GitHub Repo

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

Muse Glimmer 30B Brings Multimodal Agents to a Single GPU With 17GB Quantized Weights and a DFlash Draft Model

Meta has released the Muse Glimmer 30B weights, vision encoder, and DFlash draft model. The 17GB version can run text, image, and speculative decoding workloads simultaneously within 24GB of VRAM. Meta measured an average of 233.4 tokens/s on an RTX 5090, but safety evaluations and deployment details show that the model still requires external safeguards and a newer runtime.

2026-08-12

代理工具

ChemWorld Compiles Chemical Processes Into Replayable Agent Environments, Preserving Transaction Receipts Even for Failed Actions

ChemWorld uses typed operations, a compatibility compiler, and private chemical laws to let researchers replace a single world rule while retaining the same public interface. The open-source release passed 52 generated combinations and eight end-to-end workflows, but it validates software execution semantics—not real-world chemical accuracy.

2026-08-12

代理工具

EvoMem Turns Cross-Task Optimization Experience Into Persistent Memory, Accelerating Evolutionary Search by 5.93× on Average

EvoMem extracts provenance-tracked strategy cards from successful program mutations, then retrieves up to three cards to guide the LLM on subsequent tasks. Across nine test categories, it improved the target metric by an average of 6.40%, though results varied widely and the experiments remain limited to small, research-oriented workloads.

2026-08-12

代理工具

ACM Projects Three Agent Frameworks into Versioned Configuration Graphs, Unifying Change-Impact and Runtime-Provenance Tracking

Agentic Configuration Management normalizes agents, prompts, models, tools, and workflows into configuration items that can be versioned independently. The reference implementation supports LangGraph, CrewAI, and the OpenAI Agents SDK, but validation currently focuses on small synthetic cases and author-defined oracles.

2026-08-12

AI 基礎設施

MISA-T Schedules Mixed RL Rollouts by KV Residency Time, Boosting Step3.7 Throughput by 53.3%

Rather than selecting inference nodes based solely on prefix hits, MISA-T also limits how many sessions from different workloads can occupy the KV cache concurrently. The authors measured rollout throughput gains of 43.6% to 53.3% on Step3.7 and Qwen3.6-35B-A3B, but the implementation has not yet been released.

2026-08-12

最新模型

UniF-MoE Extracts Shared Blocks Before Routing Residual Computation, Cutting Inference Time by 45.2% Versus Top-2 GMoE

Rather than deciding shared experts, FFN width, and the number of activated experts separately, UniF-MoE lets each token first select shared channels and then accumulates routing probabilities according to its remaining requirements. In the authors’ DeiT and BERT experiments, it improves accuracy and MoE inference cost, but it has not yet been validated on generative large language models or distributed expert parallelism.

2026-08-12

代理工具

Cross-Language Prompts Alter Agent Tool Paths, With Four Large Models Retaining Only 71%–73% of Their Action Policies

A Microsoft research team compared 41 languages across 2.38 million rollouts and found that agents take different tool paths when the same task is presented in another language—even with greedy decoding. The study also shows that non-English tasks rely heavily on first translating into English, although its tools are merely symbolic calls and do not capture the errors or side effects of real-world APIs.

2026-08-12

最新模型

ReRound Uses a Diffusion Prior to Rechoose Quantization Rounding, Boosting Average Accuracy of 3-/4-Bit Small Models by Up to 1.6 Points

ReRound uses no calibration corpus. Instead, it trains a conditional diffusion model on the model’s own weights to reconsider whether weights near the midpoint of a quantization interval should be rounded up or down. It preserves the existing low-bit format at deployment with no additional inference overhead, but each model requires several hours of model-specific reconstruction upfront.

2026-08-12

代理工具

Global Debugging Memory Helps AutoResearch Agents Avoid Repeating Mistakes, Raising AIDE Gold-Medal Runs from 22 to 38

With GPT‑5‑mini fixed as the model and a two-hour budget, researchers enabled a debugging advisor to share execution-environment constraints across search branches, allowing all 90 AIDE runs to produce valid submissions. The results suggest that agent scaffolds still contain substantial recoverable compute, though the experiments covered only nine tabular prediction competitions.

2026-08-12

代理工具

gpt-oss-20b Finds 13 Classes of Defects in Rope Refactoring Diffs, 12 Accepted by Maintainers

Researchers had a local model inspect only before-and-after Python refactoring diffs and identify 13 classes of behavioral changes across 217 Rope transformations. Maintainers accepted 12 as defects, but the model’s precision was only 0.67—too low to replace testing or static analysis.

2026-08-12

AI 安全

REDAgentBench Recalculates Agent Attack Rates Using Final Service States, Finding Text Trajectories Miss Up to 11.72 Percentage Points

REDAgentBench executed 1,661 attack cases across sandboxed workspace, email, browser, banking, and external file services, rather than judging harm solely from an agent’s response. When the same runs were scored using service receipts and final states, the attack success rates of all six models were 7.73 to 11.72 percentage points higher than with trajectory-only scoring.

2026-08-12

最新模型

MeViS-Audio Champion Replaces Single-Model Decisions with Candidate Mask Consensus

The winning report for MeViSv2-Audio at the eighth LSVOS breaks speech transcription, visual grounding, segmentation, and target-presence detection into a multistage pipeline, then selects a trajectory based on agreement among candidate masks. The system achieved a final score of 0.769589, although the official public leaderboard still says results are to be announced, and neither the code nor complete ablation data has been released.

2026-08-12