代理工具

Agent、MCP、coding agent、工作流自動化與評測。

Community Turns MiniMax H3 into an Image Editor with a Single-Frame VAE, Exposing ComfyUI’s Five-Frame Minimum as a Compatibility Gap

The community has trained a 5.21GB single-frame VAE for the MiniMax H3 video model, allowing reference-to-video pipelines to generate just one frame for tasks such as virtual try-on, pose editing, and viewpoint transformation. The approach demonstrates how a video model can be repurposed as an image editor, but it currently depends on unofficial weights, specific workflows, and ComfyUI single-frame support that has yet to be fully implemented.

2026-08-17

最新模型

Qwen3.8-27B Delivers a Native 262K Context Window with a Hybrid Linear/Full-Attention Architecture While Retaining Multi-Step MTP

Qwen has released the weights for Qwen3.8-27B, using a 64-layer hybrid Gated DeltaNet/Gated Attention architecture to reduce long-context costs while providing native visual understanding and adjustable reasoning depth. Official agent benchmarks show substantial gains, but some datasets, corrected tasks, and execution frameworks were configured by Qwen, so the results should not be treated as a fair cross-vendor ranking.

2026-08-14

代理工具

optstop Dynamically Stops Evaluations Using Bayesian Credible Intervals, Saving Up to 97.3% of Trials Across Nine Test Sets

The UK AI Security Institute has open-sourced optstop, which uses posterior uncertainty at the item and task levels to decide when to stop repeated evaluations. Across nine shadow tests, it saved an average of 81.1% of trials, though performance varied with score type, item ordering, and the exchangeability assumption.

2026-08-17

代理工具

TWIN Lets Coding Agents Reconstruct Unknown Games in Real Time, Raising ARC-AGI-3 Score from 7.8 to 93.3

TWIN requires an agent to first encode an unknown environment as an executable Python world model. The agent may take real actions only after the model can replay its entire history exactly. Using the same base model, this raises the ARC-AGI-3 score from 7.8 with direct interaction to 93.3.

2026-08-17

推論系統

DeepSeek V4 API Switches to Peak Pricing, With Pro Cache-Hit Rates Rising to as Much as 12.1× Their Previous Level

DeepSeek has introduced time-of-use pricing for V4 Flash and Pro, with peak rates twice as high as off-peak rates. The greatest impact is not on ordinary input, but on cache-hit tokens heavily used by long conversations and coding agents.

2026-08-17

推論系統

Ollama 0.32.14 Transcodes WebP Before Passing It to llama-server and Relaxes Qwen System Message Positioning

The new release fixes two compatibility gaps in the model preprocessing layer: WebP images are now transcoded, and the Qwen renderer no longer requires system messages to appear first. Although the changes do not introduce new models or kernels, they can prevent multimodal and agent conversations from failing before they reach the inference core.

2026-08-17

代理工具

Pydantic AI 2.31 Moves AG-UI Run Identification into the Event Stream, Enabling Streaming Before Delayed Input Arrives

The new release allows a `UIEventStream` to be created before `run_input` is available and lets `AGUIEventStream` hold its own thread and run IDs. It also fixes Temporal sandbox compatibility and tracing attribution for fallback models, reducing diagnostic blind spots in long-running agent workflows.

2026-08-17

最新模型

GCache Allocates Diffusion Caching Based on End-to-End Error, Cutting LPIPS to 0.0316 on Wan 2.1 at the Same 2.17× Speedup

Rather than comparing only local differences between adjacent denoising steps, GCache estimates the cumulative impact of cache errors on the final image or video. It uses dynamic programming to select cache refresh points, then applies Bayesian optimization to align theoretical weights with actual generation quality.

2026-08-16

代理工具

SkillShapley Incrementally Estimates the Value of Agent Skills, Producing 206 Reusable Marginal Comparisons From 99 Configurations

SkillShapley treats the semantic steps in `skill.md` as players in a cooperative game and uses Shapley values to measure each step’s contribution to task success. Its BAES approximator prioritizes skill configurations that can yield multiple single-step comparisons, reducing the cost of running agents individually.

2026-08-16

AI 安全

Claude Code 2.1.233 Limits Bash Memory and Closes a Windows NTLM Credential Leak Vector

The new release can use Linux memory cgroups to cap memory for builds and tests run by the agent, preventing runaway processes from crashing the entire session. It also fixes a Windows special-path validation bypass, an MCP reconnection loop, and a sandbox issue that consumed an entire CPU core while idle.

2026-08-16

最新模型

SpaceX Completes Acquisition of Cursor, Bringing Composer Training and the Grok Development Toolchain Into a Single Stack

Cursor has confirmed that it is joining SpaceXAI. The two companies will jointly improve Grok Build, Grok Bot, the Grok API, and Cursor. The deal vertically integrates GPU infrastructure, coding-model training, and access to millions of developers, but no timeline has been announced for migrating models, data, or APIs.

2026-08-16

代理工具

OmniScientist Reads Raw Scientific Data Directly, Producing Traceable Papers Across 36 Cross-Disciplinary Tasks

OmniScientist carries perception through hypothesis generation, experimentation, and writing instead of first compressing images, waveforms, or trajectories into text summaries. In blinded comparisons, the full system achieved an 85% win rate against a version that received only precomputed features, though evaluations still relied primarily on model judges.

2026-08-16