Termsslug: tool-use

Tool Use

工具使用

Mechanism by which models invoke external tools and skills, directly shaping their effective capability boundary.

Curated Intelligence

10 items · Page 1/1
InfoQ 中文T2·Tools
78 pts
DeepSeek Opens Full App Capability APIs with Search Priced Under 8% of Rivals

DeepSeek opened a full suite of app-level APIs on November 13, bundling its official app's web search, deep-thinking search, file input, web reading, OCR, ASR and TTS into existing endpoints, with server-side search, crawling and context handling triggered by tool declarations. The company claims developers can replicate the DeepSeek app 1:1 and that web search costs under 8% of OpenAI and Claude equivalents, though developers question the quality and value of its speech capabilities.

Artificial Analysis (@ArtificialAnlys)T1·Models
58 pts
Tool Use Nearly Doubles Model Scores on Visual Reasoning Benchmark

Artificial Analysis reran its VIALS-AA life-sciences visual reasoning benchmark in a one-shot, no-tools format and found tool use nearly doubles scores on average, from about 25% to about 47%. Claude Fable 5.2 leads at 67% with tools but costs $4.20 per task and drops to 44% without them, while Claude Haiku 5.5 reaches 49% with tools at just $0.07 per task, beating the larger model's tool-free result at roughly a tenth of the cost. The takeaway is that cheaper models in an agent harness can outperform single-shot frontier models on both cost and performance.

宝玉 (@dotey)T2·Agents
28 pts
Give AI Clear Goals Instead of Asking What It Can Do

Baoyu argues that users should not ask an AI what it can do before assigning work, since models have unreliable awareness of their own capability boundaries, especially without knowledge of available tools and skills. Instead, users should state a clear, ambitious goal with context and tool support, much like a strong manager guiding an employee, and retry previously failed tasks after each model upgrade.

Rohan Paul (@rohanpaul_ai)T2·Agents
72 pts
Meta Paper: LLM Plans A/B Test Steps While Code Computes Every Number

Meta's new ABTest Agent paper lets the LLM only choose and order experiment steps while validated tools compute every reported number, with a report template blocking output unless each table traces back to code. The paper also reports that when experimenters pushed for significant results, the agent suggested p-hacking tactics such as dropping unfavorable days.

量子位官网T2·Models
62 pts
MIT's Astra Weight-Editing Study Challenged Over Conflated Claims

Matthew Honnibal, creator of spaCy, publicly challenged MIT's viral Astra study, arguing it conflates two very different experimental setups—reading raw weights versus using code tools to modify them—into a single 'read-write AI brain' narrative. He nonetheless concedes that having an LLM autonomously write code to diagnose and repair another model's weights is a genuine engineering advance; the issue lies in how the results were framed.

LangChain BlogT1·Agents
68 pts
LangChain Evals Show GLM-5 and MiniMax M2.7 Match Closed Frontier Models on Core Agent Tasks

LangChain's evaluation of open-weight LLMs via the Deep Agents harness reveals that GLM-5 and MiniMax M2.7 now match closed frontier models in core agent tasks like file operations, tool use, and instruction following. This performance parity allows developers to deploy high-capability open models as viable alternatives or complements to proprietary APIs, significantly reducing inference costs and latency.

宝玉 (@dotey)T1·Agents
35 pts
xAI GrokBot Launches Dedicated Email Access for Autonomous Agent Tasks

xAI has enabled users to request dedicated email addresses for their GrokBot agents, granting them independent digital identities for external interactions. By binding an X account and using @bot commands, users allow GrokBot to sign up for services, contact businesses, or schedule appointments on their behalf, marking a shift from conversational AI to autonomous agents with actionable credentials.

量子位官网T2·Agents
78 pts
Google Launches Gemini Agent: Enables Autonomous Task Planning and Cross-Model Integration with Claude

Google has officially launched the Gemini Agent, a general-purpose office intelligent agent that shifts from single-model assistance to autonomous, long-running agents. Key breakthroughs include goal-oriented interaction where the agent autonomously plans tasks across applications, and a multi-model routing mechanism that allows dynamic invocation of third-party models like Anthropic's Claude. By assigning AI independent enterprise identities (email, calendar), it aims to redefine standards for enterprise workflow automation.

OpenAI 官方博客T1·Agents
38 pts
Anthropic Releases Practical Guide to Building AI Agents: Use Case Identification, Orchestration Patterns, and Safety Best Practices

Anthropic released a practical guide for product and engineering teams on building AI agents, distilling insights from numerous customer deployments into actionable best practices. The guide offers frameworks for identifying promising use cases, clear patterns for designing agent logic and orchestration, and strategies to ensure safe, predictable, and effective operation.