14 posts published in the last hour
- 12:34Zero-Shot Weight-Space Programming for Prediction and Classification of Target Variables in Structured Datasets
- 12:34Agentic On-Policy Distillation Implicitly Reshapes LLMs’ ReAct Patterns
- 12:34Staged Semantic Distillation: Preserving Free-Form Semantics in a Low-Compute Non-LLM Surrogate of a Staged LLM Agent
- 12:34Beyond Clumsy Agentic Tool Calling: How Cueing and Spotting Make the Difference
- 12:34KAYAK Adds 28 AI Features to Pair Trip Planning With Live Prices
- 12:33Auditable Authorization for LLM Agents: Empirical Evidence Across Model, Harness, and Workflow Layers
- 12:08Mem2Fair: Online Fairness Control for Text-to-Video Generation via Fair Memory
- 12:08Can an Agent Rethink What It Knows? Selective Scene Memory Updates in a Changing World
- 12:08SnapLogic Launches Discovery Hub to Reuse and Govern MCP Servers
- 12:08CompoundingKernel: Self-Improving from Zero to First
- 12:07Personal AI Is Coming for Customer Loyalty and Brands Aren’t Ready
- 12:07What Moves a LoCoMo Score? Memory Context, Answer Prompts and Judges
- 12:07Opsera Expands Forge With Security and Governance for Legacy Application Modernization
- 12:07STaSBO: LLM-Guided Strategy Planning and Configuration Selection for Bayesian Optimization
