最新模型

新模型、開放權重、多模態、語音、影像與模型架構。

Axon Generates Five LLM Backends from a Strongly Typed DSL, Cutting MLX Median Latency to 48.3% of Transformers

Axon expresses model architectures as functional specifications with symbolic tensor shapes, then compiles them to PyTorch, Triton, JAX, MLX, and native vLLM. Across 467 inference tests, it accelerated most generative models, though some BF16, encoder, and sequence-to-sequence models still showed accuracy or performance regressions.

2026-08-21

代理工具

Restricting Module Visibility Fosters Reusable Latent Communication; Restricted Models Lead by at Least 20 Points in 9 of 10 Paired Experiments

Four modules sharing Qwen2.5-0.5B and the same LoRA learned radically different composition strategies solely because of different attention masks. Limiting each module to its own evidence fragment made it easier to develop intermediate-value communication that transferred across examples, but the experiment still missed its preregistered overall success threshold by 0.0012.

2026-08-21

MidTool Moves Tool Use into Mid-Training, Raising Qwen3-4B’s BFCLv3 Overall Score by 10.5 Points

MidTool-Mix synthesizes 20.3 billion tokens from web pages, PDFs, code, and real-world tool interfaces, enabling models to learn tool boundaries, parameters, and workflows before SFT and RL. With the same SFT recipe, Qwen3-4B’s BFCLv3 overall score rises from 39.73% to 50.25%, although deep-search tasks remain entirely unsolved.

2026-08-21

AI 安全

Even a Frozen Qwen3-8B Shows “Capability Expansion,” Prompting Researchers to Call for Empirical Null Baselines in Self-Improvement Evaluations

New research finds that single-run greedy decoding and unstable thresholds can make a completely untrained model appear to gain or lose capabilities. After switching to exact per-item tests, three forms of self-training only consistently strengthened existing capabilities, with no evidence that they acquired new capabilities never demonstrated by the base model.

2026-08-21

代理工具

CentaurBench: The Model Best at Solving Problems Independently May Not Be the Best at Guiding Another Agent

CentaurBench separately evaluates models’ automation and assistance capabilities across seven work tasks, finding a correlation of only about 0.48 between the two rankings. Unassisted GPT-3.5-Turbo outperformed every guided version on three tasks, showing that adding a powerful model does not necessarily improve an agent workflow.

2026-08-21

代理工具

TrueForge Open-Sources Agent Execution Framework, Claims 30% to 75% Lower Costs Across 14 Enterprise Tasks

TrueFoundry has released TrueForge under the MIT License, combining agent loops, MCP tools, on-demand sandboxes, subagents, and approval workflows into a self-hostable execution framework. In its Enterprise-Bench report, the company claims savings of about 30% using the same model and about 75% after switching to GLM-5.2, although the comparison covers only 14 tasks.

2026-08-21

代理工具

Slack Code Brings Coding Agents into Shared Channels, With Diff Views, Live Previews, and Human Approval

Salesforce has launched Slack Code, allowing teams to create project-specific Code Channels directly from conversations and collaboratively monitor, revise, and approve agent-generated code. Initial integrations include Claude, Devin, GitHub Copilot, ChatGPT, and Vercel agents, but details about security isolation, permission granularity, and APIs have yet to be fully disclosed.

2026-08-21

代理工具

DeepWeaver Weaves Evidence Before Generating Answers, Raising DeepSeek-V4-Flash’s Argument Sufficiency from 75.4% to 86.5%

DeepWeaver uses a Thought Block Chain to organize claims, key information, and sources, then repeatedly checks for evidence that has not yet been used. It improves long-form responses and citation metrics across several models, but the new benchmark focuses on Chinese-language water environment questions, and the code has yet to be released.

2026-08-20

推論系統

Liquid AI Adds DSpark Draft Models to LFM2.5, Delivering Up to 3.18× Faster Decoding on a Single H100

Liquid AI has released three DSpark draft models with roughly 300 million parameters, enabling LFM2.5 to verify multiple candidate tokens at once through speculative decoding. Tests with batch size 1 and greedy decoding showed speedups of up to 3.18×, but SGLang support remains in an open PR, leaving deployment maturity yet to be validated.

2026-08-20

代理工具

SkillForge Synthesizes Failures from Project Tests First, Lifting SWE-bench Verified Scores by More Than 5 Points for Two Coding Agents

Before real-world issues arrive, SkillForge creates verifiable failures from execution paths covered by tests, then distills repair trajectories into project-specific skills. When paired with Mini-SWE-Agent, it raises SWE-bench Verified Pass@1 for DeepSeek-V3.2 and GPT-5-mini to 72.2% and 60.6%, respectively.

2026-08-20

Open-MOPD Reallocates the Token Budget for Multi-Teacher Distillation, Raising Capability Integration from 35.6% to 83.4%

Open-MOPD finds that the main bottleneck in multi-teacher online policy distillation is not conflicting teacher gradients, but a severe imbalance in the effective number of token updates allocated across domains. By combining token-share balancing, gap-aware allocation, and student reward refresh, it recovers 83.4% of the available capability gains in a single 3B model.

2026-08-20

科學機器學習

Monroe Pretrains a Graph Model on 81 Million Molecules; Frozen Embeddings with TabPFN Outperform Per-Task Fine-Tuning

Monroe combines sparse graph attention, stereochemical edges, and 1,152 pretraining objectives, then uses TabPFN for in-context prediction on frozen molecular embeddings. It ranks in the statistically best-performing group across all 28 Polaris tasks, although its “100% win rate” includes ties in which it is not significantly different from the best method.

2026-08-20