AI Paper Atlas

Research map / Multi-agent systems and games / LLM agents

Great Minds Think Alike: Contextual Tacit Communication for Decentralized LLM-Agent Cooperation

Yue Pei, Hongming Zhang, Jiarui Guan, Jusheng Zhang, Liang Lin, Haogang Zhu, Ziliang Chen

ICML 2026 · Multi-agent systems and games › LLM agents · approach: LLM multi-agent decision making

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes a contextual tacit communication approach that lets decentralized LLM agents coordinate for embodied cooperation without online message passing.

Problem

LLM planners for cooperative embodied agents suffer inconsistency and miscoordination under partial observability, and explicit communication is costly or unavailable.

Approach

Uses contextual tacit communication, coordinating through shared context rather than online message passing, to avoid the independent-planning fallback when communication is removed.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add TRM rule context at test time (vs numeric rectification only) (ablation)Tact, Qwen2.5-VL-7B-SFT · VIKI-L2 (ID)ACC_ID: 77.4 -> 89.2Improved
add TRM rule context at test time (ablation)Tact, Qwen2.5-VL-7B-SFT · VIKI-L2 (OOD)ACC_OOD: 3.6 -> 30.2Improved
add residual banding for rule synthesis (ablation)Tact · VIKI-L2 (ID)ACC_ID: 10.4 -> 89.2Improved
add bias supervision for rule generation (ablation)Tact · VIKI-L2 (ID)ACC_ID: 8.5 -> 89.2Improved
add the full Tact protocol to the base planner (ablation)Qwen2.5-VL-7B-SFT planner · VIKI-L2 (ID)ACC_ID: 5.2 -> 89.2Improved
add rule constraints on top of numeric rectification (Tact vs Tact-b) (ablation)GPT-4o/Qwen backbones · VIKI-L2 (ID)ACC_ID: 5.4 -> 16.4Improved
use Tact instead of decentralized plannerQwen2.5-VL-7B-SFT · VIKI-L2 (OOD)ACC_OOD: 2.0 -> 30.2Improved
use Tact instead of SFT centralized planner under global observationQwen2.5-VL-7B-SFT · VIKI-L2 (ID)ACC_ID: 96.5 -> 89.2Hurt
use residual band 0.5 instead of 2.0 (ablation)Tact · VIKI-L2 (ID)ACC_ID: 82.6 -> 89.2Improved
use residual band 0.5 instead of 0.2 (ablation)Tact · VIKI-L2 (ID)ACC_ID: 88.4 -> 89.2Improved
loosen residual band from 0.2 to 2.0 (ablation)Tact · VIKI-L2value regret: 0.55 -> 0.92Hurt
use Tact instead of Dec-RL-ZERO with zero SFTQwen2.5-VL-3B · VIKI-L2 (zero-SFT, ID)ACC_ID: 0.72 -> 8.45Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy