Harness^2: Recursive Agent Harnessing for an Open World

Harness² improves agent execution harnesses through recursive task-level refinement and continual harness-level learning, boosting performance across benchmarks without ground-truth verifiers.

https://arxiv.org/abs/2610.14224

https://hjfy.top/arxiv/2610.14224

https://github.com/google-research/harness2 (19988)

Kronos: A Foundation Model for the Language of Financial Markets

Kronos, a specialized pre-training framework for financial K-line data, outperforms existing models in forecasting and synthetic data generation through a unique tokenizer and autoregressive pre-training on a large dataset.

https://arxiv.org/abs/2508.02739

https://hjfy.top/arxiv/2508.02739

https://github.com/shiyu-coder/Kronos (43861)

nanoMuse: An Open-Source Personal Agent for Every Device You Own

https://arxiv.org/abs/2610.08699

https://hjfy.top/arxiv/2610.08699

https://github.com/nano-muse/nanoMuse (2639)

Efficient Memory Management for Large Language Model Serving withPagedAttention

PagedAttention algorithm and vLLM system enhance the throughput of large language models by efficiently managing memory and reducing waste in the key-value cache.

https://arxiv.org/abs/2309.06180

https://hjfy.top/arxiv/2309.06180

https://github.com/vllm-project/vllm (86094)

Internal Safety Collapse in Frontier Large Language Models

Frontier large language models exhibit Internal Safety Collapse, where they generate harmful content under specific task conditions, revealing inherent vulnerabilities despite alignment efforts.

https://arxiv.org/abs/2603.23509

https://hjfy.top/arxiv/2603.23509

https://github.com/wuyoscar/ISC-Bench (2343)

MinerU2.5: A Decoupled Vision-Language Model for EfficientHigh-Resolution Document Parsing

MinerU2.5, a 1.2B-parameter document parsing vision-language model, achieves state-of-the-art recognition accuracy with computational efficiency through a coarse-to-fine parsing strategy.

https://arxiv.org/abs/2509.22186

https://hjfy.top/arxiv/2509.22186

https://github.com/opendatalab/MinerU (82527)

PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement ...

PaddleOCR-VL-1.6 enhances document parsing performance through targeted data optimization and progressive post-training techniques, achieving state-of-the-art results on OmniDocBench v1.6.

https://arxiv.org/abs/2606.03264

https://hjfy.top/arxiv/2606.03264

https://github.com/PaddlePaddle/PaddleOCR (91707)

Raven: The Harness of Harnesses for Composable Agentic Intelligence

Raven is an open-source multi-agent ecosystem that autonomously builds and evolves modular harnesses, enabling cross-domain collaboration and expanding reliable task coverage through composable agent units.

https://arxiv.org/abs/2609.33439

https://hjfy.top/arxiv/2609.33439

https://github.com/EverMind-AI/Raven (5847)

COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation

Person-grounded AI skills are automatically distilled from heterogeneous traces into inspectable, correctable packages that capture both capabilities and behavioral patterns.

https://arxiv.org/abs/2605.31264

https://hjfy.top/arxiv/2605.31264

https://github.com/titanwings/colleague-skill (26054)