learn-per-module-merge-ratios-length-aware-reward TEC-0277 · proposedLearn per-module merge ratios with a length-aware reward
Freeze a reasoning model and an instruction model of identical architecture, assign one sigmoid-bounded interpolation ratio per module, and update only those scalars with GRPO-style rollouts rewarded for correct and comparatively short answ
Proposed. Filed by the drafting stage because a paper introduces or tests it. Nobody has vouched for it. The claim drafted from that paper is its first evidence, and what the paper used to validate it is in that claim’s source note. Say whether it held up for you, below.
Freeze a reasoning model and an instruction model of identical architecture, assign one sigmoid-bounded interpolation ratio per module, and update only those scalars with GRPO-style rollouts rewarded for correct and comparatively short answ Filed by the drafting stage from GRIP: Granular Reward-Guided Parameter Interpolation for Efficient Reasoning (2608.25583) with status proposed: the paper introduces or tests it, and the claim drafted from the paper is its first evidence. The paper validated it by: Accuracy and average generated tokens on AIME25, MATH500, GSM8K, GPQA-D and LiveCodeBench against the two source models, five fixed-ratio merging methods at coefficient 0.8, and CMA-ES matched on prompts, search space and objective: 76.5 average accuracy at 73.0% of Thinking's token count versus 76.0/100% for Thinking and 76.5/85.4% for SLERP.. Nobody has vouched for it; add support or contest it on this page.
Does it work?
nothing measured0 supporting · 0 contesting sources
Efficacy claims — what this technique actually moves, under which conditions, and whether that has been contested.
No efficacy claim filed yet. The technique is catalogued; whether it moves the capability, and when, is a separate assertion that needs its own sources.
No search recorded either, so this says nothing about the literature — only that nobody has looked here yet.
Code
No repository linked yet. Contribute one.
Sources
Whether a technique works is a claim. What you file here becomes a claim about this technique under the capability it addresses, with your evidence as its source, and moves the standing above the same way a paper would.