AI Paper Atlas

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

LLM Priors for ERM over Programs

Shivam Singhal, Priyadarsi Mishra, Eran Malach, Tomer Galanti

ICML 2026 · Large language models › Agents, code and math · approach: Execution-based code verification · 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
add tool use (code execution) to the loop (ablation)LLM-PV with GPT-5-Thinking · Pattern1 (n=100)test accuracy (%): 78.4 -> 100Improved
add tool use (code execution) to the loop (ablation)LLM-PV with GPT-5-Thinking · Pattern2 (n=100)test accuracy (%): 64.7 -> 100Improved
add tool use (code execution) to the loop (ablation)LLM-PV with GPT-5-Thinking · Dyck-2 (n=100)test accuracy (%): 79.9 -> 100Improved
add tool use (code execution) to the loop (ablation)LLM-PV with GPT-5-Thinking · IsPrime+47 (n=100)test accuracy (%): 64.0 -> 80.6Improved
add tool use (code execution) to the loop (ablation)LLM-PV with GPT-5-Thinking · CycleCount (n=100)test accuracy (%): 51.0 -> 96.9Improved
add tool use (ablation)LLM-PV with GPT-5-Thinking · FP (n=100)test accuracy (%): 100 -> 100No clear effect
add tools to direct in-context predictionICL with GPT-5-Thinking · FP (n=100)test accuracy (%): 82.0 -> 99.0Improved
add tools to direct in-context predictionICL with GPT-5-Thinking · FHP (n=100)test accuracy (%): 66.0 -> 88.0Improved
add tools to direct in-context predictionICL with GPT-5-Thinking · 10-P (n=100)test accuracy (%): 47.0 -> 79.0Improved
replace tool-augmented ICL with tool-augmented LLM-PVGPT-5-Thinking with tools · Pattern1 (n=100)test accuracy (%): 51.0 -> 100Improved
fine-tune pretrained LM instead of training from scratch1B-scale LMs · Pattern1 (n=100)test accuracy (%): 51.5 -> 61.5Improved
scale SGD training set from 10 to 100k examplesfrom-scratch LM · 10-P / CAPtest accuracy (%): test accuracy near 50%No clear effect

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