AI Paper Atlas

Research map / Large language models / Agents, code and math

ARCANA: A Benchmark for Abstraction and Analogical Reasoning

Ruqi Chen, Wei Wang, Zilei Wang

NeurIPS 2026 · Large language models › Agents, code and math · approach: Inductive and abstract reasoning evaluation · 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.

Introduces ARCANA, a benchmark for far analogical reasoning between superficially dissimilar domains that share deep relational or structural similarity.

Problem

Few benchmarks explicitly test far analogical reasoning, i.e., mapping relational or structural similarities across superficially dissimilar domains.

Approach

A benchmark whose tasks require far analogical mappings from a source domain to a target domain that differ superficially but share deep relational structure.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use vision-language prompting instead of language-only chain-of-thought (ablation)Gemini 3 Pro · ARCANAaccuracy (-Typo): 23.92% -> 18.66%Hurt
use vision-language prompting instead of language-only chain-of-thought (ablation)GPT 5.2 · ARCANAaccuracy (+Typo): 40.19% -> 42.11% (+Typo); 38.28% -> 37.32% (-Typo)Mixed
combine language and vision-language setups (union of tasks solved) (ablation)LLM baselines · ARCANAaccuracy: GPT 5.2 -Typo 38.28% / 37.32% -> 48.33%Improved
correct analogy generated by the modelLLMs on pulley category · ARCANA pulley categoryanswer accuracy: GPT 0% vs Gemini 67%Improved
apply ConceptSIR (concept slippage, introspection, reflection) instead of direct promptingGemini 3 Pro + GPT 5.2 · ARCANA hard subset (17 tasks)tasks solved: solves 9/17 tasksImproved
provide only task visualization without matrices to Gemini 3 Pro inside ConceptSIR (ablation)ConceptSIR · pulley3 taskcorrect analogyHurt
increase reflection loop budget from 3 to 15 with GPT 5 (ablation)ConceptSIR with GPT 5 · bead_chain1 tasksolvedNo clear effect

Experimental setup

Benchmarks: ARCANA

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