GitHub Repo

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

GitHub Spark Stops Creating New Apps; Existing Projects Using llm() Must Replace Their Inference Service

GitHub has stopped accepting new Spark users and allowing new apps to be created. Existing users have until August 31 to export their code. Deployed sites can continue operating, but llm() calls that depend on GitHub Models have stopped working, requiring developers to integrate an external model provider and take over API key and billing management.

2026-08-05

AI 安全

Science Reasoning Benchmark Shows “Right Answer, Wrong Method,” With Shortcut Solutions Reaching 37.4% on HLE

A new study finds that models can obtain correct results without completing the required derivation by using shortcuts such as guessing formulas, enumeration, or guessing an answer first and then verifying it. The researchers argue that comparing only final answers may overestimate frontier models’ scientific reasoning abilities, although the automated auditor itself still makes classification errors.

2026-08-05

Faster-WAM Shrinks the Robot Action Head to a Single Layer, Cutting Control Inference Latency to 66.5 Milliseconds

Faster-WAM attaches a single-layer action head to a 30-layer video Transformer and obtains world-model representations through cross-layer KV fusion, eliminating the need for the action branch to replicate the full backbone depth. The study reports a 3.2× speedup over Fast-WAM, but code and weights for the new architecture have not yet been released, and the results come primarily from simulation benchmarks.

2026-08-04

代理工具

Iris Drives ML Experiments with a Revisable Knowledge State, Achieving a 64.9% Medal Rate on MLE-Bench in 12 Hours

Rather than repeatedly modifying code along a tree of candidate solutions, Iris first investigates critical unknowns and then organizes evidence across experiments into claims that can be added, updated, or retracted. The paper reports a higher medal rate on the full MLE-Bench in half the time allotted to its direct baseline, but the system’s source code and complete execution traces have not been released.

2026-08-05

CMuon Splits Fused DiT Weights Before Orthogonalization, Training a 675M Model Twice as Fast as AdamW

CMuon finds that applying Muon orthogonalization to fused QKV, AdaLN, and FFN weights as a whole causes interference between functionally distinct subspaces. The study improves late-stage convergence through blockwise momentum orthogonalization, although the claimed 2× speedup has so far been validated only on a single 675M DiT configuration.

2026-08-04

推論系統

xPress Restores Causal Dependencies to Diffusion-Based Drafts, Boosting Qwen3-8B Decoding Throughput by About 1.3× on Average

xPress adds a single parallel causal refinement step between block-diffusion drafts and the target LLM, reducing early rejections caused by drafts in which individual tokens are plausible but the sequence as a whole is not. The study reports an average increase of about 30% in accepted draft length, but no public implementation is currently available for independent reproduction.

2026-08-04

代理工具

HALT Uses Evidence Coverage to Decide When RAG Agents Should Stop, Cutting Search Loops by Up to 45%

HALT no longer relies on a generative model’s confidence to determine whether a search is complete. Instead, it verifies each claim required to answer a multi-hop question against the available evidence. It can be added to frozen search agents, but the savings depend heavily on whether accurate intermediate claims can be generated in advance.

2026-08-04

代理工具

AgentTrajectorySentinel Uses Microsecond-Level Temporal Monitoring to Stop Agents From Going Off the Rails, Raising Task Success Rate From 52% to 73% in Tests

A new study replaces step-by-step review by a second LLM with trajectory-drift detection based on telemetry such as tool actions, latency, outputs, and token probabilities. The system costs about 200 microseconds per step, but each deployment must recalibrate it using its own normal trajectories.

2026-08-04

GitHub Repo

PosterMELD Open-Sources an Editable Research Poster Agent Pipeline That Constrains Content Generation by Layout Capacity First

PosterMELD divides paper parsing, content compression, layout, and quality repair into a multi-agent workflow while preserving native PowerPoint elements in its output. The team reports an 81.3% print-ready rate, but its quality judge, API costs, and baseline configurations still require external validation.

2026-08-04

硬體

Inflect v2 Updates Ultra-Compact Local TTS Toolkit, Letting Users Adapt Voices and Export a 4M-Parameter Model to ONNX

Inflect-Nano-v2 keeps the complete text-to-waveform model to 3.97M parameters, and a recent update adds a runnable single-speaker adaptation workflow. It is suited to offline and edge voice interfaces, but its training data, cross-lingual performance, and quality comparisons still lack independent verification.

2026-08-04

代理工具

Copilot Automations Adds Comment Triggers, Allowing Users with Write Access to Launch Agents from Issues or PRs

GitHub Copilot cloud agent automations can now monitor Issue and Pull Request comments and launch tasks such as documentation updates and bug investigations when specified text appears. The feature shortens the path from discussion to agent execution, but private automation configurations, comment input, and available tools create new permission and prompt-injection boundaries.

2026-08-04

代理工具

GitHub Copilot Cloud Agent Adds Reasoning Effort Selection, Letting Complex Tasks Use More AI Credits for Deeper Analysis

GitHub now allows developers to specify both the model and reasoning effort when launching Copilot cloud agent tasks. Higher effort may improve cross-file debugging and architectural analysis, but it increases token usage and AI Credits consumption, requiring teams to establish new cost and quality benchmarks.

2026-08-04