AI Paper Atlas

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

Evaluating and Improving Tool-Augmented Computation-Intensive Math Reasoning

Beichen Zhang, Kun Zhou, Xilin Wei, Xin Zhao, Jing Sha, Shijin Wang, Ji-Rong Wen

NeurIPS 2023 · Large language models › Reasoning and chain of thought · approach: Chain-of-thought training and analysis · 9 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
DELI two-stage deliberation vs best baseline ReActDELI · CARPaccuracy (%): 64.11 -> 73.46Improved
DELI vs ReActDELI · Algebraaccuracy (%): 54.51 -> 59.65Improved
DELI vs ReActDELI · Counting & Probabilityaccuracy (%): 41.77 -> 39.03Hurt
DELI vs PHPDELI · Number Theoryaccuracy (%): 35.37 -> 33.15Hurt
add retrieved exemplars (Retrieval CoT vs Random CoT)CoT prompting · CARPaccuracy (%): 49.39 -> 63.93Improved
add tool interfaces (ReAct vs Random CoT)CoT prompting · CARPaccuracy (%): 49.39 -> 64.11Improved
ReAct-style interleaved reasoning vs PAL program generationtool-augmented prompting · CARPaccuracy (%): 40.00 -> 64.11Improved
iterate without two-stage deliberation (Iterative CoT vs Random CoT/Retrieval CoT) (ablation)Retrieval CoT · CARPaccuracy (%): 63.93 -> 61.27Hurt
iterate without two-stage deliberation (Iterative ReAct vs ReAct) (ablation)ReAct · CARPaccuracy (%): 64.11 -> 61.17Hurt
add DELI deliberation on top of ReAct (ablation)ReAct · Average of 7 datasetsaccuracy (%): 48.07 -> 50.85Improved
add DELI on top of CoT initialization (ablation)CoT prompting · CARP, Algebra, Counting & ProbabilityaccuracyImproved
increase maximum iteration turns for DELI (ablation)DELI · CARP, Algebra, PrealgebraaccuracyImproved

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