Alternates a Planner (issues sub-queries) and a Synthesizer (integrates retrieved evidence into a persistent summary) to tackle long-horizon deep-search; introduces Role‑Decoupled Policy Optimization (RDPO) for role-specific RL credit assignment and shows strong results (IterSynth-8B reaches 50.7% on five benchmarks).
Compresses Qwen3.8-27B into a 12.3 GB sensitivity-aware mixed-precision quantized checkpoint for long-horizon agent workloads; preserves BF16 fidelity (+0.02% PPL, 93.2% token Top‑1 agreement), supports 262K context and vLLM serving, text-only and Apache‑2.0 licensed.
Provides mixed-domain, verifiable RL training environments for LLM agents (code, cyber, knowledge work, web dev, music) as Parquet datasets, with domain-specific verifiers, Docker artifacts and links to training code for reproducible agentic RL experiments.
Reduces self-attention complexity to O(N log N) by using a coarse-to-fine (pyramid) Top-K block selection with LogSumExp scoring, implemented with hardware-aware Triton kernels for fused routing and scoring—aimed at long-context LMs and retrieval tasks.
Evaluates multimodal memory in large audio language models by testing four acoustic evidence types and four memory operations across multi-session spoken histories, stratified across 8K–64K token context budgets.
Provides a high-fidelity mixed-precision (≈3-bit) GGUF quant of Qwen3.8-27B tailored for long-horizon agent workloads and cyber-focused red-teaming. Preserves reasoning, thinking mode, MTP speculative decoding and vision (via a separate mmproj); released as an uncensored/abliterated research build under Apache-2.0.
Open-weight 309B Mixture-of-Experts causal LLM with 15.5B active parameters and a native 1M-token context for coding and AI R&D. Combines Sliding-Window Attention and DeepSeek Sparse Attention (no full-attention layers), supports FP8 inference; weights under MIT license.
Introduces an open-source multi-agent harness that automatically constructs, composes, and evolves modular model–harness units for long‑horizon, cross‑domain workflows. Key ingredients include a Host Agent for task decomposition and orchestration, EverOS for durable memory, and a Skill Forge of reusable procedures to improve task coverage via composition.
Learns dynamics-aligned latent representations for parametric PDE forecasting using masked-latent predictive pretraining, a geometry projector that aligns latent trajectory geometry, and a physics-structured latent predictor that separates shared evolution from parameter-dependent responses.
Provides 7,366 recorded agent trajectories from H Company’s Holo4 benchmark runs, with step-level reasoning, actions, tool results, token usage and screenshots for replay and analysis. Bundled as JSON and image files for per-trajectory inspection and automated replay; released under Apache 2.0.
Uses 360° panoramic observations to improve vision-and-language navigation by predicting longer action sequences, confidence-guided execution, and combined semantic–geometric panorama features; yields large SR gains on R2R-CE and RxR-CE Val-Unseen.
Records structural priors with skill-specific policies so a runtime agent can select and compose the version of each skill best suited to new states, improving out-of-distribution and compositional generalization for robot manipulation from few demonstrations.