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 |
|---|---|---|---|---|
| Single-Turn User Simulation | 1 | 1 | Mar 20, 2026 | |
| Context-faithful Reasoning | 1 | 1 | Feb 18, 2026 | |
| Factual Retention | 1 | 1 | Feb 19, 2026 | |
| Financial Instruction Following | 1 | 1 | Mar 20, 2026 | |
| Memorability Feedback Generation | 1 | 1 | Mar 20, 2026 | |
| Multi-ability model merging | 1 | 1 | Feb 19, 2026 | |
| Feedback Quality Evaluation | 1 | 1 | Mar 20, 2026 | |
| Conversational Visual QA | 1 | 1 | Feb 18, 2026 | |
| Human Preference Assessment |
| 1 |
| 1 |
| Mar 20, 2026 |
| Interruption Handling | 1 | 3 | Apr 15, 2026 |
|---|
| Proactive Response Timing | 1 | 1 | Mar 20, 2026 |
|---|
| Conversational AI Evaluation | 1 | 5 | May 8, 2026 |
|---|
| Role Adherence and Instruction Following | 1 | 1 | Feb 19, 2026 |
|---|
| Proactive Response | 1 | 1 | Mar 20, 2026 |
|---|
| Constraint Verification | 1 | 1 | Mar 20, 2026 |
|---|
| Arithmetic Problem Solving | 1 | 2 | Feb 19, 2026 |
|---|
| LLM Safety Assessment | 1 | 1 | Feb 19, 2026 |
|---|
| Multi-agent assistant system evaluation | 1 | 1 | Mar 23, 2026 |
|---|
| Memory-Driven Role-Play | 1 | 1 | Mar 23, 2026 |
|---|
| Deliberation Summarization | 1 | 2 | Apr 23, 2026 |
|---|
| Hallucination Detection (Dialogue) | 1 | 1 | Mar 23, 2026 |
|---|
| Logical Puzzles | 1 | 2 | Feb 19, 2026 |
|---|
| Hallucination Detection (Math Word Problems) | 1 | 1 | Mar 23, 2026 |
|---|
| Hallucination Detection (Self-contradictory Hallucinations) | 1 | 1 | Mar 23, 2026 |
|---|
| Language-conditioned long-horizon robot manipulation | 1 | 1 | Feb 18, 2026 |
|---|