Measuring the Microtask Eligibility Gap: When Is an Off-the-Shelf SLM Enough for an Agent Harness?
Research
Research News
New papers, breakthroughs and academic AI research
Characterizing a Configuration Where Inference-Time PRM-Pruned Fragment Grafting Is Inert: Evidence from Three Reasoning LMs
Research
Gradient-Aligned Pair Selection for Personalized Preference Optimization
Research
BudgetSchemaBench: A Budget-Swept Diagnostic for Schema Context in Text-to-SQL
Research
Towards a Cloud Fog Edge System for Smart Building
Research
Sequential Capacity of Quantum Processes with Finite Memory
Research
Backdoor Purification for LoRA-Tuned LLMs via Null-Space Projection
Research
Just Align $\bm{x}$: Aligning Predictions, Not Representations
Research
When Do Causal World Models Help Modular LLM Agents
Research
SCM-based Fairness and Faithful Explainability for Legal Document Classification
Research
Measuring Human-Like Bias in LLMs? A Critique of Human-Derived Bias Constructs in LLM Evaluation
Research
Scientific Agents: Evaluating Profession-Specific System Prompts on Scientific Tasks
Research