Archive
Agent、MCP、coding agent、工作流自動化與評測。
代理工具
Late in the Linux 7.2-rc7 release cycle, more than 230 contributors submitted over 400 fixes, some stemming from issues identified by AI review tools. AI has not replaced the core maintenance workflow, but agents such as Sashiko have pushed bug-finding speed beyond humans’ capacity to triage and validate reports.
最新模型
LongEarth-Bench organizes 117,000 remote-sensing images into approximately 120,000 long-sequence question-answer pairs, requiring models to track changes in landforms, anomalies, and missing states. LongEarth-R1, built on Qwen2.5-VL-7B, adds frame numbering, structured reasoning, and spatiotemporal rewards, but its data, weights, and code have not yet been released.
代理工具
AutoDesign uses an outer agent to analyze execution traces and modify the production system, with an independent development set determining whether updates are accepted. The open-source DesignHarness outperformed several commercial systems on the authors’ PosterBench, but automated scores had a correlation coefficient of only 0.34 with human preferences.
最新模型
Instead of training a video VAE solely for pixel reconstruction, V-RAE adds temporal compression and a decoder on top of semantic features from models such as DINOv3, SigLIP2, and V-JEPA 2.1. The authors found that the new latents improve both generation and future-frame prediction, though they have so far demonstrated only low-resolution, short-clip, class-conditional generation.
最新模型
The Danish Foundation Models team trained Mimir v1 from scratch, using HRM’s high- and low-level recurrent loops to approach some 4B models across the authors’ 20-benchmark evaluation. The weights are public, but “permissible data” does not mean fully open data: some corpora were used only under agreements or EU research exemptions.
最新模型
A replication found that changing the probe’s contextual framing could shift the correlation with model scale from +0.94 to −0.82. The study recommends measuring across at least nine to ten prompt wrappers; otherwise, a single activation direction is insufficient for comparing models.
代理工具
ReFind preserves conversations without rewriting them, allowing an agent to repeatedly gather evidence using keyword, time, and session filters. Across roughly 2,800 test questions, it achieved an average accuracy of 58.2%, surpassing the strongest structured-memory baseline at 53.2%, though the comparison did not standardize all controllers and tool-call budgets.
推論系統
DARTree extends causal correction for diffusion draft models from a single path to multiple branches and replaces node-by-node heap search with batched expansion by depth. In tests on a single RTX 6000 Ada, it delivered higher average speedups across seven tasks than DFlash, DDTree, and Domino, but the code has not yet been released.
最新模型
A new technical report brings scientific PDFs, time series, tool use, and long-horizon agent tasks into a unified training pipeline, while releasing the weights under Apache 2.0. The standalone Memory Decoder can add domain capabilities while keeping the 397B backbone frozen, but so far it has been demonstrated only with a biology module.
代理工具
Vero requires agents to implement multi-module software while submitting machine-verifiable correctness proofs, rather than merely passing unit tests. Across four frontier-agent configurations, the best still failed to fully solve 16 repositories, while 10 defeated every configuration.
代理工具
OmniScientist lets agents directly inspect images, signals, audio, video, 3D structures, and trajectories before completing ideation, experimentation, and paper writing. All 36 cases produced complete manuscripts, but the case count, code availability, and automated evaluation design still require clarification.
代理工具
StateBridge uses an orthogonal Procrustes transformation to map the sending agent’s final-layer hidden states into the receiving agent’s input embedding space, without training a projector. Its average scores across four models exceeded the strongest baseline by 2.4 to 2.9 points, but it currently supports only agents using identical model weights.