共享上下文挤掉等待气泡：Stanford Azalia Mirhoseini 等 DeLM，准确率最高 +17.5、快至 2.49×

View PDF HTML (experimental)

Abstract:Multi-agent systems (MAS) can scale large language model agents on long-horizon tasks by running them in parallel, yet existing designs waste much of this parallelism in bubbles: agent time spent waiting on others or redoing a peer's work. These bubbles stem from how agents communicate. Independent agents share nothing and rediscover what their peers have already found; peer-communicating agents wait at synchronous rounds; and under centralized orchestration, the main agent blocks on its sub-agents while progress is relayed. We propose Decentralized Language Models (DeLM), a MAS framework on top of existing agent harnesses that squeezes out these bubbles by replacing the main agent with a shared context and a task queue. Agents asynchronously claim tasks, publish findings as soon as they are available, and build on or correct one another's progress, with every peer's status visible to all. On long-horizon tasks from Terminal-Bench 4.0 and DeepSWE v1.1, and on SWE-bench Verified, DeLM is both more accurate and faster than Codex, Claude Code, their native subagents, and AOrchestra in every setting, improving accuracy by up to 17.5 points over the strongest baseline and running up to 2.49x faster than the harness it builds on. On ProgramBench, where agents rebuild programs from scratch, DeLM makes faster progress than Claude Code and finishes a 120-minute budget up to 19.9 points higher in test pass rate. The code is available on our project website at this https URL.

Submission history

From: Yuzhen Mao [view email]
[v1] Tue, 9 Jun 2026 10:13:07 UTC (260 KB)
[v2] Thu, 1 Oct 2026 07:39:33 UTC (415 KB)
[v3] Sun, 4 Oct 2026 11:40:11 UTC (344 KB)