AI Infra2026
Defines OpenTelemetry semantic conventions for generative AI telemetry — spans, metrics, and events for GenAI clients, the Model Context Protocol (MCP), and provider-specific integrations. Includes YAML models, human-readable docs, and reference implementations to standardize observability across GenAI deployments.
AI Infra2026
High-throughput LLM inference engine for agentic workloads, combining a local‑SPMD static compiler for parallelism, a C++ scheduler with a Python execution plane and type‑safe KV‑cache reuse, pluggable high-performance kernels (including an MLA implementation), and a low‑overhead AsyncLLM entrypoint for production GPU inference.
AI Dataset2026
Provides 1,781 OpenTelemetry execution traces of LLM-powered agents across six benchmarks, including full conversations, token usage, timing, tool calls and model metadata—useful for performance analysis, agent-behavior research, and inference debugging.
AI Dataset2026
Provides a sanitized, MIT‑licensed dataset of scanner evidence and registry verdicts for public ClawHub agent skills — 67k+ latest skill versions with redacted artifacts and structured VirusTotal, static-analysis, and SkillSpector outputs to study scanner disagreement and agent-skill risk governance.
AI Dataset2026
A 16 GB, 507-file PhD‑level cybersecurity knowledge base for training and evaluating security-focused LLMs and automation. Covers offensive/defensive/forensics/cloud/iot and AI-security across 30+ domains with real-world labs and framework mappings.
AI Infra2026
Routes agent requests across hosted, bring-your-own-key, and local models through one OpenAI-compatible API. It can also use production traces to optimize routing or train a specialized model.
AI Dataset2026
Provides labeled prompts with full-reference answers (including chain-of-thought and code blocks) and per-example metadata to train edge routing/orchestrator models that decide whether to handle inputs locally or route them to larger models. Includes complexity scores, coding/math flags, routing justifications, and an automated override rule; suited for fine-tuning small models (50M–1.5B) for edge deployment.
Autonomously proposes, modifies, executes, and evaluates ML experiments to study recursive self-improvement in machine learning engineering. Implements an open stack (OpenMLE-Gym, -RL, -Evo) and post-trains Frontis-MA1 (35B) around four evolution operators (Draft, Improve, Debug, Crossover); releases model weights and the full codebase.
Presents a unified black-box reinforcement learning framework to train and optimize agents running inside complex execution harnesses. Uses sandbox-parallel rollouts, a serving proxy that captures model calls and reconstructs multi-turn trajectories as prefix trees, and adapted GRPO/PPO optimizers to achieve stable, scalable RL across heterogeneous harnesses.
Adapts off-policy RL stabilizers to the available data regime: introduces WarpSAC, a regime-aware family using Sample Weight Decay plus two regime-matched variants (WarpSAC-L and WarpSAC-A) to improve sample efficiency, wall-time learning, and sim-to-real deployment.
AI Agent Papers2026
Jianlyu Chen, Yuyang Hu +9Beijing Academy of Artificial Intelligence, University of Science and Technology of China +2
Distills operational know‑how from ML GitHub repositories into compact, verified 'skills' that research agents can load and reuse. Produces a skill format (SKILL.md, references, scripts), the AREX‑Skill Library (5,000+ skills from 1,000 repos), and demonstrates sizable benchmark gains when agents use skills.
MLOps2026
Provides a programming model and distributed runtime that preserves parent–child lineage and ordered variable-cardinality expansions for 1→M→1 dataflow pipelines, enabling completion-driven cross-input GPU batching and ordered gathers for foundation-model data preparation. Demonstrates multi-GPU scaling speedups and lower end-to-end time versus Ray Data and Daft.