All Articles
17512 articles total
CausalDS: Benchmarking Causal Reasoning in Data-Science Agents
CausalDS is a new benchmark for evaluating the causal reasoning capabilities of data-science agents using synthetic natural-language stories and structural causal models.
Answer Set Programming Energised! End-to-End Neurosymbolic Reasoning and Learning with ASP and Energy Based Models
A new neurosymbolic reasoning methodology integrates answer set programming (ASP) with energy-based models for robust end-to-end training in dynamic domains.
Overthinking: Amplifying Reasoning Weights to Extract Learned Secrets
The 'overthinking' technique uses reasoning task vectors to amplify a model's propensity to think out loud, making it easier to extract hidden secrets from black-box models.
ASMR: Agentic Schema Generation for Ship Maintenance Report Writing
ASMR is an agentic framework that automatically generates schemas for ship maintenance reports by extracting semantic concepts and optimizing the structure via RL.
A First-Principles Theory of Slow Thinking and Active Perception
This paper proposes a mathematical theory of 'active lifting' to provide a first-principles formulation of slow thinking and active perception in LLMs.
Playing ZendoWorld: Challenging AI Agents on Active Visual Concept Induction
ZendoWorld is an interactive environment designed to challenge AI agents to perform active visual concept induction and test hypotheses about hidden logical rules.
What Big Food Did to Ice Cream
An article discussing the industrialization and changes in the ice cream industry.
Common prefix skipping, adaptive sort
A discussion on common prefix skipping and adaptive sorting algorithms.
After Apple, India’s smartphone manufacturing boom enters new phase with Vivo JV
Vivo is establishing a joint venture in India, potentially creating a new template for Chinese smartphone manufacturers.
Feedback Manipulation Regularization: Enabling Offline Agent Alignment for Imitation Learning
Introduction of Feedback Manipulation Regularization (FMR), an algorithm-agnostic method to improve imitation learning alignment in sequential decision-making environments.
Nigeria Machinery: A Low-Resource Industrial Dataset with a Domain-Grounded Reasoning Layer
The release of the Nigeria Machinery Usage and Failures Dataset and a method for building chain-of-thought reasoning examples for industrial machinery.
Persona Cartography: Charting Language Model Personality Traits in Weight Space
Research on 'Persona Cartography,' using the OCEAN framework to map and control LLM personality traits in weight space via low-rank adapters.
Evaluating the Effect of Frame Rate in Sequence-Based Classification of Autism-Related Self-Stimulatory Hand Idiosyncrasies
A study on optimizing frame rates and neural network architectures (LSTM/GRU) for the automated detection of autism-related self-stimulatory behaviors from video.
Agentic Neural Architecture Search
AgentNAS is a new pipeline that combines LLM-driven seed architecture generation with NAS-driven search to optimize neural architectures without manual engineering.
Concretized Proposition Prompting Resolves Composition-Knowledge Dichotomy in Large Language Models
Introduction of Concretized Proposition Prompting (CPP) to resolve the tension between compositionality and knowledge in LLM reasoning.
From Prompts to Contracts: Harness Engineering for Auditable Enterprise LLM Agents
A 'harness-engineering' approach for enterprise LLM agents that moves deterministic behavior into code and schemas to ensure auditability and safety.
Context Graphs for Proactive Enterprise Agents
Researchers propose the 'Context Graph', a live relational data structure and Delta Detection Engine to enable proactive enterprise AI agents that surface information before being queried.
AI-integrated models for assessing agricultural resilience
A new AI-powered tool integrates economic (GTAP) and biophysical (APSIM) models to help policymakers assess agricultural supply chain resilience using natural language queries.
Adversarial Social Epistemology for Assemblies of Humans and Large Language Models
This paper introduces Adversarial Social Epistemology (ASE) to analyze and audit trust breaches in complex communicative landscapes involving humans and LLMs.
Aligning Clinical Needs and AI Capabilities: A Survey on LLMs for Medical Reasoning
A survey on LLMs for medical reasoning that establishes a five-level competency scheme and a benchmark dataset to evaluate specialist vs general models.