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 |
|---|---|---|---|---|
| Execution Governance Evaluation | 1 | 1 | Apr 28, 2026 | |
| Intake-task dialogue assessment | 1 | 1 | Feb 18, 2026 | |
| Speculative Decoding Acceleration | 1 | 1 | Feb 27, 2026 | |
| Social Experience Evaluation | 1 | 1 | Apr 28, 2026 | |
| Attribute-level Instruction Following | 1 | 1 | Feb 22, 2026 | |
| Interruption Robustness | 1 | 1 | Apr 28, 2026 | |
| Agentic Workflow Reconstruction | 1 | 1 | Feb 18, 2026 | |
| Deceptive Alignment / Surveillance Robustness |
| 1 |
| 1 |
| Apr 28, 2026 |
| Output conformance to revised specification | 1 | 1 | Apr 28, 2026 |
|---|
| Meta-cognitive Assessment | 1 | 1 | Feb 22, 2026 |
|---|
| Agentic Rollback and Planning | 1 | 1 | Apr 28, 2026 |
|---|
| Untargeted Question Answering | 1 | 1 | Apr 28, 2026 |
|---|
| Fact-checking Explanation Generation | 1 | 1 | Apr 28, 2026 |
|---|
| Consensus Ranking | 1 | 1 | Feb 18, 2026 |
|---|
| Clinical diagnosis and treatment reasoning | 1 | 1 | Apr 28, 2026 |
|---|
| Mathematics Competition | 1 | 2 | Jun 26, 2026 |
|---|
| Multi-objective RLHF alignment | 1 | 1 | Feb 22, 2026 |
|---|
| Embodied Decision-Grounded QA | 1 | 1 | Apr 28, 2026 |
|---|
| Dialogue System | 1 | 1 | Feb 18, 2026 |
|---|
| Medical Coaching Feedback Generation | 1 | 1 | Feb 18, 2026 |
|---|
| Democratic Preference Alignment | 1 | 1 | Feb 18, 2026 |
|---|
| Humor | 1 | 1 | Feb 22, 2026 |
|---|
| Preference-based Alignment | 1 | 1 | Apr 28, 2026 |
|---|
| LLM-relation detection | 1 | 1 | Feb 22, 2026 |
|---|
| Test-time Alignment | 1 | 1 | Apr 28, 2026 |
|---|