Archive
1535 technical news articles
代理工具
SWE-bench Science uses 98 real-world scientific software repositories to test implicit contracts involving units, coordinate systems, numerical invariants, file formats, and more. Claude Code with Opus 5 currently ranks first, but its pass@1 remains below 50%, falling to just 27.78% on engineering integration tasks.
代理工具
Microsoft has open-sourced Thinkingbox, which uses isolated MCP tool environments and executable assertions to verify whether agents actually complete their work, rather than merely checking their responses or whether tool calls are valid. The best system achieves a 65.36% single-run success rate, but that falls to just 25.25% when the same task must succeed 20 consecutive times.
Task-CoEvolve dynamically selects validation tasks based on historical disagreement among candidate harnesses, then estimates overall performance using sampling probabilities. On Terminal-Bench 2.1, it approaches full-set search performance, but the paper uses the same tasks for search and evaluation, and the code has not yet been released.
推論系統
A new method lets models adapt directly to KV eviction strategies such as H2O during fine-tuning, raising accuracy on some 128K tasks from roughly 20%–64% to over 90%. However, it does not consistently lead on natural question-answering benchmarks, and the open-source implementation remains positioned as a research tool.
推論系統
ReCache rewrites attention and positional encoding so that individual tools or skills can reuse their KV caches across requests. Qwen3 experiments show up to a 3.655× improvement in time to first token, but the method requires model fine-tuning and is not yet a drop-in inference plugin.
推論系統
Teams from Tencent WeChat and the Chinese Academy of Sciences rewrote the Hopper sparse-attention kernel, adding FP8, paged KV cache, continuous batching, and mean compensation for pruned blocks. In H20 tests, kernel-level speedups reached 47.26×, but end-to-end gains were smaller, and the current integration depends on the SGLang fork bundled with the project.
AI 可解釋性研究
The new method treats the distribution of reasoning outcomes as a piecewise-smooth sequence, uses PELT to identify genuine decision points, and applies Dirichlet kernel pooling to suppress sampling noise. Experiments on two 8B models show that it can substantially reduce resampling, though the findings currently cover only tinyMMLU multiple-choice questions.
機器人／VLA 訓練
Google DeepMind has a vision-language model first break down long-horizon robotic tasks into subgoals executable by a VLA, then fine-tunes the original model on successful trajectories and adds residual off-policy reinforcement learning. The method improves exploration efficiency in simulated tasks, but has yet to demonstrate that it can replace human demonstrations on physical robots.
GitHub Repo
Teams including Google Cloud AI Research apply the agent harness concept to the environment layer, using composable interfaces to alter initial states, visible information, and task flows. Open-source experiments span five benchmarks and deliver gains of up to 9 percentage points, although reproducing the full results still requires multiple external environments and commercial model APIs.
代理工具
Nsight AI can now connect live CUDA documentation to MCP clients such as Codex and Claude, or deploy a complete coding-assistance backend locally. The open-source Blueprint combines generation, completion, embedding, and reranking models, but the reference configuration requires a Hopper-class GPU and at least 200GB of storage.
最新模型
Ornith has released three open-weight models: a 9B model, a 35B MoE, and a 397B MoE. The training loop jointly optimizes tasks, agent scaffolds, and solution trajectories. The 397B model’s coding-agent performance approaches that of closed-source frontier models, but the figures have not yet been independently reproduced, and the model’s release documentation has a licensing gap.
代理工具
Anthropic’s updated tools can perform multiple interface actions in a single model turn while combining page structure, versioned skills, and persistent files. Existing beta integrations will continue to work, but upgrading the computer use tool changes the request format, and engineering teams must still manage browser isolation and prompt-injection risks themselves.