GitHub Repo

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

MLPerf Inference 6.1 Adds End-to-End RAG and Edge Agent Tests as Benchmark Expands to Full Inference Pipelines

MLCommons is no longer testing only individual models. Inference 6.1 incorporates retrieval, reranking, generation, and multi-turn agent workflows. The new release also introduces an API-based client/server harness, signaling that data center benchmarking will shift toward the more production-like MLPerf Endpoints suite.

2026-09-16

代理工具

IBM Identifies Unstable Agent Steps From a Single Trajectory as ALTK-Evolve Turns Diagnostics Into Reusable Guidelines

IBM Research has added a Consistency Analyzer to ALTK-Evolve that uses controlled resampling to pinpoint decisions prone to changing across repeated runs of the same agent. In AppWorld experiments, it raised a GPT-4.1 agent’s five-run all-success rate from 53% to 69%, though the evidence remains limited to a single agent architecture and a simulated environment.

2026-09-16

代理工具

RSIAgent Freezes Model Weights and Builds Reusable Environment Memory Through Autonomous Exploration

RSIAgent uses curriculum, actor, and verifier agents to first explore tools broadly and then deeply test failure boundaries, saving the results as action–condition–outcome memories. Its partial score on OSWorld 2.0 rose from 71.97 to 78.98, but the comparison mixes different budgets and selectively chosen retries, so it cannot be directly interpreted as surpassing GPT-6 in model capability.

2026-09-16

AI 安全

HazardAuditor Unifies Trajectories from Four Computer-Use Agents and Trains a Safety Gatekeeper with Sequence-Level Rewards

HazardAuditor converts tool executions from Claude Code, Codex, Hermes, and OpenClaw into a shared event format, then determines whether the overall behavior is safe. Its new GuardPO method makes the final safety verdict drive model updates, but the research data has not been released, and gains of up to 16.5 percentage points still await independent replication.

2026-09-16

推論系統

vLLM Streams Hidden States Across Nodes with Mooncake to Train a DSpark Draft Model for the 2.8T-Parameter Kimi K3

vLLM and Red Hat AI have released a 5-billion-parameter DSpark draft model for Kimi K3, along with a complete recipe for extracting and transferring hidden states across nodes. In official tests, single-user generation speed increased from about 110 to 435 tokens/s, though the results depend on a GB300 cluster and a specific inference workload.

2026-09-16

代理工具

Claude Code 2.1.273 Patches Command Permission Bypasses and Enforces Enterprise MCP Policies

Anthropic fixed two command review gaps in version 2.1.273, along with a settings-merging issue that could cause managed MCP and connector policies to be ignored. The release also adds optional request headers for LLM gateways and MCP disconnection alerts, but Anthropic has not classified these fixes as CVEs or security advisories.

2026-09-16

AI for Science／訓練基礎設施

Periodic Neon Trains a Trillion-Parameter XRD Agent on Laboratory Data and Reveals the System Bottlenecks of Long-Trajectory RL

Periodic Labs used 1,300 H200 GPUs to conduct scientific mid-training and reinforcement learning on a trillion-parameter open model, enabling Neon to automatically analyze complex X-ray diffraction results. Its 55.3% success rate and comparisons with frontier models are all based on internal data, a proprietary toolchain, and model-based judging. At this stage, it is better viewed as a testable vertical AI recipe than as a demonstrated system for autonomous scientific discovery.

2026-09-16

代理工具

FlashREINFORCE Replaces Same-Prompt Group Sampling in Agentic RL With Asynchronous Single-Trajectory Updates

NVIDIA researchers propose a critic-free, single-rollout training method that lets tool-use trajectories of varying lengths enter the update process as soon as they finish. In small-model experiments, it outperformed the reported GRPO baseline using half as many rollouts, but its stability across environments and model scales remains insufficiently validated.

2026-09-16

推論系統

Jev Abandons Text Generation for Typed Probabilistic Decisions via Parallel Sampling

TypeSafe AI’s Jev produces only predefined booleans, choices, and scores, seeking to turn model inference into low-latency branches that can be embedded directly in software. Type-correct outputs do not guarantee correct decisions, and the company’s speed and cost claims still rest on in-house workflows and undisclosed models.

2026-09-16

Gensyn open-1b Builds a Cross-Hardware, Bit-Level Audit Trail for 80,957 Training Steps

Gensyn has released the data, checkpoints, step-by-step hashes, and replay tools for its 1.61B-parameter model, allowing third parties to spot-check whether training states match its commitments. This reproducibility comes at the cost of roughly a fivefold reduction in training performance, and matching hashes alone still cannot prove that the original cluster actually ran as claimed.

2026-09-16

訓練基礎設施

TRL 1.14 Syncs Only LoRA Weights, Removing NCCL Dependency for Cross-Machine Asynchronous GRPO Training

Hugging Face distributes `AsyncGRPOTrainer` training and vLLM rollouts across separate machines, transferring only a few megabytes of LoRA adapters through shared object storage. A published experiment cut a 500-step run from 3 hours 27 minutes to 53 minutes, but the result is still based on a single small-model recipe and does not prove large-scale RL convergence or cost advantages.

2026-09-16

AI 安全

“Plan Injection” Makes Models Rewrite External Faulty Reasoning as Their Own—and Evade Chain-of-Thought Monitoring

New research finds that malicious plans phrased in benign language and inserted into context can be absorbed, rewritten, and executed by models, with even the strongest monitors missing at least a quarter of attacks. Showing monitors the original injected content or increasing the reasoning budget does not reliably improve detection, suggesting that agents cannot establish their safety solely through their output chain of thought.

2026-09-16