AI Model2026
230M-parameter multilingual instruction-tuned text-only LLM for on-device agentic pipelines and data extraction; 32K context, 19T-token pretraining, optimized for fast CPU/edge inference (e.g., 213 tok/s on Galaxy S25 Ultra, 42 tok/s on Raspberry Pi 5); not for heavy reasoning or complex code generation.
AI Dataset2026
Measures how autonomous AI agents learn via long-horizon, feedback-rich executable tasks; publishes 51 public tasks from a 134-task suite and provides SForge, a two-container evaluation harness for iterative 12+ hour runs to track learning trajectories.
AI Dataset2026
Measures whether models produce valid JSON/YAML that strictly follow a requested schema across diverse, naturally phrased prompts. Contains 2,000 frozen test prompts with binary structural validation (no constrained decoding), focusing on schema compliance and edge cases like escaping, wrapper keys, and fenced code blocks.
AI Audio2026
Local English text-to-waveform TTS producing a single fixed synthetic voice in a deployable package below 10M parameters. Offers deterministic seeds, punctuation-aware long-text chunking, CPU/CUDA and ONNX runtime options, measured evaluations and a compact FP32 footprint; English-only, one voice.
Provides a rubric-based benchmark that converts dense image captions into instance-specific atomic checks (Must-Right and Easy-Wrong) and a gated scoring rule, aiming to expose perceptual brittleness and better align multimodal model evaluation with human judgment.
AI Model2026
Mixture-of-Experts LLM designed for million-token contexts, combining hybrid compressed attention, FP4/FP8 quantization-aware training for MoE experts, and multi-mode 'thinking' (Non-think/Think High/Think Max); includes a speculative-decoding extension for faster inference.
Proposes Monotonic Inference Policy Improvement (MIPI) and a two-step Monotonic Inference Policy Update (MIPU) to address training–inference probability mismatch in LLM reinforcement learning by constructing sampler-referenced candidate updates and accepting synchronized updates using an inference-gap proxy; shows improved reasoning accuracy and stability under FP8-quantized rollouts.
AI Dataset2026
Provides 300 adversarial "metacognitive-trap" problems to measure whether LLMs notice and recover from their own reasoning errors. Combines multiple-choice vulnerability tests with free-form adapter-gain evaluation and ships per-model metacognition adapters for frozen-base probing.
AI Agent Papers2026
Matches detection paradigms to four stratified attack-surface layers of AI agents — infrastructure, protocol/tool, agent behavior, and model — and presents AI-Infra-Guard: an open-source red-teaming framework with rule-based infra scanning, LLM-driven audits of MCP servers and skill packages, and a jailbreak/attack-operator harness.
AI Model2026
Provides quantized GGUF weights and configs for Agents‑A1 — a 35B Mixture-of-Experts agent trained for long-horizon, tool-enabled reasoning; supports 262K-context serving and runtimes like vLLM and SGLang.
AI Agent Papers2026
Evaluates how long-term memory in LLM agents amplifies sycophantic behavior and when memory should or should not influence decisions. Provides five targeted tasks, 1,550 standardized samples, an evaluation pipeline, and baseline adapters to test memory use, conflicts, scope, updates, and personalization.
Zhilin Wang, Han Song +14University of Science and Technology of China, The Chinese University of Hong Kong +6
Provides a benchmark and protocol to evaluate agents that iteratively edit executable policies under a fixed interaction budget, recording full execution–feedback–revise trajectories. Built from compact RL environments with trajectory-level diagnostics and hidden held-out validation.