Tootfinder

FATHOMS-RAG: A Framework for the Assessment of Thinking and Observation in Multimodal Systems that use Retrieval Augmented Generation
Samuel Hildebrand (Louisiana State University), Curtis Taylor (Oak Ridge National Lab), Sean Oesch (Oak Ridge National Lab), James M Ghawaly Jr (Louisiana State University), Amir Sadovnik (Oak Ridge National Lab), Ryan Shivers (Oak Ridge National Lab), Brandon Schreiber (Oak Ridge National Lab), Kevin Kurian (University of Florida)

FATHOMS-RAG: A Framework for the Assessment of Thinking and Observation in Multimodal Systems that use Retrieval Augmented Generation
Retrieval-augmented generation (RAG) has emerged as a promising paradigm for improving factual accuracy in large language models (LLMs). We introduce a benchmark designed to evaluate RAG pipelines as a whole, evaluating a pipeline's ability to ingest, retrieve, and reason about several modalities of information, differentiating it from existing benchmarks that focus on particular aspects such as retrieval. We present (1) a small, human-created dataset of 93 questions designed to evaluate a pipe…

Learning to Make MISTAKEs: Modeling Incorrect Student Thinking And Key Errors
Alexis Ross, Jacob Andreas
https://arxiv.org/abs/2510.11502 https://arxiv.org…

Learning to Make MISTAKEs: Modeling Incorrect Student Thinking And Key Errors
Research on reasoning in language models (LMs) predominantly focuses on improving the correctness of their outputs. But some important applications require modeling reasoning patterns that are incorrect. For example, automated systems that can reason about and simulate student errors are useful for providing real-time feedback in the classroom or offline practice for educators-in-training. This paper presents a new method, MISTAKE, that (1) constructs high-quality synthetic examples of reasonin…

In the olden days when I was a young 'un, I used not to wear a scarf, because "whatever for?!"
Nowadays I'm thinking of it as a seal, and therefore it is obligatory. Even in bed, where it seals the space between my head and the blanket *.
* But more seriously, it's helping when I'm on the verge of throat infection.

Day 10: Stacey Mason
Another academic, but this time one of my compatriots; we overlapped at UC Santa Cruz as advisees of Michael Mates, and even collaborated on a Twitch stream called ScholarsPlay for a bit, although we never coauthored any papers. We did chat about our research, and I had many good discussions with her about agency in interactive fiction, a topic we both published on. Her paper "On Games and Links: Extending the Vocabulary of Agency and Immersion in Interactive Narratives" (#20AuthorsNoMen

Eye-Tracking and BCI Integration for Assistive Communication in Locked-In Syndrome: Pilot Study with Healthy Participants
Ana Patr\'icia Pinto, Rute Bettencourt, Urbano J. Nunes, Gabriel Pires
https://arxiv.org/abs/2509.23518

Eye-Tracking and BCI Integration for Assistive Communication in Locked-In Syndrome: Pilot Study with Healthy Participants
Patients with Amyotrophic Lateral Sclerosis (ALS) progressively lose voluntary motor control, often leading to a Locked-In State (LIS), or in severe cases, a Completely Locked-in State (CLIS). Eye-tracking (ET) systems are common communication tools in early LIS but become ineffective as oculomotor function declines. EEG-based Brain-Computer Interfaces (BCIs) offer a non-muscular communication alternative, but delayed adoption may reduce performance due to diminished goal-directed thinking. Thi…

Early Results from Teaching Modelling for Software Comprehension in New-Hire Onboarding
Mrityunjay Kumar, Venkatesh Choppella
https://arxiv.org/abs/2510.07010 https://

Early Results from Teaching Modelling for Software Comprehension in New-Hire Onboarding
Working effectively with large, existing software systems requires strong comprehension skills, yet most graduates enter the industry with little preparation for this challenge. We report early results from a pilot intervention integrated into a SaaS company's onboarding program: a five-session course introducing systems thinking and Labelled Transition System (LTS) modelling. Participants articulated their understanding of product behaviour using a structured template and completed matched pre…

Thinking about it, if Russia combines deploying his own drones from ships at sea in Denmark and elsewhere, with activating people inside Europe to try the same with their hobby drones, things could get chaotic because detection and defense systems in Europe are not very capable in handling drones….🤔
#drones #russia

Seems like a good day to bring back this 2021 post: https://systemsapproach.org/2021/07/19/decentralizing-the-internet-again/

the future is not a countdown — #climateanxiety

Chronos vs Kairos: Rethinking Time, Change, and Leadership in a World of Uncertainty
We’ve been taught to see time as running out — every crisis a countdown. This essay reimagines time through Chronos and Kairos, exploring impermanence, systems thinking, and ethical leadership. The future isn’t a deadline — it’s a field of possibility we can participate in.

Perspectra: Choosing Your Experts Enhances Critical Thinking in Multi-Agent Research Ideation
Yiren Liu, Viraj Shah, Sangho Suh, Pao Siangliulue, Tal August, Yun Huang
https://arxiv.org/abs/2509.20553 …

Perspectra: Choosing Your Experts Enhances Critical Thinking in Multi-Agent Research Ideation
Recent advances in multi-agent systems (MAS) enable tools for information search and ideation by assigning personas to agents. However, how users can effectively control, steer, and critically evaluate collaboration among multiple domain-expert agents remains underexplored. We present Perspectra, an interactive MAS that visualizes and structures deliberation among LLM agents via a forum-style interface, supporting @-mention to invite targeted agents, threading for parallel exploration, with a r…