AI Paper Atlas

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

AlgoPilot: Cross-Paradigm Reasoning in Language Models via Strategy Selection and Guidance

Yilun Hao, Ruixiao Yang, Hudson Hilal, Yongchao Chen, Kaizhi Qian, Yada Zhu, Yang Zhang, Chuchu Fan

NeurIPS 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 AlgoPilot, a cross-paradigm reasoning framework that adaptively selects a problem-solving strategy and guides LLM solution formulation.

Problem

LLM reasoning across diverse domains (program synthesis, symbolic reasoning, planning, optimization) requires both identifying an appropriate solution paradigm and formulating it correctly.

Approach

A framework that adaptively selects among different solution paradigms and guides the LLM in formulating the chosen approach, rather than using a single fixed reasoning style.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add SteerLM+GuideLM cross-paradigm pipeline on top of Qwen3-8BQwen3-8B · cross-paradigm test setaverage accuracy: 38.4 -> 72.9Improved
refine SteerLM with GRPO after SFT (ablation)AlgoPilot SteerLM · cross-paradigm test setaverage accuracy: 67.2 -> 72.9Improved
use learned SteerLM instead of self-selected strategy (with GuideLM) (ablation)AlgoPilot · cross-paradigm test setaverage accuracy: 45.3 -> 72.9Improved
add GuideLM formulation guidance (with SteerLM) (ablation)AlgoPilot · cross-paradigm test setaverage accuracy: 45.7 -> 72.9Improved
add GuideLM guidance with self-selected strategy (ablation)Qwen3-8B · cross-paradigm test setaverage accuracy: 36.1 -> 45.3Improved
prompt Qwen3-8B to reason about approach first (Reason vs Direct)Qwen3-8B · cross-paradigm test setaverage accuracy: 38.4 -> 36.1Hurt
replace GuideLM with QA-SFT fine-tuned executor on same problems (ablation)AlgoPilot · cross-paradigm test setaverage accuracy: 72.9 -> 59.3Hurt
evaluate on paraphrased inputsAlgoPilot · cross-paradigm test setaverage accuracy: 72.9 -> 68.6Hurt
transfer trained SteerLM and GuideLM to Gemma-4-E4B-it executorGemma-4-E4B-it · cross-paradigm test setaverage accuracy: 50.8 -> 60.5Improved
add weighted lower-ranked candidate rewards S2, S3 to SteerLM reward (ablation)SteerLM GRPO · SteerLM reward designTop-3 accuracy: 77.13 -> 83.67Improved
add structural format and duplicate penalties to reward (ablation)SteerLM GRPO · SteerLM reward designValid-3: 94.8 -> 100.0Improved
add ranking bonus to reward (ablation)SteerLM GRPO · SteerLM reward designValid-3: 84.7 -> 94.8Improved

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