GitHub Repo

GitHub 熱門專案、開源工具、框架、runtime 與重要 release。

SWE-Gate Adds Review-Constraint Tests for Coding Agents, Finds One-Third of Green Patches Still Fail Requirements

SWE-Gate turns review feedback from real pull requests into an executable second test suite, separately measuring functional fixes and engineering constraints. Of 644 patches generated by four models that passed functional tests, 221 still violated explicitly stated review requirements.

2026-09-05

GitHub Repo

K2 Horizon Launches in Six Sizes, With Its MoVA Model Activating Only a Subset of Value Projections per Token

IFM has released the K2 Horizon model family, ranging from 0.9B to 375B parameters. The 36B version extends MoE-style routing to the attention mechanism’s value projections. Weights and deployment recipes are now available, but the organization’s claim of being “fully open source” still runs ahead of what it has actually delivered.

2026-09-05

代理工具

GitHub Copilot CLI 1.0.83 Adds CIMD Login Support for MCP and Expands Sandbox File Tool Read Access

The new release lets MCP OAuth clients publish identity metadata at a URL, reducing the need to register individually with authorization servers. It also allows built-in sandbox file tools to read development tool configurations, including `.npmrc` files that may contain tokens, so deployers should review their default permissions.

2026-09-05

推論系統

Random Attention Randomly Evicts KV Cache Entries After Preserving the Prompt, Outperforming Scoring-Based Methods on Long-Reasoning Throughput

Salesforce AI Research found that after protecting the original prompt, randomly retaining reasoning tokens within each KV head can match the accuracy of several content-scoring strategies. In H200 tests with 32K-token outputs, it processed 32% to 43% more tokens than TriAttention, though short outputs and long code prompts did not necessarily benefit.

2026-09-05

Compile by Training Compiles Natural-Language Specifications into Locally Executable Functions on a 0.6B Model

The new method uses a large teacher model to synthesize task data, then trains a function-specific LoRA for each task so subsequent requests do not need to call a remote model. It achieves 83.6% semantic accuracy on a difficult benchmark, but compilation still requires a teacher API, about 40 GB of accelerator memory, and output validation.

2026-09-05

AI 安全

CISA Adds LiteLLM MCP Authentication Bypass to Known Exploited Vulnerabilities Catalog After Failed Keys Were Downgraded to Valid Sessions

CVE-2026-59822 allowed forged Bearer tokens to bypass LiteLLM authentication in a specific OAuth2 passthrough path, enabling attackers to list and invoke configured MCP tools. The vulnerability was fixed in version 1.84.0, but its addition to CISA’s KEV catalog makes inventorying public endpoints and rotating upstream credentials an immediate priority.

2026-09-05

代理工具

GitHub HydraFusion Orchestrates Multiple Models at Copilot Runtime, Using Cascades and Cross-Review to Control Costs

The Copilot CLI research preview no longer selects just one model for each task. Instead, it routes tasks among three workflows: direct execution, staged escalation, and cross-model review. GitHub’s offline tests indicate that some workloads may reduce estimated costs, but the router, quality gates, and internal benchmark have not been disclosed.

2026-09-05

AI 安全

Goose 1.49 Adds a Fail-Closed Mode for Agent Tool Interception and Completes Cross-Lifecycle Audit Identifiers

The AAIF open-source agent Goose 1.49 allows `PreToolUse` policies to reject tool calls when execution fails, preventing operations from continuing after security checks break down. The new release also adds a stable `tool_call_id` and result events, but remains fail-open by default, requiring administrators to explicitly change the configuration.

2026-09-05

AI 基礎設施

AWS Open-Sources HyperPod InstantStart, Enabling Human Operators and AI Agents Through the Same Governed APIs

HyperPod InstantStart orchestrates EKS, GPU capacity, training, inference, and storage operations as retryable, stateful workflows, then exposes them to agents through MCP tools. Agents do not operate the AWS CLI directly, but deployers remain responsible for IAM, Kubernetes, networking, and cross-service cost management.

2026-09-05

電腦視覺

Scal3R Fixes Drift in Long-Video 3D Reconstruction With Multi-Reference Pose Queries, Training Only About 1% Additional Parameters

Scal3R retains a frozen CUT3R or STream3R backbone, using lightweight query tokens to estimate relative poses against multiple historical keyframes before passing them to online pose graph optimization. The authors report a mean ATE on KITTI more than 60% lower than the strongest online competitor, but the results use Sim(3) alignment and therefore should not be interpreted as preserving true scale.

2026-09-05

VibeVoice-ASR-Streaming Combines Incremental Recognition and Speaker Attribution, Open-Sources 1.5B and 7B Weights

Microsoft Research’s streaming speech model interleaves audio chunks, brief lookahead, and the existing transcript to directly output “who said what.” The public release supports ten languages and custom hotwords, but expected speaker-attribution latency remains two seconds, and performance degrades during prolonged overlapping speech.

2026-09-05

代理工具

Agno 3.0.6 Enables Stateless Horizontal Scaling for MCP Services—at the Cost of Notifications and Stream Resumption

Agno 3.0.6 introduces stateless MCP transport, allowing any replica to handle requests without session affinity. The framework also adds protocol version negotiation and a Server Card, but retains the legacy session-based mode as the default for compatibility with existing deployments.

2026-09-04