Live intelligence

Latest AI updates

4 updates
Products Editor selected

Anthropic Adds Experimental Code Mode to Claude Code, Letting Claude Chain Tool Calls in JavaScript

Anthropic shipped Code Mode in Claude Code v2.1.323 as an experimental, opt-in feature that lets Claude write a single JavaScript program to orchestrate multiple Bash, Read and Edit calls instead of requesting each tool call individually. Developers enable it with CLAUDE_CODE_EXPERIMENTAL_CODE_MODE=1 or via the settings env block, and it runs only in the interactive terminal on the native build with an Anthropic API or Claude subscription account. Anthropic publishes no benchmark or token-saving figure for the feature; waiting code times out after 10 minutes, while background runs can last up to 2 hours. Availability is narrow: no Bedrock, Google Cloud, Microsoft Foundry, -p, Agent SDK, VS Code or Desktop support, and admins can block it org-wide but cannot force it on.

Why it matters: It gives developers a concrete, actionable look at a new agentic tool-calling pattern in Claude Code, including how to enable it and its permission and availability constraints.

AnthropicClaude CodeAI coding agents
Research

TIGA: Tool-Grounded LLM Agents for Controlled Taxonomy Induction

Researchers introduce TIGA, a knowledge-engineering architecture that treats taxonomy induction as an iterative decision process over an explicit state and constrained action space. TIGA combines executable taxonomy-editing tools, interaction memory recording tool calls and rationales, and a runtime-adaptive organizational policy, with an optional global reviewer. Evaluated on four benchmark taxonomies with two LLM backbones, TIGA achieves the strongest structural-quality results in most configurations but does not dominate every precision measure. The gains come with substantially higher token consumption, API-call volume, and inference time, and ablation results show benefits from policy and memory components while global review depends on dataset and revision budget.

LLM agentstaxonomy inductionstructured knowledge representations
Research Editor selected

ReTrace: Distilling Tool-Using Agents into Planner-Free Workflows

ReTrace converts a natural-language SOP and a few logged agent runs into a reusable workflow where code, not an LLM, selects each next step. It extracts the conditions behind actions from the agent's written reasoning, merges them into a compact rule document, and compiles that into an executable workflow for different orchestration platforms. On 79 production procedures, ReTrace workflows reached 93.8% completion versus 96.8% for the agent at 24% lower cost per task. On τ²-Bench, workflows reached 75.8% task success versus 80.6% for the agent while running in 1.3s instead of 170s; repair lifted k=2 workflows from 66.7% to 81.2%.

Why it matters: The paper offers a concrete method and measured trade-offs for cutting LLM-agent latency and cost by compiling repeated SOPs into deterministic workflows.

LLM agentsworkflow automationtool use
Industry Editor selected

What Is the "Chain of Thought" in Agent Models?

Recently, you might have heard several fancy terms floating around: Interleaved Thinking (Claude), Thinking-in-Tools (MiniMax K2), Thinking in Tool-Use (DeepSeek V3.2), and Thought Signature (Gemini). At first glance, they sound complex—but in realit<!--autointro-->

Agent modelschain of thoughtinterleaved thinking