cs.AI — items we recorded

148 item(s) from this outlet appeared in our collection.

• Context as Infrastructure: Knowledge Compilation for Retrieval in Agentic Systems with Harnesses
  2026-11-03
• Beyond CLIP: Calibrated (Few-Shot) Defect Detection With System One Decision Models
  2026-11-03
• From Evaluation to Evolution: Benchmarking Image Editing and Evolving Image Models
  2026-11-03
• Coarse3D: Controllable and Faithful Sparse Structure Generation for Image-to-3D
  2026-11-03
• More Rules, Longer Lists? Benchmarking Self-Evolving Agents on a Hidden-Rule Curriculum
  2026-11-02
• Beyond Plausible Prediction: Safety Sufficiency in Web World Models
  2026-11-02
• Circumventing the Computational Hardness of Computational Arbitrage
  2026-11-02
• Incongruence-Aware Evaluation of Multimodal Speech Emotion Recognition in Audio Large Language Models
  2026-11-02
• LRMoE: Demand-Side Load Re-Calibration for Efficient MoE Training on Memory-Constrained Nodes
  2026-10-31
• Amortized Localized Posterior Inference for Model Calibration with Application to an Ocean Turbulence Closure
  2026-10-31
• ThinkJev: One Thought, Every Budget for Calibrated Typed Decisions
  2026-10-31
• OpenFrontiers: A Collection of Open Research Problems and a Benchmark for Scientific Rediscovery
  2026-10-31
• Counting the Bandages: On measuring the time that AI saves
  2026-10-28
• Enhancing Deep Learning Model Performance through Data Generation Strategies: Classification of Olive Tree Diseases
  2026-10-28
• The Trinity:Capability-Driven Recursive Self-Improvement for Multimodal Agents
  2026-10-28
• CohortFlow: A Steerable Clinical Cohort Curation Agent with Localized Semantic Correction
  2026-10-28
• Inverse Modeling for Laser Pulse Shape Design in Inertial Confinement Fusion
  2026-10-27
• IRON-Meme: A Benchmark for Structured Understanding of Identities and Roles in Online Meme Narratives
  2026-10-27
• Prospect Theory in Large Language Models: A Meta-Analysis of Loss Aversion, Diminishing Sensitivity, and Probability Weighting
  2026-10-27
• Artificial Intelligence in Mechanical Engineering: Foundations, Opportunities, Challenges, and Responsibilities
  2026-10-27
• Tradeoff-Aware Territory Design: A Multi-Objective Decision System for Enterprise Customer-to-Seller Allocation
  2026-10-26
• Phronix: The Capability-Centric Learning Paradigm for Agents
  2026-10-26
• Patronizing and Condescending Language Detection in English and Mandarin
  2026-10-26
• PaperFormalizer: Author-in-the-Loop Autoformalization of Research Papers in Lean
  2026-10-26
• A Small Model Asks Better: Fine-Tuning Query Clarification for Retrieval-Augmented Generation
  2026-10-23
• Scaling in Games: Continued Pre-Training For Embodied Agents In Diverse Virtual Worlds
  2026-10-23
• SpecEvo: Speculative Evolution with Large Language Models for Cost-Efficient Scientific Discovery
  2026-10-23
• Automating ML for Science: Can Frontier Agents Climb Scientific Hills in the Wild?
  2026-10-23
• Navalia: Advancing Cowork Agents through Verifiable Task Synthesis and Long-Horizon Post-Training
  2026-10-21
• Large language model and reinforcement learning based autonomous construction and progress updates
  2026-10-21
• Pareto-Optimal RTL Code Generation via Multi-Objective Reinforcement Learning with Large Language Models
  2026-10-21
• MedPAO-Assist: Edge-Deployable, Modality-Aware Agentic AI for Radiology Report Structuring
  2026-10-21
• Structured Authority Injection: Persistent Human Control for LLM Agents via Typed MCP Overrides
  2026-10-19
• Rethinking User Encoders: Routing Diffusion States for Scenario-Adaptive User Representation
  2026-10-19
• From Events to Reasoning: Hierarchical Rule Composition over Explicit States
  2026-10-19
• ECHOES: Seeing Beyond the Current Image via Recursive History Compression and Privileged On-Policy Distillation
  2026-10-19
• The World Won't Wait: Evaluating and Teaching Agents Under a Live Clock
  2026-10-16
• Evaluating Model Capabilities After Benchmark Saturation
  2026-10-16
• Value-Informed Schedule Trimming for Accelerated Sequential Monte Carlo Guidance in Discrete Diffusion
  2026-10-16
• AlphaDiana: A Measurement System for Agents in Verifiable Reasoning Tasks
  2026-10-16
• Artificiality's First Exam: An LLM-Referenced C-test for Supraintelligence
  2026-10-15
• The Silent Failures in Agentic Data Science
  2026-10-15
• ClawLoop: Self-Improving Agents via Harness-Native Training Loop
  2026-10-15
• Correction Training for Diffusion Models
  2026-10-15
• Faithfulness Without Anchors: A Position Paper on the Structural Misalignments of Explainable AI Faithfulness Metrics for Feature Importance
  2026-10-12
• EliteTable: Self-Improving Program Search for Executable Control Policies
  2026-10-12
• Equal-Budget Monte Carlo Tree Search versus Randomized-Restart List Scheduling for DAG Workflows: A Controlled Equal-Budget Computational Study
  2026-10-12
• Know What You Don't Know: Agentic Data Synthesis by Evolving Generation Space for Closed-Loop Learning
  2026-10-12
• An Explainable Header-Centric Framework for Large-Scale Semantic Table Interpretation and Data Quality Assessment
  2026-10-09
• Synthesis Through Simulation: Generating Coherent Enterprise Data via Scalable Agent-System Interaction
  2026-10-09
• Agent-Controlled Forgetting for Tool-Using Agents: Reversible Context Curation in Practice
  2026-10-09
• Verification and Self-Improvement in Agentic AI: Foundations and Limits
  2026-10-09
• GAMEGO: Training Game-Dev Agents with Synthetic Trajectories Anchored in Real-World Assets
  2026-10-07
• Text2Dashboard: A Governed Agent Architecture for Natural-Language Dashboard Generation over Enterprise DataBrain
  2026-10-07
• FluidPD: In-Place Elasticity for SLO-Aware Prefill-Decode Disaggregated LLM Serving
  2026-10-07
• Anchor Divergence for Semantic Geometry in Contrastive Learning
  2026-10-07
• MintFlow: Minimal Trajectory Intervention for Constrained Flow Matching
  2026-10-05
• Fast Models, Slow Evidence: A Paired and Self-Audited Evaluation of System-1 Decision Models for LLM Agent Harnesses
  2026-10-05
• The AI Risk Observatory: What Can We Learn from AI Disclosures in Annual Reports About Societal Resilience?
  2026-10-05
• Keep It CALM: Analyzing the Limits of Global Unsafety in Text-to-Image Generation
  2026-10-05
• Heavy-Tailed Memory Traces in Long-Horizon Language Agents
  2026-10-02
• When Do Causal World Models Help Modular LLM Agents
  2026-10-02
• From Proposal to Verified Effect: Praxa, an Evidence-Bound Harness for Governed AI Agent Execution
  2026-10-02
• What Do Rationales Communicate? A Message-Intervention Study in Role-Specialized QA
  2026-10-02
• Improving OCR Faithfulness via Gated and Attenuated On-Policy Distillation
  2026-10-01
• AREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks
  2026-10-01
• MoFlow: Multi-Objective Agentic Workflow Generation
  2026-10-01
• AI Agents are Vulnerable to Radicalization
  2026-10-01
• OpenAI-HuggingFace: A Reproduction & Lessons for Alignment Testing
  2026-09-30
• Neurosymbolic Routing for Reliable Reasoning on Resource-Constrained Edge Devices
  2026-09-30
• Is Human-Readable Text Necessary for Effective LLM Fine-Tuning?
  2026-09-30
• The Price of Token Boundaries: Compression Certificates and Prediction
  2026-09-30
• Bringing AI to Autonomous Systems -- From Cognition to Collective Intelligence
  2026-09-28
• ScopeBench: Do Agents Preserve Engagement Boundaries Under Goal Pressure?
  2026-09-28
• When Is a Multi-Agent Code Judge Actually Grounded? Two Label-Free Measurements, and a Judge That Declines to Guess
  2026-09-28
• Bridging LLM Agents and Data Spaces: An Architectural Mediation Approach using the Model Context Protocol
  2026-09-28
• When Should Forecasting Agents Reason? Behavioral Stress Tests for Reliability Routing
  2026-09-25
• TW3Cast: A Frozen Router of Lightly Fine-Tuned Foundation Models for Time-Series Forecasting on GIFT-Eval, Selected Entirely on the Training Split
  2026-09-25
• PAWS: Policy-driven Agentic World Simulation
  2026-09-25
• Pistis Technical Report
  2026-09-25