← Back to all news
arXiv Machine Learning By Pingchuan Ma, Rui Ding, Shuai Wang

Benchmarking and Enhancing Agentic Causal Discovery

Read the original on arXiv Machine Learning →

The paper introduces Heuresis, a benchmark of anonymous simulated datasets spanning linear Gaussian to heavy-tailed mechanisms, designed to evaluate how well LLM agents can perform causal discovery and improve upon existing algorithms. The benchmark tracks algorithmic gains versus data‑driven insights and records every edge an agent modifies. Using this benchmark, GPT‑6.1 Sol and Claude Opus 5.5 outperform the best existing algorithms on all six dataset families, with GPT‑6.1 Sol achieving a 14% adjacency F1 improvement on the hardest family.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
Oct 5

Mapping and Advancing the Scalability-Accuracy Frontier of Nonlinear Causal Discovery

The paper evaluates four main approaches to scalable nonlinear causal discovery—differentiable, amortized, score‑matching, and combinatorial search—highlighting their distinct accuracy‑runtime trade‑offs. It introduces SPADE, a spline‑based score‑evaluation method that compiles and reuses sufficient statistics, reducing combinatorial search complexity from O(nd³) to O(nd²+d³). Empirical results show SPADE dramatically extends the scalability‑accuracy frontier, solving large‑scale problems with high structural accuracy on both synthetic and real‑world data.

By Hendrik Suhr, Sascha Xu, Jilles Vreeken
benchmarks
More like this →
arXiv AI
Jun 3

CauTion: Knowing When to Trust LLMs for Ensemble Causal Discovery

arXiv:2606. 03602v1 Announce Type: cross Abstract: Causal discovery from observational data remains challenging due to the fundamental limitations of purely statistical methods, such as statistical distinguishability within equivalence classes and sensitivity to finite sample sizes.

By Bo Peng, Kaiwen Wu, Sirui Chen, Zhiheng Wang, Yu Qiao, Chaochao Lu
llms
More like this →
arXiv Machine Learning
Sep 11

CausalArena: Benchmarking Causal Discovery in the Foundation Model Era

CausalArena is a new benchmark designed to evaluate causal discovery methods in the era of foundation models. It unifies synthetic structural causal models (SCMs), semantically grounded SCMs, and formula‑grounded SCMs, while also including real‑world datasets for external validation. Experiments show that performance rankings vary widely across different SCM families and protocols, indicating that strong results on one benchmark do not necessarily transfer to others.

By Zi-Rong Li, Si-Yang Liu, Tian-Zuo Wang, Han-Jia Ye
benchmarks
More like this →