Loading the SOTA2 catalog…
SOTA2 Research · tasks
Explore the problems researchers are working on and the benchmarks used to measure progress.
| Task Name | Domain | Benchmarks | Papers | Last Update |
|---|---|---|---|---|
| Compound LLM Collaboration | 1 | 1 | Mar 9, 2026 | |
| Intra-shot prompt-following alignment | 1 | 1 | May 15, 2026 | |
| Compound AI System Alignment | 1 | 1 | Mar 9, 2026 | |
| Persona-grounded Dialogue | 1 | 1 | Feb 18, 2026 | |
| Compound LLM Collaboration System | 1 | 1 | Mar 9, 2026 | |
| AI Interruption Detection | 1 | 1 | May 18, 2026 | |
| HR Scenario Completion and Governance | 1 | 1 | May 18, 2026 | |
| Reasoning and Math Problem Solving | 1 | 1 | Feb 18, 2026 | |
| Citation |
| 1 |
| 1 |
| May 18, 2026 |
| Zero-shot Task Accuracy | 1 | 1 | Mar 9, 2026 |
|---|
| LLM Behavior | 1 | 1 | May 18, 2026 |
|---|
| Large Language Model Pre-training | 1 | 1 | Mar 9, 2026 |
|---|
| Kernel-level Attention Speed and Memory Analysis | 1 | 1 | May 18, 2026 |
|---|
| RL Training | 1 | 1 | May 18, 2026 |
|---|
| GRPO Training | 1 | 1 | May 18, 2026 |
|---|
| Counseling Quality | 1 | 1 | Feb 18, 2026 |
|---|
| E-commerce Shopping Assistance | 1 | 1 | Mar 9, 2026 |
|---|
| General Multitask Evaluation | 1 | 1 | May 18, 2026 |
|---|
| Multi-perspective Alignment | 1 | 1 | Mar 9, 2026 |
|---|
| Multi-task Reasoning and Efficiency | 1 | 1 | May 18, 2026 |
|---|
| Prompt Authoring | 1 | 1 | May 18, 2026 |
|---|
| Social agent strategy optimization | 1 | 1 | May 18, 2026 |
|---|
| Generative Modeling Efficiency | 1 | 1 | May 18, 2026 |
|---|
| Emotional Support Conversation Generation | 1 | 1 | Feb 18, 2026 |
|---|
| Question Answering Correctness | 1 | 1 | Feb 18, 2026 |
|---|