago
Player-1: Learning to Play from Synthetic Experience
Paper • 2610.20584 • Published • 334
Workflow-GYM: Towards Long-Horizon Evaluation of Computer-use Agentic tasks in Real-World Professional Fields
Paper • 2606.11042 • Published • 216
VideoJev: System One Model for Video Understanding and Interaction
Paper • 2610.18615 • Published • 358
OneStreamer: Unifying Perception, Memory, and Proactive Response in Streaming Video Interaction
Paper • 2610.01762 • Published • 237
ClawBench: Can AI Agents Complete Everyday Online Tasks?
Paper • 2604.08523 • Published • 369
MJev-Spatial: System One Spatial Intelligence via Native Attention Matching
Paper • 2610.22276 • Published • 352
Grounded Action Model: 3D Grounding as a Foundation for Robotics
Paper • 2609.23863 • Published • 89
Beyond Pixels: From Video Priors to 4D Worlds
Paper • 2608.10744 • Published • 194
Function-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation Models
Paper • 2607.12463 • Published • 157
StartupBench: Benchmarking General-Purpose Agents on Market-Validated End-to-End Workflows
Paper • 2608.17800 • Published • 140
StudentSim: Training LLM-based Student Simulators
Paper • 2609.01591 • Published • 612
Dream-RSI: Recursive Self-Improvement through Evolving Worlds
Paper • 2609.14858 • Published • 333
RewardHarness: Self-Evolving Agentic Post-Training
Paper • 2605.08703 • Published • 240
VGI-Bench: Probing Visual Intelligence in Video Generation Models
Paper • 2608.19583 • Published • 333
Omni-IO Skills: Harnessing Your Agent Omni-Native
Paper • 2609.31847 • Published • 458
Dr. Claw: An AI Scientist Workspace for Vibe Research
Paper • 2609.00365 • Published • 408
liked 3
datasets 4 days ago