Archive
Agent、MCP、coding agent、工作流自動化與評測。
LLMOps
The new release can copy a small sample of real requests to a candidate router, then use a blinded judge to compare responses without affecting production results. Complexity classification also no longer treats a fixed agent system prompt as a signal of each request’s technical difficulty.
代理工具
The new release provides scriptable model and sandbox testing tools, allowing multi-turn agent workflows to be reproduced in CI without calling model providers. The upgrade also adds compatibility with OpenAI Python 3 and HTTPX 2, while fixing issues involving interruption state, tool approvals, and sensitive error leakage.
代理工具
StateBridge aligns the sending agent’s final-layer hidden states with the receiver’s embedding space and injects them directly as a continuous prefix. It matched or achieved the best result in 22 of 26 tests across four open models, but remains limited to same-model agents whose internal states are accessible.
推論系統
Community testing indicates that Apple Silicon inference frameworks still cannot reliably provide built-in MTP speculative decoding, hybrid-state prefix caching, and batched serving at the same time. The problem affects more than benchmarks: it can also force long-running coding agents to repay the prefill cost on every conversational turn.
AI 安全
A new open-source protocol lets agents create Ed25519 signatures and witnessed append-only records for memory, identity, and actions, while providing a zero-dependency offline verifier. It turns persistent-memory poisoning into a detectable integrity problem, but still cannot prove that a memory was originally true and has not yet become an IETF standard.
最新模型
Google is rolling out Gemini 3.7 Flash across its API, Antigravity, Android Studio, and enterprise agent platforms, offering a limited-time 50% discount to capture high-volume agent workloads. Early integrations show that multimodal input, tool calling, and cross-API formats are already supported, but reasoning parameters and cost data still pose migration pitfalls.
AI 安全
SkillMisevo-Bench tracks how agents generate, retrieve, and reuse skills from execution traces, finding that all 21 evolution-capable configurations produced unsafe artifacts. SafeEvolve can reduce downstream harm, but the evidence is currently limited to four CLI agents and controlled computer-use tasks.
代理工具
QuoteBench holds model output constant and changes only how Bash commands are transported and reparsed, directly measuring failures caused by the agent interface. Its results show that near-perfect schema adherence can still conceal widespread quoting and escaping errors.
代理工具
A new evaluation decomposes agentic R&D into Solution Framing, Execution, and Feedback Control, while using counterfactual experiments to measure whether memory genuinely improves the next decision. Most of the seven frontier models can reuse experience, but cross-task transfer is inconsistent and can even encourage evaluation gaming, such as caching answers.
推論系統
vToken adds a logical token table and asynchronous compaction on top of the existing PagedAttention design, allowing per-token eviction to actually release physical blocks. Its vLLM prototype improves SLA-constrained throughput by up to 1.37×, but the code has not yet been released, and the authors have not shown that its data-movement costs are suitable for all hardware and workloads.
代理工具
DiG-bench uses 70 entirely new text-based games that require models to experiment independently and infer unknown rules and victory conditions. Opus 5 leads by solving 50, but existing agent frameworks do not consistently outperform the base model loop on the most difficult problems.
最新模型
DeepSeek has moved V4-Pro-0813 into general availability, with the existing `deepseek-v4-pro` name now pointing directly to the new version. The update strengthens coding agents and tool use while adding an OpenAI Responses API compatibility layer, although the published scores still come primarily from the company’s official harness.