代理工具

Agent、MCP、coding agent、工作流自動化與評測。

AlayaWorld v1.1 Switches to a Streaming 3D Point Cache, Raising Its Long-Horizon Video Consistency Score to 89.5

AlayaWorld has rewritten the spatial memory and conditioning pipeline of its interactive world model so that camera controls, historical frames, and generated content use aligned causal VAE representations. A new report claims the highest overall consistency score on WBench, but the updated weights and inference code have yet to be released.

2026-08-14

推論系統

GCache Allocates Diffusion Caching Based on End-to-End Error Impact, Cutting Wan2.1 LPIPS to 0.0316 at the Same Speed

GCache no longer decides whether to recompute based on local similarity between adjacent denoising steps. Instead, it searches for a cache-reuse schedule with the lowest impact on final image quality. On Wan2.1, it substantially reduces deviation while maintaining a 2.17× speedup, but policy search requires multiple H100 GPUs and the implementation has not yet been released.

2026-08-14

推論系統

Trie Automata Precompute Token Masks, Delivering Up to 29× XGrammar’s Throughput for Finite-Choice Decoding in vLLM

A new method precomputes trie states and token masks for thousands to tens of thousands of valid strings, avoiding the cardinality bottleneck of general-purpose grammar compilation. The authors measured 219 requests per second at a batch size of 256, but have not yet released the implementation, and the figure also includes integration gains from bypassing the existing guided-decoding path.

2026-08-14

最新模型

混合線性注意力在完整注意力層前形成巨量啟用尖峰，規律橫跨 1.2B 至 397B 模型

新研究發現，混合線性注意力模型的巨量啟用並非隨機散布，而會在完整注意力層前形成尖峰，並於中間的線性層維持平台。團隊公開分析程式與受控模型，但完整論文圖表所用的逐筆輸入尚未全部釋出。

2026-08-14

代理工具

Model Main Effects Fall Below 3% Across Three Agent Benchmarks, as DDR Recasts Leaderboards as a Deployment Reliability Problem

A new study uses generalizability theory to decompose results from TheAgentCompany, τ²-bench, and AppWorld, finding that agent–task interactions far outweigh average differences between agents. The authors propose the DDR reporting framework, which requires model-selection decisions to disclose task difficulty, holdout validation, cost, and required sample size.

2026-08-14

代理工具

LLM Agents Send HPC Workloads to Heterogeneous Clusters, with Descriptive Hardware Data Raising the Success Rate from 48% to 87%

An LLNL team enabled agents to explore resources managed by Flux, Slurm, Kubernetes, and other systems, then translate high-level intent into verifiable job specifications. Experiments across six cloud clusters show that architecture, network, and memory metadata mainly rule out machines incapable of running a workload, rather than serving as a reliable performance optimizer.

2026-08-13

代理工具

GSR Compiles Scoring Rules into Typed Graphs, Improving Exact-Score Agreement for LLM Judges by Up to 6.75 Points

Graph-Structured Rubrics compile natural-language rubrics into typed judgment, transformation, aggregation, and gating nodes before seeing the response to be evaluated. Experiments with GPT‑OSS‑120B show that GSR outperforms flat Prometheus-style scoring, although no implementation has been released and the gains vary substantially by dataset.

2026-08-13

最新模型

64-Way Self-Consistency Voting Actually Reduces Per-Question Accuracy on Most Hard GPQA Problems

A preregistered study found that, on most GPQA Diamond questions, Qwen2.5-7B and Llama-3-8B become increasingly likely to lock onto the wrong answer as more samples are put to a vote. Overall average scores still rise slightly, showing how aggregate metrics can conceal per-question regressions.

2026-08-13

代理工具

Harness-IF Separates “What Models Would Do Anyway” From Genuine Instruction Following, Finding Gaps of Up to 7.4 Points Across 12 Coding Agents

Harness-IF distributes rules across system prompts, project files, user instructions, tool descriptions, and skill descriptions, then scores each rule using evidence from actual execution. All 12 frontier models became less accurate when rules conflicted with their default tendencies.

2026-08-13

AI 安全

VICBench Traces 100 Vulnerabilities to Their Initial Introducing Commits; Existing Automated Methods Reach Only 40.1% F1

Using independent manual and agent-based tracing, VICBench labels the vulnerability-introducing commits for 100 CVEs across Python, Java, and C++ projects. Cross-file moves and refactoring cause extensive misclassification by V-SZZ and LLM4SZZ, while also exposing reliability problems in affected-version data.

2026-08-13

最新模型

Qwen3.8 Makes 2.4T-Parameter Max-Class Weights Available for the First Time, Activating 95B per Token

Alibaba’s Qwen team has released Qwen3.8-2.4T-A95B, featuring 512 experts and a hybrid of linear and standard attention, with support for contexts of up to approximately 1.01 million tokens. The model offers adjustable reasoning depth, but accepts text only and cannot disable thinking mode, making its practical deployment requirements far higher than those of typical open-weight models.

2026-08-13

最新模型

Rankings Reverse for the Same Models as Token Limits Change, Four-Model Test Records 56,476 Inferences

A new study increased the generation limit for four open-weight models from 64 to 4,096 tokens and found that the leading model changed on all three reasoning benchmarks. Even after truncated outputs were excluded, 3% to 19% of questions changed from correct to incorrect as the budget increased, showing that a single token setting is insufficient for deployment decisions.

2026-08-13