Archive
新模型、開放權重、多模態、語音、影像與模型架構。
推論系統
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.
代理工具
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.
開發者平台
OpenAI plans to replace Custom GPTs with Plugins that include Skills and Apps. Affected Enterprise workspaces are scheduled to stop running legacy GPTs on December 11. The built-in migration handles only some settings, while Custom Actions must be rewritten as supported connectors or custom MCP servers.
代理工具
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.
AI 安全
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.
推論系統
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.
代理工具
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.
AI 安全
A new benchmark rewrites 150 SWE-bench Verified tasks into 750 issues containing security traps, testing whether automated repair agents will deliver code that is functionally correct but insecure. Across three model backends, an average of 51.7% of cases achieved both the repair and attack objectives, while common model reviews and static analysis still missed many malicious patches.
AI for Science／訓練基礎設施
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.
最新模型
Using Nemotron 3 Super as its foundation, Salesforce trained Koa, its first CRM reasoning model, through synthetic enterprise scenarios, SFT, and GRPO. It delivers clear improvements in multi-turn tool use, but the paper acknowledges that its overall performance still trails the strongest frontier models, while the official claim of “three times fewer errors” comes from Salesforce’s own CRM benchmark.
代理工具
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.
搜尋與推薦系統
Google Research distills a set-level search strategy learned through reinforcement learning into a lightweight diffusion model that can generate multiple vectors in parallel. Experiments claim a 12× to 20× speedup over autoregressive expansion, but the evidence so far is concentrated on fashion data and a non-public music dataset.