All Articles
16650 articles total
Arduino Launches Plug-and-Play Modules for Long-Range Sensor Projects
Arduino has launched new plug-and-play modules designed to simplify the creation of long-range sensor projects.
Can AI Agents Really Complete RTL-to-GDS? Lessons from Benchmarking Tool-Interactive EDA Workflows
Researchers introduce FluxBench to evaluate AI agents in end-to-end electronic design automation (EDA) workflows, demonstrating that system design is more critical than domain-specific skills alone.
The Curvature Shadow: An Apparent Failure of Maximum-Entropy Equilibrium Selection is a Removable Artifact
A technical study reveals that an apparent failure of maximum-entropy equilibrium selection in zero-sum games is actually a removable artifact related to curvature shadows.
Retain or Consolidate? Budget-Dependent Operator Selection for Language Agent Memory
The paper proposes a budget-dependent operator selection method for language agent memory, introducing the Offline Abstraction-Safety (OAS) learner to balance memory retention and consolidation.
Why Does Feedback-Augmented Self-Distillation Fail to Improve Retrieval-Interleaved Search Agents?
This research analyzes the failure of Feedback-Augmented Self-Distillation in search agents, identifying 'decoding collapse' and proposing an EMA teacher to stabilize supervision.
Reinforcement Learning: From Algorithms To Foundation Models
A comprehensive thesis exploring the evolution of Reinforcement Learning from game algorithms to foundation models, including diffusion-based world models.
ZifaMem: Structured Memory for Persona, Preference, and Emotional Continuity in AI Companions
ZifaMem is introduced as a structured memory system for AI companions to maintain emotional continuity and persona grounding.
A Dual-Hypothesis Reasoning Framework for LLM Guardrails
ARBITER is proposed as a cost-effective LLM guardrail framework using dual-hypothesis reasoning and multi-component supervised fine-tuning.
Is Progressive Disclosure All You Need for Long-Context Agents?
A controlled study on 'progressive disclosure' for long-context agents shows it is most effective when corpora exceed the agent's inherent navigation capabilities.
Learning-Driven Adaptive Audit Scheduling: A Sequential Decision Approach to Off-Chain Data Integrity
Researchers propose DRQN-CMDP, a deep recurrent Q-network that optimizes off-chain data auditing to reduce gas costs by 83% while maintaining low miss rates.
Agentic ERP: Multi-Agent Large Language Model Architecture for Autonomous Enterprise Resource Planning
The paper introduces Agentic ERP, a multi-agent LLM architecture that uses role-aligned agents and a graph-based orchestrator to autonomously execute complex business workflows.
DeeperRadar: End-to-End MIMO Radar Design and Multi-Modal Fusion for Autonomous Vehicle Perception
DeeperRadar is an end-to-end framework that co-designs MIMO radar sensing and multi-modal fusion for autonomous vehicles to optimize receiver antenna activation.
Self-Modifying Lean Proof Agents with Verifier-Grounded Benchmark Coevolution
Researchers developed a self-evolving Lean proof agent that coevolves its workflow and benchmark, achieving a 45.1% solve rate on a held-out miniF2F test split.
Quantifying Diversity of Thought: A Predictive Law of Weighted LLM Ensemble Lift
This study derives a formal law to predict the performance lift of LLM ensembles based on 'diversity of thought' and accuracy-adjusted correctness correlation.
Intermittent Control Is Not Diluted Control: A Switching Effect in Artificial Agency
The paper identifies a 'switching effect' in artificial agency where intermittent access to anticipatory control can reduce the long-term regulatory burden of recovery.
Empirical Grounding Improves the Realism of LLM Agents Simulating Human Behavior During Disruptions
The study demonstrates that grounding LLM agents with real-world demographic and routine data significantly improves their ability to simulate human behavior during disruptions.
AEC-DS: Adaptive Erasure Coding with PDP-Triggered Reputation and QoS-Aware Migration for Decentralized Storage
AEC-DS is a closed-loop adaptive erasure coding mechanism for decentralized storage that uses PDP feedback to optimize shard placement and data durability.
Panache: One-Pass Motif Discovery at Every Window Length
Panache is a new one-pass streaming algorithm for z-normalized pan matrix profile motif discovery that is significantly faster than current CPU and GPU baselines.
Pailitao-MMSearch: Building Native E-Commerce Multimodal Search Foundation
Taobao introduces Pailitao-MMSearch, a native multimodal search foundation model for e-commerce that improves GMV and transaction volume through hybrid reasoning.
How to pack ternary numbers in 8-bit bytes
A discussion on the technical methods of packing ternary numbers into 8-bit bytes for memory efficiency.