AI Paper Atlas

Research map / Large language models / Reasoning and chain of thought

AdaReason: Progressive Training of Multi-LoRA Adapters for Budget-Adaptive Language Reasoning Models

Jiacheng Wang, Tianle Chen, Pengyu Cheng, Xiaofeng Hou, Jiacheng Liu

AAAI 2026 · Large language models › Reasoning and chain of thought · approach: Efficient and adaptive thinking · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes AdaReason, a progressive training scheme for multiple LoRA adapters that lets a single reasoning model adapt its chain-of-thought length to a user-specified compute budget.

Problem

Large reasoning models face a trade-off between efficiency and accuracy; existing methods either lack user-specified computational budget support or require maintaining multiple independent models.

Approach

Progressively trains multiple LoRA adapters on a shared base reasoning model so that a single deployed model supports budget-adaptive reasoning, avoiding separate models per budget level.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use multi-LoRA adapters with progressive training instead of L1-MaxDeepScaleR-1.5B · GPQA+HumanEval avgaccuracy: 57.3 -> 58.5Improved
budget-weighted adapter merging vs naive pairwise merging at shortest budget (ablation)AdaReason · Math avgaccuracy: 53.9 -> 55.5Improved
budget-weighted merging vs naive pairwise merging at longest budget (ablation)AdaReason · Math avgaccuracy: 61.3 -> 61.0No clear effect
budget-weighted merging vs naive pairwise merging at medium budgets (ablation)AdaReason · Math avgaccuracy: 59.9 -> 59.6 (T2/T3), 57.6 -> 58.0 (T3/T4)Mixed
tighten budget progressively, shorter adapter (T5 vs T1) (ablation)AdaReason · GPQA+HumanEval avgaccuracy: 59.3 -> 57.9Hurt
compare AdaReason adapters against unconstrained modelDeepScaleR-1.5B · GPQA+HumanEval avggeneration length: 5047.3 -> 4196.3 (T1)Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy