# Multi-agent steering on Synthetic Multi-agent Scenarios Source: [Multi-agent steering on Synthetic Multi-agent Scenarios]() Collection index: [llms.txt]() Data updated: 2026-04-10T08:20:55.787Z Evaluation of model performance on multi-agent steering tasks within the Synthetic Multi-agent Scenarios environment, measured by accuracy and performance delta. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Multi-agent steering | | Dataset (including any stated split) | Synthetic Multi-agent Scenarios | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 16 of 16 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Accuracy](): Higher is better; unit: PERCENT. - [Performance Delta (pp)](): Higher is better; unit: SCALAR. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | DACS | 98.4 | Not recorded | 69d883fb7d0172140ec77999 | | DACS | 96.7 | Not recorded | 69d883fb7d0172140ec77999 | | DACS | 96.7 | Not recorded | 69d883fb7d0172140ec77999 | | DACS | 96 | Not recorded | 69d883fb7d0172140ec77999 | | DACS | 94 | Not recorded | 69d883fb7d0172140ec77999 | | DACS | 94 | Not recorded | 69d883fb7d0172140ec77999 | | DACS | 90.2 | Not recorded | 69d883fb7d0172140ec77999 | | DACS | 90 | Not recorded | 69d883fb7d0172140ec77999 | | Baseline | 60 | Not recorded | 69d883fb7d0172140ec77999 | | Baseline | 56.7 | Not recorded | 69d883fb7d0172140ec77999 | | Baseline | 52.5 | Not recorded | 69d883fb7d0172140ec77999 | | Baseline | 44.2 | Not recorded | 69d883fb7d0172140ec77999 | | Baseline | 38.7 | Not recorded | 69d883fb7d0172140ec77999 | | Baseline | 37 | Not recorded | 69d883fb7d0172140ec77999 | | Baseline | 34.8 | Not recorded | 69d883fb7d0172140ec77999 | | Baseline | 21 | Not recorded | 69d883fb7d0172140ec77999 | ### DACS Accuracy: 98.4. Result ID: 69d8b2e547f34ce924c17898. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Phase":"3","Scenario":"s8\_n3\_dense\_d3","N":"3","D":"15"}. This record does not assert independent reproduction. ### DACS Accuracy: 96.7. Result ID: 69d8b2e547f34ce924c1788a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Phase":"1","Scenario":"s1\_n3","N":"3","D":"≈3"}. This record does not assert independent reproduction. ### DACS Accuracy: 96.7. Result ID: 69d8b2e547f34ce924c1788c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Phase":"1","Scenario":"s2\_n5","N":"5","D":"≈3"}. This record does not assert independent reproduction. ### DACS Accuracy: 96. Result ID: 69d8b2e547f34ce924c17892. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Phase":"2","Scenario":"s5\_n5\_crossfire","N":"5","D":"4"}. This record does not assert independent reproduction. ### DACS Accuracy: 94. Result ID: 69d8b2e547f34ce924c17894. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Phase":"2","Scenario":"s6\_n5\_cascade","N":"5","D":"3"}. This record does not assert independent reproduction. ### DACS Accuracy: 94. Result ID: 69d8b2e547f34ce924c17896. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Phase":"3","Scenario":"s7\_n5\_dense\_d2","N":"5","D":"8"}. This record does not assert independent reproduction. ### DACS Accuracy: 90.2. Result ID: 69d8b2e547f34ce924c17890. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Phase":"2","Scenario":"s4\_n3\_homogeneous","N":"3","D":"4"}. This record does not assert independent reproduction. ### DACS Accuracy: 90. Result ID: 69d8b2e547f34ce924c1788e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Phase":"1","Scenario":"s3\_n10","N":"10","D":"≈3"}. This record does not assert independent reproduction. ### Baseline Accuracy: 60. Result ID: 69d8b2e547f34ce924c1788b. [Reporting paper]() Recorded evaluation configuration: {"Phase":"1","Scenario":"s1\_n3","N":"3","D":"≈3"}. This record does not assert independent reproduction. ### Baseline Accuracy: 56.7. Result ID: 69d8b2e547f34ce924c17895. [Reporting paper]() Recorded evaluation configuration: {"Phase":"2","Scenario":"s6\_n5\_cascade","N":"5","D":"3"}. This record does not assert independent reproduction. ### Baseline Accuracy: 52.5. Result ID: 69d8b2e547f34ce924c17891. [Reporting paper]() Recorded evaluation configuration: {"Phase":"2","Scenario":"s4\_n3\_homogeneous","N":"3","D":"4"}. This record does not assert independent reproduction. ### Baseline Accuracy: 44.2. Result ID: 69d8b2e547f34ce924c17899. [Reporting paper]() Recorded evaluation configuration: {"Phase":"3","Scenario":"s8\_n3\_dense\_d3","N":"3","D":"15"}. This record does not assert independent reproduction. ### Baseline Accuracy: 38.7. Result ID: 69d8b2e547f34ce924c1788d. [Reporting paper]() Recorded evaluation configuration: {"Phase":"1","Scenario":"s2\_n5","N":"5","D":"≈3"}. This record does not assert independent reproduction. ### Baseline Accuracy: 37. Result ID: 69d8b2e547f34ce924c17893. [Reporting paper]() Recorded evaluation configuration: {"Phase":"2","Scenario":"s5\_n5\_crossfire","N":"5","D":"4"}. This record does not assert independent reproduction. ### Baseline Accuracy: 34.8. Result ID: 69d8b2e547f34ce924c17897. [Reporting paper]() Recorded evaluation configuration: {"Phase":"3","Scenario":"s7\_n5\_dense\_d2","N":"5","D":"8"}. This record does not assert independent reproduction. ### Baseline Accuracy: 21. Result ID: 69d8b2e547f34ce924c1788f. [Reporting paper]() Recorded evaluation configuration: {"Phase":"1","Scenario":"s3\_n10","N":"10","D":"≈3"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.