Tag
Explains how to create the custom subagent luna_worker in Codex, including the full prompt and configuration method, referencing @Saccc_c's approach to help users run tasks in parallel.
In the article, the author traces the evolution of subagent paradigms in AI coding assistants over the past year, and introduces 'Swarm Coding' as a consolidated agent skill that delegates subagent management to an agent itself.
Nader Dabit visualizes the speed difference between 1,000 tok/s subagents and 85 tok/s, highlighting that lightning skill offload enables ~5x faster execution by using subagents for implementation while keeping frontier models as planners and reviewers.
GPT-5.6 Sol Ultra, released by OpenAI, reportedly proved the 50-year-old Cycle Double Cover Conjecture in under one hour using 64 subagents, marking a major AI breakthrough.
Anthropic benchmark shows that using a larger model (Fable) as orchestrator with cheaper models (Sonnet) as workers achieves 96% of full Fable performance at 46% cost, available now in Claude Code.
Detailed introduction to the most practical prompt engineering tips before Fable5 goes offline, including letting the model run experiments autonomously, optimizing workflows, and reducing token consumption through subagent allocation, along with other practical experiences.
Practical tips for using AI coding tools like Fable and Opus: let them apply their own judgement instead of dictating behavior, and delegate smaller tasks to lower-power models via subagents to save tokens and improve efficiency.
A tweet argues that subagents are an antipattern in AI/software design.
LangChain's Deep Agents now supports dynamic subagents, where the main agent writes orchestration code to coordinate work at scale, enabling workflows like processing hundreds of documents with deterministic coverage.
Boris Cherny, head of Claude Code at Anthropic, explains four key loops (stop hooks, verification, subagents, and memory) that make the tool highly effective for coding tasks, with simple configs that senior engineers use to outpace others.
This week's Phoenix update adds server-side bash for PXI subagents with sandboxed execution and built-in GraphQL access, improving feedback visibility and agent capabilities.
A tweet highlights Q from Korea achieving a session with nearly 300 subagents running for over a day using the Codex desktop app and lazycodex, showcasing frontier agentic engineering.
Anthropic's Ultracode is a highly efficient token-burning coding agent that excels at parallelized subagent-based dynamic workflows, though it requires proper repo setup to fully leverage its capabilities.
Xiaomi released MiMo Code, a free AI coding assistant with persistent memory across sessions, automatic subagents, and workflow distillation, requiring zero configuration.
Arize Phoenix announces an experimental feature for PXI to spin off subagents, keeping the main context window lean during long investigations.
Announces first-class support for subagents and background tasks observability, likely a new feature in an AI agent framework or tool.
Boris Cherny announced nested subagent support in Claude Code, allowing agents to spawn subagents for better context management, capped at depth 5 and rolling out in today's release.
Neural_avb highlights how Minimax M3's RLMs use subagent swarms with pydantic contracts for type checking and schema validation, reducing hallucination rates and failed subagent calls.
Explores a common failure mode in recursive language models (RLMs) where free-text subagent responses cause issues, and presents a solution using structured outputs to improve reliability, illustrated with a long-context question-answering example from NarrativeQA.
This paper introduces SearchSwarm, a model trained on synthesized delegation intelligence to improve long-horizon deep research tasks via task decomposition and subagent coordination, achieving state-of-the-art results on BrowseComp benchmarks.