关注大模型推理能力、思考模式、评测与推理技术更新。
## What's Changed * fix(cli): scope the ACP permission queue to the session by @chiga0 in https://github.com/QwenLM/qwen-code/pull/11802 * feat(channels): add shared output modes with DingTalk support by @qqqys in https://github.com/QwenLM/qwen-code/pull/11822
IT之家 9 月 19 日消息，OpenAI 研究员诺姆 · 布朗（Noam Brown）最新表示，伴随着 AI 模型能力越来越强，模型的思维链可监测性正逐渐下降，未来开发者可能无法有效、可靠地发现、解释并约束 AI 的风险行为。 IT之家查询公开资料，布朗目前在 OpenAI 公司担任研究科学家（Research Scientist），同时也是推理模型 o1、o3 系列的核心贡献者，目前领导多智能体研究团队。 因其创新性的工作，他被《麻省理工科技评论》(MIT Tech Review) 评为“35 位 35 岁以
## Bug Fixes - New local TUI sessions now leave reasoning summaries disabled by default, fixing request rejection by providers that do not support them. Explicit reasoning-summary settings remain respected. (#46467) ## Changelog Full Changelog: https://github.
## Verify Docker Image Signature All LiteLLM Docker images are signed with [cosign](https://docs.sigstore.dev/cosign/overview/). Every release is signed with the same key introduced in [commit `0112e53`](https://github.com/BerriAI/litellm/commit/0112e53046018d
## New Features - Added experimental `/voice` conversations with live transcripts and microphone controls on supported builds, enabled through `/experimental`. (#43581, #43651, #44331) - The TUI now shows live reasoning summaries in the status row and completi
## What's Changed * fix(cli): scope the ACP permission queue to the session by @chiga0 in https://github.com/QwenLM/qwen-code/pull/11802 * feat(channels): add shared output modes with DingTalk support by @qqqys in https://github.com/QwenLM/qwen-code/pull/11822
## What's Changed ### Features - Support aliases as connection identifiers - Record reasons for deployment creation failures - Collect human feedback and pause events in tracing - Add `llm_overlay` context variable to route agent roles to models - Carry `task_
Alibaba released the open weights for Qwen3.8-2.4T-A95B (Qwen3.8-Max), its largest open-weight model, bringing near-frontier capabilities to the open...
AI agents on foundation models often misapply healthcare and life sciences decision frameworks, citing the right guideline but applying it incorrectly. This post shares 38 open-source agent skills across 11 HCLS domains that close this gap, with installation s
## Verify Docker Image Signature All LiteLLM Docker images are signed with [cosign](https://docs.sigstore.dev/cosign/overview/). Every release is signed with the same key introduced in [commit `0112e53`](https://github.com/BerriAI/litellm/commit/0112e53046018d
Know everything. Do anything. That was the message NVIDIA founder and CEO Jensen Huang brought to Salesforce Dreamforce Tuesday, joining CEO Marc Benioff onstage in an appearance that coincided with the announcement of Koa — Salesforce’s first CRM reasoning mo
## Verify Docker Image Signature All LiteLLM Docker images are signed with [cosign](https://docs.sigstore.dev/cosign/overview/). Every release is signed with the same key introduced in [commit `0112e53`](https://github.com/BerriAI/litellm/commit/0112e53046018d
# v0.29.0 ## Highlights This release features 594 commits from 277 contributors (91 new)! * **Model Runner V2 is now the default for all models** (#53183), completing the rollout that began with pooling models (#48290). MRV2 also gained CUDA graph memory profi
Changes since langchain-openai==1.6.1 release(openai): 1.6.2 (#40339) fix(openai): add GPT-6 Astra reasoning efforts (#40330) chore(deps): bump httpx2 from 2.10.0 to 2.12.0 in /libs/partners/openai (#40309)
Meet GPT-6 Astra, OpenAI’s most capable model for business, with advanced reasoning, computer use, and stronger writing and design judgment.
Changes since langchain-openai==1.6.0 fix(openai): bump `max_completion_tokens` in cache breakpoint integration test (#40284) release(openai): 1.6.1 (#40268) chore(model-profiles): refresh model profile data (#40217) fix(openai): support Azure AD auth with Ope
Running reasoning and agentic AI at the edge has been harder than it needs to be. Until recently, models capable of multi-step reasoning were too large to run...
# Dify 1.15.0 Release Note ## What's Changed ### UX & UI Enhancements - **Redesigned landing / onboarding** for an easier first-run experience (#37433, #37844, #37800) - **Faster navigation** — improved "go to anything" palette and autofocused search inputs (#
## What's Changed * fix(formatter): derive audio format from media type by @ump45nose in https://github.com/agentscope-ai/agentscope/pull/2301 * fix(gemini): exclude tool-execution tokens from output_tokens by @iluv7 in https://github.com/agentscope-ai/agentsc
AI factories must support increasingly large models and more complex reasoning workloads. To keep up with the insatiable compute demands of AI workloads,...
### Summary of major features and improvements * Functionally enabled Muse-Glimmer-30B model: * Model card and IR available: [OpenVINO/Muse-Glimmer-30B-int4-ov · Hugging Face](https://huggingface.co/OpenVINO/Muse-Glimmer-30B-int4-ov) * Notebooks to try: * [Mus
# v0.28.0 ## Highlights This release features 584 commits from 270 contributors (76 new)! * **Kimi-K3 performance push**: a major optimization effort for Kimi-K3 across the stack — Decode Context Parallel (DCP) support (#50484), fused FlashKDA decode and prefi
来源标注日期：2026-08-21（未提供具体时刻）。 Today, the new multimodal vision understanding model DeepSeek-V4-Flash-Vision-Exp is now available on the DeepSeek API platform. This is an experimental model that can be accessed by setting model='deepseek-v4-flash-vision-exp'. Ter
Long-running AI agents spend most of their time on high-volume execution: tool calls, result validation, and subagent delegation. Using a frontier reasoning...
Autonomous vehicle (AV) development often relies on separate models for trajectory generation, high-level intent prediction, scene understanding, and data...
Modern vision-language models (VLMs) can support tasks such as visual question answering, captioning, and image-text reasoning. In practice, however, the data...
A path, a fence, a knot. MindTopo sets a new benchmark for testing how AI understands topological relationships and highlights new opportunities to strengthen spatial reasoning and planning. The post MindTopo reveals VLMs’ spatial reasoning abilities appeared
Radiology AI is evolving beyond report generation. CARE-X explores a unified approach that combines flexible reasoning, calibrated predictions, and measurement-based tools for chest X-ray interpretation. The post Introducing CARE-X: Towards Clinically Useful R
# Highlights *582 PRs from 194 contributors.* **Kimi K3 day-0 support**: A 2.8T-parameter multimodal LatentMoE (896 experts, top-16, routed in a 3584-dim latent space) with a 1M-token context, 69 KDA linear-attention layers interleaved with 24 MLA layers, and
## What's Changed * fix(kimi): use remaining context for completion budget by @RealKai42 in https://github.com/MoonshotAI/kimi-cli/pull/2494 * fix(kosong): preserve empty-string reasoning_content as ThinkPart by @bigeagle in https://github.com/MoonshotAI/kimi-
