Tag

Agent Memory Distillation: Empowering Small LLM Agents with Hierarchical Teacher Memory

Transfers hierarchical, structured memory from a large teacher agent into small LLM agents to improve tool-use success. Constructs Workflow, Subtask and Function memories with proactive/reactive injection; training-free and validated on multiple tool-use benchmarks.

Ouroboros: A Self-Developing Frontier Coding Agent with Reviewed Core Evolution

Enables a coding agent to self-develop by evolving its harness, prompts, tools, and core code via reviewed commits — supporting recursive free evolution and experience-driven evolution. Demonstrated a 161-day live lineage and state-of-the-art scores on multiple coding benchmarks while foregrounding operational safety.

Can LLM Agents Stick to the Script? A Benchmark for Long-Horizon Consistency in Interactive Narratives

Evaluates whether LLM-driven storyteller agents preserve long-horizon logical consistency under adversarial player interventions. Introduces NCP-Bench (100 movie-derived narrative environments) with structured trajectory/commitments and automatic violation checks; finds strong LLMs often contradict themselves across multi-turn interactions.

Muse Glimmer-30B-GGUF

A GGUF release of Meta's Muse Glimmer 30B optimized for local multimodal agent inference; includes two quantized text builds, a perception encoder for image input, and an optional DFlash drafter for speculative decoding—fits on 24–32 GB VRAM.

dots3-note Preview

Multimodal Mixture-of-Experts text-generation model that accepts text, images, video and audio and returns text; preview open-weight release with 280B total params, 16B activated params, up to 512K token context and BF16/FP8 checkpoints under Apache-2.0.

Muse Glimmer-30B-GGUF

Runs a quantized, locally executable 29.6B multimodal causal language model optimized for agentic workflows. Includes a perception encoder for image+text input, 4-bit quantized weights for 24–32GB devices, a DFlash drafter for speculative decoding, and robust tool-call support.

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA

A research report proposing a continual-learning agent workflow that pairs recursive self-improvement with a Mixture-of-LoRA design: freeze a foundation model, compose specialist LoRA adapters routed per user turn, and support them with long-context RL and post-training infrastructure.

Ling-3.0-tiny

Lightweight sparse-MoE LLM (7.9B params, ~1.3B activated per token) designed for hybrid multi-step reasoning and agentic tasks. Uses a KDA–MLA hybrid attention stack and a 128-expert sparse FFN; offered in BF16/FP8/INT4 for local and edge deployment.

GitSkills

Provides a queryable dataset of 3,797,117 SKILL.md agent-skill files found on public GitHub, deduplicated by content hash and enriched with representative text, front matter, folder composition, repo metadata, and sampled commit history for research.

NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4

Open-weight 30B-parameter Mixture-of-Experts LLM with 3B active params, NVFP4-quantized checkpoint, and speculative-decoding support for long-context (up to 1M tokens) agentic, chat, reasoning and tool-calling workloads optimized for NVIDIA GPUs.

AVA-Encoder: Towards Agent-Native Video Representation Learning

Encodes videos into a Film Knowledge Graph and reconstructs them to learn agent-native, editable video representations for agentic reasoning and manipulation. Uses agentic auto-encoding with dual-loop textual-gradient optimization, reports large reconstruction gains, and releases a benchmark and dataset.

Spark-to-Paper: End-to-End Research Paper Generation as a Composable Skill

Generates full publication-format research papers from a short idea by composing 13 coding-assistant skills; it retrieves literature, plans and runs feasible experiments, produces editable vector figures, and enforces deterministic integrity checks so claims are revised to match measured evidence.