# Agentic Workflow Performance (Retry Loops) on SWE-bench + AutoGen Source: [Agentic Workflow Performance (Retry Loops) on SWE-bench + AutoGen]() Collection index: [llms.txt]() Data updated: 2026-05-08T11:17:08.271Z Evaluation of agentic workflow performance, specifically focusing on retry loop handling, using the SWE-bench dataset augmented with AutoGen configurations. 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 | Agentic Workflow Performance (Retry Loops) | | Dataset (including any stated split) | SWE-bench + AutoGen | | Metric | Latency (s) | | Unit | TIME | | Direction | Lower is better | | Results loaded | 8 of 8 | | 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 - [Latency (s)](): Lower is better; unit: TIME. - [TTFT (s)](): Lower is better; unit: TIME. - [Hit Rate (%)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Latency (s) | Result date | Report paper | | --- | --- | --- | --- | | Full PBKV | 118.61 | Not recorded | 69fd6e5c5497b3b670c89726 | | PBKV-HE | 141.53 | Not recorded | 69fd6e5c5497b3b670c89726 | | Full PBKV | 160.18 | Not recorded | 69fd6e5c5497b3b670c89726 | | PBKV-HE | 177.22 | Not recorded | 69fd6e5c5497b3b670c89726 | | PBKV-LAE | 177.5 | Not recorded | 69fd6e5c5497b3b670c89726 | | LRU | 214.74 | Not recorded | 69fd6e5c5497b3b670c89726 | | PBKV-LAE | 233.86 | Not recorded | 69fd6e5c5497b3b670c89726 | | LRU | 271.9 | Not recorded | 69fd6e5c5497b3b670c89726 | ### Full PBKV Latency (s): 118.61. Result ID: 69fdc62747f34ce924e1a94d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-14B"}. This record does not assert independent reproduction. ### PBKV-HE Latency (s): 141.53. Result ID: 69fdc62747f34ce924e1a94c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-14B"}. This record does not assert independent reproduction. ### Full PBKV Latency (s): 160.18. Result ID: 69fdc62747f34ce924e1a949. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-32B"}. This record does not assert independent reproduction. ### PBKV-HE Latency (s): 177.22. Result ID: 69fdc62747f34ce924e1a948. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-32B"}. This record does not assert independent reproduction. ### PBKV-LAE Latency (s): 177.5. Result ID: 69fdc62747f34ce924e1a94b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-14B"}. This record does not assert independent reproduction. ### LRU Latency (s): 214.74. Result ID: 69fdc62747f34ce924e1a94a. [Reporting paper]() Recorded evaluation configuration: {"Model":"Qwen3-14B"}. This record does not assert independent reproduction. ### PBKV-LAE Latency (s): 233.86. Result ID: 69fdc62747f34ce924e1a947. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-32B"}. This record does not assert independent reproduction. ### LRU Latency (s): 271.9. Result ID: 69fdc62747f34ce924e1a946. [Reporting paper]() Recorded evaluation configuration: {"Model":"Qwen3-32B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.