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 |
|---|---|---|---|---|
| few-shot question answering | 1 | 1 | Feb 18, 2026 | |
| Multi-task Language Modeling | 1 | 2 | Apr 28, 2026 | |
| Agentic Planning | 1 | 1 | Apr 16, 2026 | |
| SAE steering | 1 | 1 | Feb 20, 2026 | |
| Roleplay Personalization | 1 | 1 | Apr 20, 2026 | |
| End-to-end Dialogue Modelling | 1 | 2 | Feb 18, 2026 | |
| Procedure customization | 1 | 1 | Feb 18, 2026 | |
| Long-form QA Factuality Detection | 1 | 1 | Apr 20, 2026 | |
| Learning and Mastery in Text-Adventure Games |
| 1 |
| 1 |
| Apr 20, 2026 |
| Long Question Answering | 1 | 1 | Apr 20, 2026 |
|---|
| Memory Capacity | 1 | 1 | Feb 20, 2026 |
|---|
| LLM Pre-training | 1 | 1 | Apr 20, 2026 |
|---|
| Neighbor Domain Knowledge Preservation | 1 | 1 | Apr 20, 2026 |
|---|
| Multi-turn Multimodal Instruction-following | 1 | 1 | Feb 18, 2026 |
|---|
| Multiple Choice Evaluation | 1 | 1 | Feb 21, 2026 |
|---|
| Steering effectiveness correlation analysis | 1 | 1 | Apr 20, 2026 |
|---|
| Multi-agent social interaction evaluation | 1 | 1 | Apr 20, 2026 |
|---|
| Yes/No Reading Comprehension | 1 | 1 | Feb 18, 2026 |
|---|
| Scientific Intervention Generation Evaluation | 1 | 1 | Apr 20, 2026 |
|---|
| Multi-party negotiation | 1 | 1 | Apr 20, 2026 |
|---|
| Contextual Planning | 1 | 1 | Apr 20, 2026 |
|---|
| Proactive Seeking | 1 | 1 | Apr 20, 2026 |
|---|
| Abductive Reasoning Generation | 1 | 1 | Feb 18, 2026 |
|---|
| Conversational Style Question Answering | 1 | 1 | Feb 18, 2026 |
|---|
| Result Feedback | 1 | 1 | Apr 20, 2026 |
|---|