Murano is an open source framework for designing, running, and reproducing mechanistic interpretability studies of large language models, intended for researchers across disciplines and builds on existing interpretability and machine learning libraries.
Abstract
This paper presents Murano, an open source framework for designing, running, and reproducing mechanistic interpretability studies of large language models, intended for researchers across disciplines. These studies often combine loading, recording, attribution, intervention, and evaluation, while existing libraries tend to focus on different parts of this workflow. As a result, researchers using several libraries may need to adapt outputs from one for use by another. To bridge this gap, Murano represents operations from these five areas as composable steps. Steps exchange named result artifacts and declare the inputs they require and the outputs they produce. A pipeline executes its steps in the order supplied, and Murano uses canonical addresses when component identities pass between operations. Murano builds on existing interpretability and machine learning libraries. We demonstrate Murano through two reproductions of established interpretability studies and one illustrative sparse autoencoder case study.
ReFigBench, a benchmark and evaluation framework built on 1,000 real overview figures retrieved from arXiv papers with full provenance, is introduced, exposing the tension between fidelity and editability as the central challenge for practical multimodal document agents.
Li-Yang Fan, Chi Wei, Yi-Tai Li et al.· 0 citations
Together, these results recast the evolved harness as a legible compensation layer, shaped jointly by the language's engineering demands and the model's behavioral gaps, rather than an opaque benchmark-tuned scaffold.
Siqi Yang, Qianlan Yang, Yu-Xiong Wang et al.· 2 citations
This work presents a series of architectural improvements and feature enhancements to AquiLLM, including local embedding and reranking, multimodal capabilities, OpenAI-compatible inference interfaces, user interface improvements, semantic and episodic memory capabilities, and skills support.
J. Stark, S. Saikrishnan, Vikram Seenivasan et al.· 1 citation
The Stream Recursion Model is introduced, a modification of the Hierarchical Reasoning Model designed to expose internal computational structure while remaining scalable and achieves performance comparable to GPT-2 on a per-parameter basis.
Asael Sorensen, Charles Brock, D. Chamberlain et al.· arXiv.org· 0 citations
Praxist is introduced, a lineage-centered generational system that converts reproducible artifacts and evaluator outcomes into a typed evidence graph of findings, lane-structured frontiers, and agendas, and Separating local artifact construction from cohort-level evidence synthesis lets later attempts inherit validated...
Jin Li, Ahmed Murtadha, Zhiying Wang et al.· 0 citations
Meta-Harness is presented, a system that casts harness design as search over three per-domain objectives (accuracy, behavioural safety, and token cost) solved by an agentic proposer (Claude Code) with full filesystem access to prior harness source, execution traces, and scoring artifacts.
Subhojyoti Mukherjee, Mahmud Tanjim· 1 citation
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduNov 20, 2026
Senior Research Scientist Jim Glass discusses how his MIT-IBM Computing Research Lab collaboration connects perception and language, and addresses the shortcoming of current models.
MIT News · Artificial Intelligence· news.mit.eduNov 19, 2026
An MIT and Dana-Farber Institute-led team used large language models to examine nearly 4,000 studies and hundreds of code repositories, revealing gaps in the information needed to scrutinize and reuse published research.
By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.