Research Idea Arena
What should come after your paper?
Two anonymous models propose follow-up ideas. Steer them, then vote for the better one.
Add your paper
arXiv or DOI link, a title, or a PDF
Blind
Start battle
Next step
Open problem
New angle
Combine
YOUR PAPER
A
Model A
hidden
B
Model B
hidden
No paper at hand? Try one from this year
Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces
Mike A. Merrill et al.
World Action Models are Zero-shot Policies
Seonghyeon Ye et al.
Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models
Siyan Zhao et al.
Meta-Harness: End-to-End Optimization of Model Harnesses
Yoonho Lee et al.
Towards End-to-End Automation of AI Research
Yutaro Yamada et al.
LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
Lucas Maes et al.
Self-Distillation Enables Continual Learning
Idan Shenfeld et al.
DFlash: Block Diffusion for Flash Speculative Decoding
Jian Chen et al.
SimpleMem: Efficient Lifelong Memory for LLM Agents
Jiaqi Liu et al.
Generative Modeling via Drifting
Mingyang Deng et al.
Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces
Mike A. Merrill et al.
World Action Models are Zero-shot Policies
Seonghyeon Ye et al.
Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models
Siyan Zhao et al.
Meta-Harness: End-to-End Optimization of Model Harnesses
Yoonho Lee et al.
Towards End-to-End Automation of AI Research
Yutaro Yamada et al.
LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
Lucas Maes et al.
Self-Distillation Enables Continual Learning
Idan Shenfeld et al.
DFlash: Block Diffusion for Flash Speculative Decoding
Jian Chen et al.
SimpleMem: Efficient Lifelong Memory for LLM Agents
Jiaqi Liu et al.
Generative Modeling via Drifting
Mingyang Deng et al.