Auditable AI Text Detectors with Sparse Features
Turning opaque neural text detectors into concept-level, auditable classifiers.
DailyUpdated 2026-11-07 12:20 UTC87 articles120 signals
The frontier of AI engineering, explained.
Every day, Frontier reads the frontier of AI engineering — papers, releases, repos and what builders post — and explains what actually changed, how it works and what to do with it.
UniWALM: closing the loop between language and action
How a unified world–action–language model turns language into on-board robot memory.
Proof-Carrying Contracts for Agent Control
How PC2 uses machine-checkable proofs and an “Airlock” to constrain AI agents.
Monsoon: building speech corpora as a system
Inside a five-stage pipeline for low-resource spontaneous speech that actually moves ASR metrics
Let agents design their own interfaces
Agent S4 shows that evolving tool interfaces from experience can beat static, hand-built UI for computer-use agents.
Evolving semantic indexes for generative retrieval
LLM-driven evolutionary search is starting to auto-design the discrete pieces of generative search indexes.
Agentic SEER Reproducibility at Scale
An AI agent reproduces thousands of SEER-based claims and stress-tests their analytical choices, flagging fragile results for human review.
FuTransformer’s FP8/INT4 path on Hopper, decoded
How FuTransformer restructures Llama-style inference into FP8 prefill and INT4 decode kernels on NVIDIA Hopper.
Tool gateways for agents with 8k+ tools
How a three-tool gateway exposes 8,200 tools to multi-step agents without blowing the context window.
Scaling Tool Use: Recommenders as the Agent Gateway
A tool-recommendation gateway lets agents safely access thousands of tools through three calls while cutting context and cost.
Testing LLM Solidity with SolBehave-style oracles
SolBehave shows that compilation is a weak signal for LLM-generated Solidity and that you need behavioral test oracles wired into your agent stack.
Latent Compaction: training KV caches at test time
How Latent Compaction treats the KV cache as a trainable latent and squeezes 32× context with minimal accuracy loss.
Fresh signals
- Scientist World: Grow a Research World for AI-Scientists arXiv · 1 days ago · frontier 95%
- @OpenAI: Our security researchers built an autonomous cyber vulnerability discovery, exploitation, and… X · ai radar · 2 days ago · frontier 92%
- @cursor_ai: You can now build live apps in Cursor and share them with a link. X · vibecoding radar · 1 days ago · frontier 73%
- PyRUA-DataFarm: LLM Agent as a Cost-Efficient Teleoperator for Real-Ready Robot Data arXiv · 3 days ago · frontier 92%
- @AnthropicAI: New Anthropic research: progress on provable inference for large language models. X · ai radar · 3 days ago · frontier 89%
- FrontierPhysics: Evaluating Agents for End-to-End Physics Research arXiv · 2 days ago · frontier 90%
- Social Humanoid: Socially Responsive Human-Humanoid Interaction arXiv · 1 days ago · frontier 90%
- Perceptive Humanoid Motion from Simulation arXiv · 2 days ago · frontier 93%
- 4D Point Splatting for mmWave Radar Micro-Doppler Differentiable Rendering arXiv · 1 days ago · frontier 91%
- Airlock: Bounding the Multi-Agent Blast Radius via Selective Online Containment arXiv · 2 days ago · frontier 85%
- ServerBench: How can your coding agents design specialized LLM serving systems? arXiv · 2 days ago · frontier 88%
- GFlowQEC: Generative Flow Networks that Learn to Sample Quantum LDPC Codes arXiv · 2 days ago · frontier 87%