7 papers

Multi-Agent Systems

Orchestration, collaboration, roles, and why teams of agents succeed or fail.

Papers
7
Read time
1.9h
Avg length
16m
01
Multi-Agent Systems

Why Do Multi-Agent LLM Systems Fail?

Berkeley hand-read 200+ traces from 7 multi-agent LLM frameworks, found they fail 60–86% of the time, and built MAST — a 14-mode taxonomy showing most failures come from bad *system design and coordination*, not weak models.

CEMRI, PAN, YANG ET AL. (UC BERKELEY) · ARXIV 2025 · 2503.13657V2
Read
16 min
02
Multi-Agent Systems

Drop the Hierarchy and Roles: How Self-Organizing LLM Agents Outperform Designed Structures

Stop hand-assigning roles to your agents — give them a mission, the right ordering protocol, and a strong model, and they self-organize into better teams than anything you'd design, but only if the model is smart enough to know what it doesn't know.

VICTORIA DOCHKINA (MIPT) · 2026
Read
16 min
Source
arXiv:2603.28990
03
Multi-Agent Systems

Games Agents Play: Towards Transactional Analysis in LLM-based Multi-Agent Systems

Give each agent three competing inner voices — a Parent, an Adult, and a Child, each with its own memory store — and let a referee pick which voice speaks, and your multi-agent simulations start producing the messy, repetitive, psychologically-loaded conversations real humans actually have.

MONIKA ZAMOJSKA, JAROSŁAW A. CHUDZIAK (WARSAW UNIVERSITY OF TECHNOLOGY) · 2025
Read
14 min
Source
arXiv:2507.21354
04
Multi-Agent Systems

Latent Collaboration in Multi-Agent Systems

Instead of having LLM agents talk to each other in English, let them pass their raw internal "thoughts" (hidden states and KV-caches) directly — no decoding to text — which is faster, cheaper, and actually more accurate, with zero extra training.

ZOU, YANG, QIU, LI, TIEU, LU, SHEN, TONG, CHOI, HE, ZOU, WANG, YANG (PRINCETON / UIUC / STANFORD)
Read
16 min
Source
arXiv:2511.20639
05
Multi-Agent Systems

Multi-Agent Collaboration via Evolving Orchestration

Instead of wiring your agents into a fixed graph, put a single small "puppeteer" model in charge of picking which agent speaks next at every step, and train that puppeteer with reinforcement learning to get answers that are both better and cheaper.

DANG, QIAN, LUO, FAN, XIE, ET AL. (TSINGHUA, SJTU, BUPT, SIEMENS, TENCENT) · NEURIPS 2025
Read
18 min
06
Multi-Agent Systems

TUMIX: Multi-Agent Test-Time Scaling with Tool-Use Mixture

Instead of making one agent smarter, run a dozen *different* tool-using agents in parallel, let them read each other's answers and refine for a couple of rounds, then have an LLM decide when to stop and vote on the winner — and you beat every other test-time-scaling method at the same cost.

YONGCHAO CHEN, JIEFENG CHEN, RUI MENG, ET AL. (MIT, HARVARD, GOOGLE CLOUD AI RESEARCH, GOOGLE DEEPMIND) · 2025
Read
16 min
Source
arXiv:2510.01279
07
Multi-Agent Systems

Unifying Language Agent Algorithms with a Graph-Based Orchestration Engine (AGORA)

Build every agent reasoning strategy — from plain Chain-of-Thought to tree search to visual search — as swappable "operators" inside one shared graph-workflow engine, then run them all through the same evaluation harness, and you discover that the simple ones usually win on both accuracy and cost.

ZHANG, LIAO, YING, MA, ET AL. (OM AI RESEARCH / ZHEJIANG UNIVERSITY) · MAY 2025
Read
18 min
Source
arXiv:2505.24354