(chore) add agentic-sys and roundtrip
This commit is contained in:
+8
-8
@@ -49,13 +49,13 @@ The central structural decision, and the one the previous revision got wrong.
|
||||
```
|
||||
┌──────────────────────────────────────────────────────────┐
|
||||
│ DOMAIN — user-defined, data, versioned, hot-swappable │
|
||||
│ workflow definition · rubrics · verifiers · tools │
|
||||
│ workflow definition · rubrics · verifiers · tools │
|
||||
└──────────────────────────────────────────────────────────┘
|
||||
│ executed / graded by
|
||||
┌──────────────────────────────────────────────────────────┐
|
||||
│ KERNEL — framework-owned, compiled, exhaustively typed │
|
||||
│ attempt lifecycle · event log · intents · branches │
|
||||
│ scheduling · tournament · partitioning · tenancy │
|
||||
│ KERNEL — framework-owned, compiled, exhaustively typed │
|
||||
│ attempt lifecycle · event log · intents · branches │
|
||||
│ scheduling · tournament · partitioning · tenancy │
|
||||
└──────────────────────────────────────────────────────────┘
|
||||
```
|
||||
|
||||
@@ -1040,10 +1040,10 @@ the model calls, and that trade is now the user's to make explicitly rather than
|
||||
one the framework makes for them.
|
||||
|
||||
```
|
||||
[ G comparable episodes for one task, one outcome class ]
|
||||
[ G comparable episodes for one task, one outcome class ]
|
||||
│
|
||||
▼
|
||||
[ shuffle into brackets ] ◄── shuffling also cancels position bias
|
||||
[ shuffle into brackets ] ◄── shuffling also cancels position bias
|
||||
│
|
||||
▼
|
||||
┌─────────────────────────────────┐
|
||||
@@ -1051,10 +1051,10 @@ one the framework makes for them.
|
||||
└────────────────┬────────────────┘
|
||||
│
|
||||
▼
|
||||
[ Bradley-Terry fit over all comparisons ]
|
||||
[ Bradley-Terry fit over all comparisons ]
|
||||
│
|
||||
▼
|
||||
[ strength per episode + confidence interval ]
|
||||
[ strength per episode + confidence interval ]
|
||||
```
|
||||
|
||||
Swiss rather than round-robin: O(G log G) instead of O(G²). Eight episodes is
|
||||
|
||||
Reference in New Issue
Block a user