SURL AI News
繁中English日本語

Archive

代理工具

Agent、MCP、coding agent、工作流自動化與評測。

最新模型

Muse Glimmer 30B Brings Multimodal Agents to a Single GPU With 17GB Quantized Weights and a DFlash Draft Model

Meta has released the Muse Glimmer 30B weights, vision encoder, and DFlash draft model. The 17GB version can run text, image, and speculative decoding workloads simultaneously within 24GB of VRAM. Meta measured an average of 233.4 tokens/s on an RTX 5090, but safety evaluations and deployment details show that the model still requires external safeguards and a newer runtime.
AI 輔助科學研究

Dual-Agent Research System Derives a New Lower Bound for the Grothendieck Constant From Repeated Failures, but the Key Pivot Still Came From Humans

Using reasoning models, coding agents, and file-based memory across roughly 240 research sessions, a team ultimately proposed—and the authors verified—`K_G ≥ 6π/11`. The system demonstrated strong local proof capabilities but did not independently recognize that its search had reached a bottleneck; research direction and decisions about which results to pursue still depended on roughly 40 human instructions.
代理工具

ChemWorld Compiles Chemical Processes Into Replayable Agent Environments, Preserving Transaction Receipts Even for Failed Actions

ChemWorld uses typed operations, a compatibility compiler, and private chemical laws to let researchers replace a single world rule while retaining the same public interface. The open-source release passed 52 generated combinations and eight end-to-end workflows, but it validates software execution semantics—not real-world chemical accuracy.
代理工具

Cross-Language Prompts Alter Agent Tool Paths, With Four Large Models Retaining Only 71%–73% of Their Action Policies

A Microsoft research team compared 41 languages across 2.38 million rollouts and found that agents take different tool paths when the same task is presented in another language—even with greedy decoding. The study also shows that non-English tasks rely heavily on first translating into English, although its tools are merely symbolic calls and do not capture the errors or side effects of real-world APIs.
代理工具

Global Debugging Memory Helps AutoResearch Agents Avoid Repeating Mistakes, Raising AIDE Gold-Medal Runs from 22 to 38

With GPT‑5‑mini fixed as the model and a two-hour budget, researchers enabled a debugging advisor to share execution-environment constraints across search branches, allowing all 90 AIDE runs to produce valid submissions. The results suggest that agent scaffolds still contain substantial recoverable compute, though the experiments covered only nine tabular prediction competitions.
AI 安全

REDAgentBench Recalculates Agent Attack Rates Using Final Service States, Finding Text Trajectories Miss Up to 11.72 Percentage Points

REDAgentBench executed 1,661 attack cases across sandboxed workspace, email, browser, banking, and external file services, rather than judging harm solely from an agent’s response. When the same runs were scored using service receipts and final states, the attack success rates of all six models were 7.73 to 11.72 percentage points higher than with trajectory-only scoring.
代理工具

Agent instruction files grow by an average of 226%; study curbs CLAUDE.md bloat with “rule rationales”

A study of 1,867 public repositories found that agent instruction files such as CLAUDE.md continually accumulate rules while older rules are deleted less and less often. Controlled experiments showed that retaining model-readable rationales for adding rules can eliminate 99.3% of superfluous instructions, though the results have yet to be prospectively validated in large real-world codebases.
AI 軟體與企業管理

Microsoft Adds Separate Removal and Sign-In Controls After OneDrive Photos Was Accidentally Pushed to Enterprise PCs

The OneDrive photo experience, still in internal testing, was accidentally enabled more broadly, exposing an entry point on some managed Windows 11 PCs. Initially, it could not be removed separately while retaining the sync client. Microsoft has now added administrator sign-in policies and standalone uninstallation to the Microsoft 365 Roadmap, but both fixes remain scheduled for future release.
最新模型

MeViS-Audio Champion Replaces Single-Model Decisions with Candidate Mask Consensus

The winning report for MeViSv2-Audio at the eighth LSVOS breaks speech transcription, visual grounding, segmentation, and target-presence detection into a multistage pipeline, then selects a trajectory based on agreement among candidate masks. The system achieved a final score of 0.769589, although the official public leaderboard still says results are to be announced, and neither the code nor complete ablation data has been released.