@yoheinakajima: more ppl are now trying out this approach of agents communicating with a shared state (vs talking to each other)
Summary
Azalia Mirhoseini highlights DeLM, a decentralized language model approach where agents communicate via shared state, achieving ~10% improvement on SWE-bench Verified with Gemini-3 Flash at less than half the cost.
View Cached Full Text
Cached at: 06/18/26, 02:01 AM
more ppl are now trying out this approach of agents communicating with a shared state (vs talking to each other)
Azalia Mirhoseini (@Azaliamirh): Thank you @VentureBeat for covering our work on Decentralized Language Models (DeLM)!
DeLM makes agentic tasks like coding and multi-doc Q&A more accurate and significantly cheaper, e.g. a ~10% jump on SWE-bench Verified with Gemini-3 Flash at less than half the cost.
Similar Articles
Decentralized Multi-Agent Systems with Shared Context
This paper introduces Decentralized Language Models (DeLM), a framework for multi-agent systems that uses parallel agents with a shared verified context to improve test-time scaling and reduce costs, achieving state-of-the-art results on SWE-bench Verified and LongBench-v2.
@Thom_Wolf: Multi-agents collaborations are among the most interesting agent behaviors right now! We did an experiment the other da…
An experiment with over 100 AI agents collaborating for a week to improve Gemma 4 inference speed in vLLM achieved a 5x speedup, revealing emergent behaviors like self-policing, division of labor, and communal knowledge sharing.
@rohanpaul_ai: A new Stanford paper just proved that decentralized multi-agent systems can beat Claude Code and Codex on complex codin…
A Stanford paper introduces DeLM, a decentralized multi-agent framework that removes the central coordinator in favor of a shared context and task queue, reportedly running up to 2.49× faster and gaining up to +19.2 points in accuracy over Claude Code and Codex baselines on Terminal-Bench 4.0, DeepSWE v1.1, and ProgramBench. Code, 720 trajectories, and an open-source plugin for Codex and Claude Code are released.
See What I See, Know What I Think: Dense Latent Communication Across Heterogeneous Agents
This paper presents a method for dense latent communication between heterogeneous multi-agent systems using aligned KV-cache transformation, achieving better performance than text-based methods with lower computational costs.
@omarsar0: The hard part of multi-agent systems is getting agents to stay quiet. Put five agents on one task, and they duplicate w…
Offloop introduces D1, a dispatcher model for multi-agent systems that reduces redundant work and token usage, achieving state-of-the-art performance on GDPval at lower cost.