All Articles
18727 articles total
New way of making espresso with ultrasound
Exploration of using ultrasound technology to create espresso, potentially changing the extraction process.
Getting Creative with Perlin Noise Fields
A technical look at using Perlin Noise Fields for creative generative art and programming.
Trinket.io shutting down, so we saved it and hosted it a trinket.strivemath.org
The community saved the Trinket.io platform by hosting a mirror at trinket.strivemath.org after its shutdown.
Commodore Releases Flip Phone
Commodore has released a new flip phone, attempting to revive the brand in the mobile hardware market.
Looking Is Not Picking: An Attention-Segment Account of Tool-Selection Failures in LLM Agents
Research showing that LLM tool-selection failures happen at the decision readout stage rather than due to 'lost-in-the-middle' context issues.
Posterior Twins: Distributional Behavioral Simulation for Enterprise Decisions
Introduction of 'Posterior Twins,' a digital-twin approach for distributional behavioral simulation to improve enterprise decision-making.
When Agent Automation Becomes Profitable: Quantifying and Insuring Autonomous AI Risk through Trace-Economic Underwriting
A framework for quantifying and insuring autonomous AI risk using 'trace-economic underwriting' based on tool-use traces.
Tensor-Coord: Algebraic Decomposition of Joint Plan Tensors for Conflict-Free Multi-Agent LLM Planning
Tensor-Coord uses multilinear algebra (CP and Tucker decompositions) to prevent conflicts in multi-agent LLM planning.
Steering Emotional Dynamics for Art Therapy: Controllable Narrative Script Generation through Hierarchically Guided LLM Agents
EC-Script is a framework for generating narratives with controlled emotional trajectories to assist in AI-driven art therapy.
Post-Hoc Merging is Not Enough: Many-Shot Model Merging with Loss-Gap Balancing
METIS introduces a loss-aware many-shot model merging protocol to reduce task interference and information erasure in multi-task LLMs.
After resurrecting an iconic PC brand, Commodore is getting into flip phones
Commodore is being revived by a retro gaming YouTuber, starting with a modern version of the Commodore 64 and expanding into flip phones.
Latent Thought Flow: Efficient Latent Reasoning in Large Language Models
Researchers propose Latent Thought Flow (LTF), a method that moves LLM reasoning into continuous space to reduce inference overhead compared to traditional Chain-of-Thought.
SpecAlign: Efficient Specification-Grounded Alignment of Large Language Models via Synthetic Data
SpecAlign is introduced as a framework to align LLMs using synthetic data generated directly from structured provider specifications rather than abstract principles.
State-Grounded Multi-Agent Synthetic Data Generation for Tool-Augmented LLMs
StateGen is a synthetic data generation platform for tool-augmented LLMs that uses an authoritative state manager to eliminate tool-call hallucinations.
Architectural Wisdom: A Framework for Governing Optimization in AI Systems
The authors propose 'architectural wisdom,' a governance layer for AI systems designed to interrogate objectives rather than just optimizing them to prevent structural failures.
AdaSTORM: Scaling LLM Reasoning on Dynamic Graphs via Adaptive Spatio-Temporal Multi-Agent Collaboration
AdaSTORM is a new framework that enables LLMs to reason on thousand-node dynamic graphs by using adaptive partitioning and multi-agent collaboration.
Exploiting Search in Symbolic Numeric Planning with Patterns
This paper presents a numeric planning procedure based on Symbolic Pattern Planning (SPP) that uses symbolic search to refine patterns for better goal reachability.
Phase-Aware Guidance Injection for Recurrent MAPPO in Assembly-Line Disruption Recovery
A phase-aware guidance injection framework for recurrent MAPPO is proposed to improve disruption recovery in industrial assembly lines using external knowledge.
Medical Heuristic Learning: An LLM-Driven Framework for Interpretable and Auditable Clinical Decision Rules
Medical Heuristic Learning (MHL) is an LLM-driven framework that produces interpretable, versioned Python decision rules for clinical tabular prediction instead of black-box models.
Whose hotel does the AI recommend? An algorithm audit of reputation signals in LLM-assisted hotel selection
An audit of LLM hotel recommendations reveals that guest ratings and price dominate selections, while list position also significantly influences outcomes.