A mobile-planning agent paper that develops a closed-loop AI-for-AI lifecycle to generate data, train a planner model, and co-evolve a runtime Harness for multi-app task execution. Demonstrates top performance on MobilePA-Bench with improved tool use, memory, skill coordination and low estimated per-task output cost.
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).
Provides 5.5K+ self-contained data-analysis RL tasks: each row bundles a real tabular dataset, a question, and a deterministically-gradable gold answer. Verified from jupyter-agent notebooks; splits for training, held-out testing, and quick eval; intended for prompting, fine-tuning, and agent RL.
Shows that private post-training changes leave measurable "behavioral shadows" in task-unrelated single-word outputs and proposes Active Taskless Distillation (ATD) to transfer capabilities to a student using only those single-word teacher responses, without teacher logits or parameters.
Provides a plug-and-play harness that makes existing agents omni-native by exposing hierarchical multimodal Skills, a standardized execution interface, dependency-aware orchestration, and a persistent Asset Registry. Represents multi-asset workflows as Declare Execution Graphs to schedule concurrent operations and enable cross-turn reuse across interchangeable execution backends.
Learns joint predictive visual dynamics and action generation for generalist robot manipulation, translating future-relevant visual representations into actions. Integrates a Mixture-of-Transformers coupling a video expert and action expert, a frozen vision-language model for semantics, 4D distillation, and Causal Imprint; pretrained on a 20K+ hour heterogeneous corpus.
Capability-targeted compression of Qwen3.8-Flash-Next: half the experts are removed and remaining weights quantized to 3.5 bpw, producing a 58.4 GB GGUF (29.6 GB resident) that preserves coding and multimodal ability while trading off other domains.
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.
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.
Transcribes English speech into punctuated, capitalized text — a 164 MB quantized ASR model that averages 5.21% WER across seven Open ASR Leaderboard sets. Optimized for on-device and CPU/GPU inference, with fast runtimes on Apple M5 and Docker/GPU support.