lrm

A Survey of Reinforcement Learning for Large Reasoning Models

Democratizing AI scientists with ToolUniverse

Official Implementation of "Reasoning Language Models: A Blueprint"

The BAZAAR challenges LLMs to navigate the double-auction marketplace, where buyers and sellers must make strategic decisions with incomplete information. Each agent receives a private value and must decide how to quote based solely on the history of previous rounds. A realistic test of market intuition and strategic adaptation.

Code for the 2025 ACL publication "Fine-Tuning on Diverse Reasoning Chains Drives Within-Inference CoT Refinement in LLMs"

[arXiv 2501.13117]The Multiplex CoT makes AI more thoughtful.

A CIDOC-CRM-based Application Profile, consisting in a set of entities and properties for representing the digitisation process of cultural heritage objects in a machine-readable format.

A system for doing NER using LLMs and LRMs

Reimplementation of TripoSR for 2D-to-3D object reconstruction

[ICLR 2026] FROST: Filtering Reasoning Outliers with Attention for Efficient Reasoning

Evaluating Relational Reasoning in LLMs with REL

A comprehensive cheatsheet of VHDL-20xx with concise examples and code snippets to quickly look up

AI Agents Arena is a benchmark harness that pits 8 distinct AI agent architectures against a suite of tasks.

Leaflet routing machine Locationiq provider

Mock LRM pour interface plateforme numérique SAS