AI Paper Atlas

Research map / Reinforcement learning / RL from feedback

AlphaRouter: Token-level Routing Between SLM and LLM with Reinforcement Learning and Tree Search

Siteng Liao, Yuzhu Liang, Hengzhong Rao, Xizhao Luo, Tian Wang

ICML 2026 · Reinforcement learning › RL from feedback · approach: Scaling RL with verifiable rewards

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add TAPO-learned routing instead of routing to LLM at every predicted mismatch (ablation)AlphaRouter · GSM8K (~1.0B active params)accuracy (%): 64.50% -> 78.00%Improved
add TAPO-learned routing instead of mismatch-triggered routing (ablation)AlphaRouter · GSM8K (~1.0B active params)LLM call rate (%): 8.80% -> 6.45%Improved
add tree-advantage (sibling-branch) credit assignment instead of GRPO-style rollout objective (ablation)AlphaRouter · GSM8Kaccuracy (%)Improved
increase CITS path budget M from 16 to 32 (ablation)AlphaRouter · GSM8Kaccuracy (%): 86.00% -> 90.50%Improved
increase CITS expansion rounds N from 2 to 3 (M=32) (ablation)AlphaRouter · GSM8Kaccuracy (%): 89.50% -> 90.50%Improved
transfer router trained on 0.5B+7B to unseen 3B LLMAlphaRouter · GSM8K (0.5B+3B pair)accuracy (%): 86.0% -> 90.0%Improved
use AlphaRouter token routing instead of R2R at ~1.0B active paramsAlphaRouter · GSM8K (~1.0B active params)accuracy (%): 71.0% -> 78.0%Improved
use AlphaRouter at 91% accuracy instead of standalone Qwen-7B decodingAlphaRouter · GSM8K system efficiencylatency (s): 3.8420 -> 2.9459Improved
use AlphaRouter at 91% accuracy instead of standalone Qwen-7BAlphaRouter · GSM8K system efficiencycomputation (TFLOPs): 588.19 -> 259.92Improved
use AlphaRouter instead of speculative decoding at 91% accuracyAlphaRouter · GSM8K system efficiencycomputation (TFLOPs): 605.64 -> 259.92Improved

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