Tsinghua releases SRHarness and MechBench to test whether AI agents explain formulas
Original titleTsinghua's SRHarness Helps AI Agents Find Formulas, While MechBench Tests Whether They Grasp Why
AISummary
Tsinghua University's Data Science and Intelligence Lab released SRHarness, an open-source runtime for agentic symbolic regression, and MechBench, a benchmark for recovering the mechanisms behind formulas.
The papers report SRHarness reaching a 93.69% symbolic recovery rate on LSR-Transform versus 62.16% for SR-Scientist, while Codex with GPT-5.6-sol recovers mechanisms in only 13.75% of core-set cases against 35% for laws.
Source: Pandaily · pandaily.comPublished · added here