No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by deep-symbolic-mathematics · Agent Tool · ★ 267
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is LLM-SR safe to install? View the security audit →
: Scientific Equation Discovery and Symbolic Regression via Programming with LLMs Official Implementation of paper LLM-SR: Scientific Equation Discovery via Programming with Large Language Models (ICLR 2025 Oral). Updates Our recent more comprehensive benchmark LLM-SRBench: A New Benchmark for Scientific Equation Discovery with Large Language Models (to appear at ICML 2025 as Oral) is released following this work to effectively test LLM-based scientific equation discovery methods beyond memorization. Check out the benchmark data on huggingface and evaluation codes here. Overview In this paper, we introduce LLM-SR, a novel approach for scientific equation discovery and symbolic regression that leverages strengths of Large Language Models (LLMs). LLM-SR combines LLMs' scientific knowledge and code generation capabilities with evolutionary search to discover accurate and interpretable equations from d
| Stars | 267 |
| Forks | 51 |
| Language | Python |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 73.9784056248711/100 |
| Open Issues | 8 |
| Last Updated | 2025-07-31 |
| Created | 2024-04-19 |
| Platforms | python |
| Est. Tokens | ~598k |
These tools work well together with LLM-SR for enhanced workflows:
Looking for a LLM-SR alternative? If you're comparing LLM-SR with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
A Pair Programming Framework for Code Generation via Multi-Plan Exploration and Feedback-Driven Refinement, AS
Open-source autoresearch powered by autonomous coding agents. Run Claude Code, OpenCode, and Codex with gradin
[ICLR'25] BigCodeBench: Benchmarking Code Generation Towards AGI
Promptdesk is a tool designed for effectively creating, organizing, and evaluating prompts and large language
Open-source, local-first desktop AI research workbench for scientific computing with Python/R, MCP bioinformat
Low code tool to rapidly build and coordinate multi-agent teams
Explore other popular agent tool tools:
LLM-SR is [ICLR 2025 Oral] This is the official repo for the paper "LLM-SR" on Scientific Equation Discovery and Symbolic Regression with Large Language Models. It is categorized as a Agent Tool with 267 GitHub stars.
LLM-SR is primarily written in Python. It covers topics such as ai4code, ai4math, ai4science.
You can find installation instructions and usage details in the LLM-SR GitHub repository at github.com/deep-symbolic-mathematics/LLM-SR. The project has 267 stars and 51 forks, indicating an active community.
LLM-SR is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to LLM-SR on Agent Skills Hub include PairCoder, CORAL, bigcodebench. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: