Page 3 of Ai Research headlines on WeSearch — deduped and updated continuously from 10+ editorial sources.
An agent-based world model calls an LLM API and reasons flexibly in language, but its errors appear as hallucinated…
Many planning environments, however, are not vectors or images; they are graphs of agents, tools, skills, routes, and…
Most current applications focus on static coding benchmarks. We extend this paradigm to algorithmic trading. This…
The paper discusses the concept of accelerating returns, which suggests that technological progress becomes…
Researchers have developed COrigami, an AI pipeline for co-designing flat-foldable visually recognizable origami. The…
The paper introduces OpenFinGym, a unified gym environment designed for evaluating quantitative‑finance agents across…
Computer Science > Artificial Intelligence arXiv:2606.26348 (cs) [Submitted on 24 Jun 2026] Title:What We are Missing…
Classical exact solvers suffer from combinatorial explosion for these types of problems, and standard reinforcement…
We introduce narration-of-thought (NoT), a system prompt that structures chain-of-thought into five sections:…
Electric bus fleets provide a relevant test case. Their operation requires continuous coordination between service…
Computer Science > Artificial Intelligence arXiv:2606.26346 (cs) [Submitted on 24 Jun 2026] Title:How Do…
For today's coding agents, this intuition is being inverted: as foundation models develop stronger reasoning…
We formalize this as compositional behavioral leakage (CBL): interference between modules sharing a context window.…
This paper observes that human institutions have governed powerful autonomous actors not by monitoring their reasoning…
Siegel, Arvind Narayanan View a PDF of the paper titled Life After Benchmark Saturation: A Case Study of CORE-Bench,…
Integrating them without conflating evidence and anecdote is especially consequential in psychiatry, where poorly…
These data pairs determine the degree to which interpretability frameworks can reliably detect model features…
However, they inherently suffer from response lag due to their exclusive reliance on match outcomes, neglecting the…
We introduce an LLM-powered comparative pipeline for large-scale governance discourse analysis, integrating automated…
Researchers have found that refusal and persona traits in chat models are interconnected, with a compliant persona…
All Work Published on Generative AI Stanford HAI
1 November 21, 2022 Response to the Request for Comments on Trade Regulation Rule on Commercial Surveillance and Data…
Stanford HAI Stanford HAI
Stephen Eglash Stanford HAI
Shana Lynch Stanford HAI
Distinguished Fellows Stanford HAI
All Work Published on Workforce, Labor Stanford HAI
Stanford HAI Stanford HAI
Efficiently Modeling Long Sequences with Structured State Spaces Stanford HAI
Senior Fellows Stanford HAI
Manisha Desai Stanford HAI
Affiliated Faculty Stanford HAI
Dawn Siegel Stanford HAI
AI + Health Conference Stanford HAI
Elizabeth Schumann Stanford HAI
News Stanford HAI
““ Stanford HAI
Seed Research Grants Stanford HAI
Marissa Reitsma Stanford HAI
Bryce Marion Stanford HAI
Justin Sonnenburg Stanford HAI
What is Big Data? Stanford HAI
Luis Hernandez-Nunez Stanford HAI
Stanford HAI Stanford HAI
Chris Mentzel Stanford HAI
All Work Published on Regulation, Policy, Governance Stanford HAI
AI+Science: Accelerating Discovery Stanford HAI
What is Overfitting? Stanford HAI
The article introduces the Lab Agent Protocol (LAP), designed to enhance the interaction between autonomous agents and…
The paper titled 'Proof-Refactor' addresses the challenges in generating formal proofs using Large Language Models…
