Removing the current task from the curator input lowers untrained JITMEM-base by up to 3.1 ALFWorld and 4.6 WebShop success-rate points; after RL training, the maximum drops widen to 11.4 and 10.4 points, which the paper interprets as evidence that RL learns to exploit the task signal.

Removing the current task from the curator input lowers untrained JITMEM-base by up to 3.1 ALFWorld and 4.6 WebShop success-rate points; after RL training, the maximum drops widen to 11.4 and 10.4 points, which the paper interprets as evidence that RL learns to exploit the task signal. · CiteArk

Measurement results

0/18 assessed

0 supported0 disputed or conflicting18 not assessed

The complete result group stays with its claim. Assessed rows come first; their judgments do not replace the whole-claim conclusion. Expand a row for conditions, sources, and evidence history.

Each row is a measurement with its reported value, latest available observation, and cumulative evidence state.
Reported	Latest observation	Evidence judgment
57.4 percentage points	—	Not assessed
25.3 points	—	Not assessed
7.1 percentage points	—	Not assessed
77.4 percentage points	—	Not assessed
51.2 points	—	Not assessed
41.8 percentage points	—	Not assessed
78.3 percentage points	—	Not assessed
44.2 points	—	Not assessed
34.8 percentage points	—	Not assessed
66 percentage points	—	Not assessed
49.6 points	—	Not assessed
22.4 percentage points	—	Not assessed

Removing the current task from the curator input lowers untrained JITMEM-base by up to 3.1 ALFWorld and 4.6 WebShop success-rate points; after RL training, the maximum drops widen to 11.4 and 10.4 points, which the paper interprets as evidence that RL learns to exploit the task signal.

Reported and observed measurements

Assessments (0)

Runs (0)

Measurement results