The paper introduces SRHarness, a domain-specific runtime harness for agentic symbolic regression that provides three key mechanisms: composable scientific actions (a common interface over raw, transformed, and candidate-derived quantities), persistent scientific state (retaining evaluated hypotheses with compact views), and trajectory lifecycle management (coordinating continuation, branching, restart, and termination). Evaluated on the LLM-SRBench benchmark using the DeepSeek-v4-flash-0731 LLM backbone, SRHarness achieved 93.69% symbolic accuracy on the LSR-Transform dataset, compared to 62.16% for the SR-Scientist baseline, and retained 72.97% accuracy on an anonymized variant versus 39.64% for SR-Scientist. These results demonstrate that structured runtime support matters as much as model and tool choice.
Structured agent harnesses improve LLM-driven discovery of symbolic equations
SRHarness organizes scientific operations, hypothesis history, and search trajectories, improving equation recovery without changing the underlying language model.
BNRist · Tsinghua University
In one line
SRHarness, a structured runtime harness, improves agentic symbolic regression accuracy via composable actions, persistent state, and trajectory lifecycle management.
Before you read this
Three ideas this paper builds onThe authors developed SRHarness around three components: composable scientific actions for analyzing data and candidate equations, persistent state for retaining evaluated hypotheses, and lifecycle management for continuing, branching, restarting, or terminating search trajectories.
How it works
stage by stageThe Daily Edition
The front page in your inbox each weekday morning: the lead, the picks, and why each one earned its place.