Opinions
The Hidden Costs of Monitoring Employees with AI
Guido Friebel, a professor of human resources at Goethe University, argues that AI is making employee monitoring dramatically cheaper, more…
Opinions
Israel takes its war on Palestine into the AI age
Said Arikat reports that an Israeli-funded operation called the Hanover Institute produced more than 560,000 words across 124 fake academic-style…
Opinions
AI Is Already Killing People—And Governments Are to Blame
Matthew Petti argues that the real near-term danger from military AI is not a sentient machine going rogue but governments…
Engineering
RRSI: Regularized Recursive Self-Improvement of Agent Harnesses
The paper introduces RRSI, a method for automatically refining LLM agent harnesses while mitigating overfitting during recursive self-improvement. It constrains…
Engineering
Document Retrieval-Aware Chunking (D-RAC): Universal Retrieval-Aware Ingestion of Enterprise Documents via PDF Normalization and Multimodal Markdown Conversion
The paper presents D-RAC, a technique that normalizes heterogeneous enterprise documents into PDF before converting them into retrieval-optimized Markdown using…
Engineering
One to More, More to One: Category-Aware Iterative Expert Training for Software Engineering Agents
The paper addresses uneven performance across task categories in software-engineering agents by training category-specific expert models via reinforcement learning with…
Engineering
Harness-Zero: Harness Distillation via Agent-as-Harness
The paper introduces Harness-Zero, a method for transferring behaviors learned with an optimized external agent harness into a model’s own…
Engineering
Jev-Mem: System-One-Controlled Agentic Memory for Efficient AI Agents
The paper introduces Jev-Mem, an agentic memory architecture that splits control into a lightweight ‘System-One’ controller (fast query routing, retrieval-budget…
Engineering
1% of Tokens Can Be Enough: On Gradient Estimation in On-Policy Distillation
The paper analyzes gradient estimation noise in sparse on-policy distillation and proposes an ‘information-efficiency ratio’ (IER) metric, based on signal-to-noise…
Engineering
Complex KDA: Understanding and Enhancing the Expressivity of Kimi Delta Attention
The paper introduces Complex KDA (CKDA), an enhanced Kimi Delta Attention variant for linear RNNs that extends parameter ranges (gates…
Engineering
The Functionalizer: Lossless Functional Decomposition for Subword Tokenization
The paper presents the Functionalizer, a pre-tokenization framework that decomposes orthographic variations (capitalization, diacritics, etc.) into reversible opcode/operand pairs encoded…
Engineering
EDGEGEN: Improving Tool-Calling Agents Beyond Happy Paths with Synthetic Edge Case Generation
The paper introduces EdgeGen, a framework that automatically generates synthetic edge-case tasks by extracting compliance rules from agent specifications and…