Tag
Explore by tags
Provides a modular full-stack reinforcement learning stack to train and evaluate long-horizon, multi-turn tool-use LLM agents, including a performant trainer, a Tinker-compatible backend, agent orchestration, and Gymnasium-style environments for task design.
Provides a reproducible, deduplicated corpus of text extracted from PDFs for LLM pretraining—about 3 trillion tokens from ~475 million documents in 1733 language-script pairs. Includes OCR and text extraction pipelines, per-page language IDs, MinHash deduplication, and is released under ODC‑By 1.0.
Multi-agent workbench for long- and short-form fiction, scriptwriting, interactive narrative games and multilingual translation. Offers Studio/CLI/TUI tools that plan, draft, audit and revise chapters while maintaining structured story state, branching forecasts, cover generation and multi-model routing. Suited for authors and teams automating long-horizon narrative workflows.
Benchmarks LLM agents on realistic legal work by packaging lawyer-style assignments with client materials and expert, per-deliverable rubrics. Includes an execution harness to run, score, and compare agents across a large, evolving task set spanning multiple practice areas.
Runs coding and long-running research workflows inside a persistent IPython environment with programmatic subagents and a durable 'Continual Harness' for session-level refinements. Key features include recursive subagents (RLM), executable Python skills, background daemon sessions, and evidence-backed local refinements. Best for reproducible, long-horizon coding, experiments, and evaluation pipelines where auditable agent-driven updates matter.
Maintains a local, durable control-plane state that preserves objectives, typed todos, gates, evidence logs, quotas, and verifiable handoffs for long-running AI agent work. Designed to coordinate multi-day agent loops across Codex, Claude Code, Cursor or custom runners while keeping human judgment, auditability, and safe fallbacks explicit.
Benchmark dataset for evaluating long-horizon coding agents and software-engineering tasks, containing English code and tabular metadata in Parquet format; small scale (<1K examples) for fast prototyping and evaluation.
27B multimodal reasoning model built on Qwen3.5-27B that preserves the base model's native multi-token-prediction head, full vision tower, and a 1,048,576-token YaRN context window. Designed for agentic tool use, long-context reasoning, and research deployments; released under Apache-2.0.
An open-weight LLM checkpoint post-trained for agentic deep search: Qwen-compatible reasoning and tool-call formats optimized for web browsing, multi-source evidence aggregation, long-horizon planning and recovery from failed interactions; typically paired with the AxisAgentic harness.
An open-weight, Qwen-derived thinking model optimized for agentic deep web search and long-horizon planning. Provides Qwen-compatible reasoning and tool-call formats for English/Chinese browsing, multi-source evidence aggregation, source verification, and recovery from failed environment interactions.
Provides a unified survey of progress-reward modeling for robotic learning, detailing interfaces, modeling techniques, and evaluation practices. Organizes the literature into three perspectives—interface, model internals, and data/benchmarks—and highlights limitations and open problems. Useful for researchers designing rewards for long-horizon or sparse-reward robotic tasks.
A 124B hybrid-linear Mixture-of-Experts language model optimized for instruction following, long-context reasoning and agentic workflows, activating ~5.1B parameters per token. Key features include a 256K native context (extendable to 1M), alternating KDA/MLA attention layers, and vLLM/SGLang inference support.