Meta iterates Muse Spark toward long-horizon agentic coding

Meta Superintelligence Labs shipped Muse Spark 1.3 (9/2), an agentic-coding iteration of the Muse Spark line: better long-horizon task sustainment, generating its own context from messy or conflicting sources, proactively correcting plan gaps, and self-tracking learnings; collaboration behaviors (clarifying questions on ambiguous prompts, asking for help when stuck, confirming before consequential actions); fewer dropped constraints on long-form instructions; better routing inside messy single-threaded contexts including interruptions; improved self-awareness of knowledge limits ('hitting hurdles rather than hallucinating outcomes'); and cleaner coding output with fewer unnecessary turns. Meta engineer comparisons vs 1.2: ~20% fewer tool calls and ~25% fewer tokens. Available in Muse Code and the Meta Model API (max-reasoning variant live on both); a Muse Spark open-weights release is teased but undated.

The US-lab frontier coding-agent line is iterating on agent-efficiency economics (~20% fewer tool calls, ~25% fewer tokens is a direct cost cut at fixed capability), and the open-weights tease matters for the open-weight competitive landscape (trend #1's US supply side). Beyond that, the collaboration behavior set — ask, confirm-before-consequence, admit limits — is becoming table stakes for deployed agents, and it is useful as a checklist when specifying your own agent behavior.