Skip to content

armgit / ruflo

Public Imported from GitHub
0

🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated

darwin: iter 17 β€” scifact validated +1.3% from stacked iters 1-14

ruv3d5c1be0a2f1
diff --git a/docs/benchmarks/runs/beir-scifact-hybrid-rrf-latest.json b/docs/benchmarks/runs/beir-scifact-hybrid-rrf-latest.json
index 3f2eccd54a..e38b42d6a3 100644
--- a/docs/benchmarks/runs/beir-scifact-hybrid-rrf-latest.json
+++ b/docs/benchmarks/runs/beir-scifact-hybrid-rrf-latest.json
@@ -1,19 +1,19 @@
{
- "runAt": "2026-05-30T21:59:27.327Z",
+ "runAt": "2026-06-26T21:49:37.378Z",
"benchmark": "beir-scifact-hybrid",
"dataset": "scifact",
"pipeline": "BM25+BGE RRF",
"bgeModel": "Xenova/bge-base-en-v1.5",
- "rrfK": 60,
+ "rrfK": 40,
"rerank": false,
"queries": 300,
"corpusSize": 5183,
"metrics": {
- "ndcg10": 0.5694059569922902,
- "mrr10": 0.5392526455026454,
- "recall10": 0.6871666666666666,
- "recall100": 0.9543333333333334,
- "avgQueryLatencyMs": 442.59461027666663
+ "ndcg10": 0.5765772269258473,
+ "mrr10": 0.5427248677248677,
+ "recall10": 0.7054999999999999,
+ "recall100": 0.9510000000000001,
+ "avgQueryLatencyMs": 313.86981944333337
},
"perQuery": [
{
@@ -795,16 +795,16 @@
},
{
"qid": "532",
- "ndcg10": 0,
- "mrr10": 0,
- "recall10": 0,
+ "ndcg10": 0.3010299956639812,
+ "mrr10": 0.1111111111111111,
+ "recall10": 1,
"recall100": 1
},
{
"qid": "533",
- "ndcg10": 0,
- "mrr10": 0,
- "recall10": 0,
+ "ndcg10": 0.3010299956639812,
+ "mrr10": 0.1111111111111111,
+ "recall10": 1,
"recall100": 1
},
{
@@ -984,9 +984,9 @@
},
{
"qid": "641",
- "ndcg10": 0.3065735963827292,
+ "ndcg10": 0.5,
"mrr10": 0.3333333333333333,
- "recall10": 0.5,
+ "recall10": 1,
"recall100": 1
},
{
@@ -1012,8 +1012,8 @@
},
{
"qid": "660",
- "ndcg10": 0.3010299956639812,
- "mrr10": 0.1111111111111111,
+ "ndcg10": 0.38685280723454163,
+ "mrr10": 0.2,
"recall10": 1,
"recall100": 1
},
@@ -1166,9 +1166,9 @@
},
{
"qid": "768",
- "ndcg10": 0,
- "mrr10": 0,
- "recall10": 0,
+ "ndcg10": 0.3010299956639812,
+ "mrr10": 0.1111111111111111,
+ "recall10": 1,
"recall100": 1
},
{
@@ -1491,7 +1491,7 @@
"ndcg10": 0,
"mrr10": 0,
"recall10": 0,
- "recall100": 1
+ "recall100": 0
},
{
"qid": "982",
@@ -1572,8 +1572,8 @@
},
{
"qid": "1049",
- "ndcg10": 0.3010299956639812,
- "mrr10": 0.1111111111111111,
+ "ndcg10": 0.31546487678572877,
+ "mrr10": 0.125,
"recall10": 1,
"recall100": 1
},
@@ -1593,8 +1593,8 @@
},
{
"qid": "1088",
- "ndcg10": 0.38685280723454163,
- "mrr10": 0.2,
+ "ndcg10": 0.5,
+ "mrr10": 0.3333333333333333,
"recall10": 1,
"recall100": 1
},
@@ -1754,8 +1754,8 @@
},
{
"qid": "1196",
- "ndcg10": 0.2890648263178879,
- "mrr10": 0.1,
+ "ndcg10": 0.38685280723454163,
+ "mrr10": 0.2,
"recall10": 1,
"recall100": 1
},
@@ -1915,22 +1915,22 @@
},
{
"qid": "1278",
- "ndcg10": 0,
- "mrr10": 0,
- "recall10": 0,
+ "ndcg10": 0.3562071871080222,
+ "mrr10": 0.16666666666666666,
+ "recall10": 1,
"recall100": 1
},
{
"qid": "1279",
- "ndcg10": 0,
- "mrr10": 0,
- "recall10": 0,
+ "ndcg10": 0.3010299956639812,
+ "mrr10": 0.1111111111111111,
+ "recall10": 1,
"recall100": 1
},
{
"qid": "1280",
- "ndcg10": 0.2890648263178879,
- "mrr10": 0.1,
+ "ndcg10": 0.3010299956639812,
+ "mrr10": 0.1111111111111111,
"recall10": 1,
"recall100": 1
},
@@ -1950,8 +1950,8 @@
},
{
"qid": "1290",
- "ndcg10": 0.3562071871080222,
- "mrr10": 0.16666666666666666,
+ "ndcg10": 0.43067655807339306,
+ "mrr10": 0.25,
"recall10": 1,
"recall100": 1
},
diff --git a/docs/darwin/log.jsonl b/docs/darwin/log.jsonl
index 2f60b8ef4b..97ac1032fd 100644
--- a/docs/darwin/log.jsonl
+++ b/docs/darwin/log.jsonl
@@ -15,3 +15,4 @@
{"iter":14,"ts":"2026-06-26T21:26:36.293Z","dimension":"beir-nfcorpus","change":"nfcorpus-bm25-weight-0.2-to-0.0","measured":{"ndcg10":0.3517,"prior":0.3489},"deltaScore":0.0028,"action":"measured-improved","commit":"da6bc0ba7","note":"Pure dense fusion (bm25=0.0). Cumulative iter 1-14: 0.3282 β†’ 0.3517 (+0.0235, +7.2% rel). Gap to SOTA 0.380 closed from 0.052 β†’ 0.0283 (45% gap-closure). Rank still 2."}
{"iter":15,"ts":"2026-06-26T21:35:55.540Z","dimension":"beir-nfcorpus","change":"adaptive-rrf-k-40-to-20","measured":{"ndcg10":0.3517,"prior":0.3517},"deltaScore":0,"action":"noImprovement","commit":"","note":"k=20 vs k=40 identical for pure-dense fusion (single system, k cancels out of ordering). Reverted. nfcorpus champion 0.3517 stands. Halt counter: 1 of 3."}
{"iter":16,"ts":"2026-06-26T21:46:41.956Z","dimension":"beir-nfcorpus","change":"bge-query-prefix-scientific","measured":{"ndcg10":0.2961,"prior":0.3517},"deltaScore":-0.0556,"action":"noImprovement","commit":"","note":"Adding BGE-EN task prefix to queries shifted query embedding space without re-embedding docs β†’ mismatch. Reverted code + restored latest file. Halt counter: 2 of 3."}
+{"iter":17,"ts":"2026-06-26T21:50:15.109Z","dimension":"beir-scifact","change":"validate-stacked-iters-1-14-on-scifact","measured":{"ndcg10":0.5766,"baseline":0.5694},"deltaScore":0.0072,"action":"measured-improved","commit":"","note":"Stacked iters 1-14 generalize: scifact 0.5694 β†’ 0.5766 (+0.0072, +1.3% rel). Rank still 10 vs SOTA 0.74. Gap closed 0.1706 β†’ 0.1634. Validates the adaptive RRF k + min-max norm + adaptive candidate pool changes are dataset-agnostic (no per-dataset weights for scifact yet β€” that would be the next optimization)."}