AI Paper Atlas

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

Abductive Reasoning with Probabilistic Commonsense

Joseph Cotnareanu, Chiara Roverato, Han Zhou, Didier Chételat, Yingxue Zhang, Mark Coates

ICML 2026 · Large language models › Agents, code and math · approach: Mathematical and structural reasoning benchmarks · 0 citations (OpenAlex)

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
use score-minimizing sampling (model-count score) instead of text-based informativeness beam searchIf-Beam · FOLIO (Llama 3 8B)accuracy: 74% -> 82%Improved
same swap on QUAILIf-Beam · QUAIL (Llama 3 8B)accuracy: 74% -> 80%Improved
PACS vs text-based heuristic search on CosmosQAIf-Beam · CosmosQA (Llama 3 8B)accuracy: 82% -> 82%No clear effect
PACS vs commonsense-clause sampling ARGOSARGOS · FOLIO (Llama 3 8B)accuracy: 78% -> 82%Improved
PACS vs self-consistency with 20 samplesSC-20 · FOLIO (Llama 3.3 70B)accuracy: 77% -> 88%Improved
minimize model-count score to choose steps (ablation)PACS · FOLIO, QUAIL, CosmosQA (Llama 3 8B)average path length: 6.7 -> 4.6 (FOLIO)Improved
aggregate over diverse sampled commonsense pathsPACS · FOLIO (Llama 3 8B)% problems never sampled correct: 16% -> 3% (vs If-Beam)Improved
use PACS with small non-thinking model instead of SC with thinking modelPACS Llama 3.3 70B · FOLIOaccuracy: 82% -> 88% (vs SC GPT-OSS-120B)Improved
PACS with Llama 3 8B vs thinking 120B modelPACS Llama 3 8B · FOLIOaccuracy: 82% vs 82%No clear effect
LLM-generated steps without guidanceCOT · FOLIOscore progressionHurt

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