Research hub
Communication-efficient RLVR
The two-circuit GRPO research hub — weekly status, curated reports, and the full run record.
Most important tab
Weekly Update
The current readout for people who only have time for one page.
The two-circuit method beyond GSM8K: harder math and correct base models
On harder math the cheap projection lever is worthless, but the two-circuit correction does not collapse as long as the anchor stays fresh. And on a correct math-distilled base with 16k reasoning, both variants hold the dense line. The trajectories look random step to step and still pay off by the end.
Curated evidence
Essential Reports
Only the reports that carry the current decision chain are copied into this repo.
Same Rank-1, Different Projectability - What Breaks from GSM8K to Big-Math
Decomposes the two tasks. The rank-1 spatial structure only dents (EVR₁ ~90-96% on both), but forward linear projectability collapses (op ratio 0.90 → 1.00). Reconciled by two timescales: the cumulative direction is stable on both, while raw per-step updates align only on GSM8K (0.86 vs 0.15). Rank-1 is necessary but not sufficient for projection.
Rank-1 Trajectories on a Harder Task - Big-Math vs GSM8K
Re-runs the rank-1 analysis on Big-Math (EXP-58). Rank-1 structure replicates, but the single line's durability degrades on the harder task: ~6× more of the move lands off the line (25% vs 4.5%) and the direction rotates further over the run (|cos| 0.46 vs 0.64).
Big-Math signed-EMA (α, β) sweep - how much correction, how fresh an anchor?
Seven communication-efficient runs varying the merger's correction weight α and anchor-memory β, plus a dense control. α=0.25 with a fresh anchor (β=0.00) is the stable winner; only the stalest anchor (β=0.90) collapses. Dense stays the ceiling.
Big-Math Training Reward - Does Weight Projection Help?
Live training on Big-Math: no compressed variant beats dense, and plain stale signed EMA every step (no projection) beats every projection variant. A GSM8K appendix shows the coherent-trajectory contrast that explains why.
MOAT Projector Verdict - ANCHOR/FAST from GSM8K to Big-Math
Integration rollup for the projector lanes. Fixed damped-linear wins on GSM8K, but is not adopted as a universal default because Big-Math collapses to do-nothing.
Math-only Projector Ablation
EXP-61 confirms the harder Math trace is only marginally projectable at the freshest anchor and do-nothing-optimal at operational staleness.
Rank-1 Trajectory Family on the EXP-57 Trace
RELEX-style rank-1 structure replicates, but the paper form is the wrong objective for short-horizon staleness repair. Use rank-1 as position state, not blind extrapolation.
LA-WARMUP-V2 - PP-GRPO at 20/20 Without Collapse
Live training result for communication-efficient pipeline-parallel GRPO at longer cadence, useful as the bridge from offline projection geometry to end-to-end stability.