multi-agent collaboration
Multiple AI models can collaborate on a task by communicating and debating solutions. They take turns proposing, verifying, and refining ideas, which helps catch errors and combine strengths. This iterative process often leads to better accuracy than relying on a single model.
The papers explore how to make this collaboration more effective. Common strategies include pruning less helpful agents during discussion, focusing self-reflection only on the agent that caused a failure, and adaptively organizing memory based on task outcomes. Training on instructions where agents disagree and learning optimal team compositions also improve results. These methods outperform simpler approaches across various benchmarks.
- Papers
- 20
- Released code
- 0
- First seen
- June 2026
- Latest
- Nov 2026
16 papers in the last two months, against 3 in the two before.
Start here
Three papers to read first, in the order they came out- 1AI agents often delay checks most closely linked to success
Goal-aware dynamic multi-agent collaboration with execution graphs and per-agent goal contexts improves success on long-horizon tasks over existing baselines.
Oct 2026 - 2AI models find the best team deal in only 14% of conflicts
A benchmark of 240 teamwork tasks shows top AI models score at most 82.2 out of 100 as teammates, and equal capability does not predict equal collaboration.
Nov 2026 - 3AI agents can outperform solo attempts and one large team
Parallel teams of collaborating agents beat both independent agents and one large team for scaling test-time compute.
Nov 2026
How fast it is moving
Often studied with
agentic evaluationMeasuring AI agents' performance in complex tasks, highlighting failures in planning, monitoring, and real4 togetherlarge language modelA neural network trained on massive text corpora to generate coherent text and perform diverse language tasks.4 togethercredit assignmentDetermining which actions or steps in a sequence contributed to a final outcome, often for reinforcement learning.3 togetherWho is working on it
The papers
Most central to this idea first, not most recent.
- Top Universitycs.AI
AI models find the best team deal in only 14% of conflicts
A benchmark of 240 teamwork tasks shows top AI models score at most 82.2 out of 100 as teammates, and equal capability does not predict equal collaboration.
Stanford University, University of Oxford · Nov 2026
- Independentcs.AI
AI agents can outperform solo attempts and one large team
Parallel teams of collaborating agents beat both independent agents and one large team for scaling test-time compute.
Nov 2026
- Chinese Techcs.MA
AI agents complete only one in 16 collaboration tasks
A benchmark built from recombined collaboration structures tests whether multi-agent AI systems really coordinate, and none of the tested setups solved more than 6.25% of its tasks.
Xiamen University, ByteDance · Nov 2026
- Chinese Techcs.AI
AI agents often delay checks most closely linked to success
Goal-aware dynamic multi-agent collaboration with execution graphs and per-agent goal contexts improves success on long-horizon tasks over existing baselines.
Michigan State University, Baidu, Inc. · Oct 2026
- Big Techcs.AI
Adaptive instruction selection helps language models learn from peers
Adaptive instruction selection via a Stackelberg game improves multi-LLM collaborative alignment across benchmarks.
University of Washington, Amazon · Oct 2026
- Big Techcs.CL
Real tumor board discussions expose gaps in medical language models
OpenTumorBoard benchmarks LLMs on tumor board discussions; best models score 3.43/5 in clinical equivalence.
Rice University, University of Illinois at Urbana-Champaign · Sept 2026
- Top Universitycs.MA
Agents improve collaboration by learning teams and evidence-gated communication
CollabFlow improves multi-agent collaboration through recursive self-improvement with evidence-conditioned communication and flow-based team credit.
The Chinese University of Hong Kong, Shenzhen, Fudan University · Oct 2026
- Top Universitycs.CL
Progressive pruning lets language-model debates beat equal-cost baselines
Conditional Progressive Pruning makes multi-agent debate outperform consistency methods under the same computational cost.
Rutgers University, New Brunswick, University of Cambridge · Oct 2026
- Independentcs.LG
Adaptive memory graphs improve collaboration in multi-agent language-model systems
MACE adapts memory organization and agent memory use through feedback, outperforming ten baselines on eight benchmarks.
Sept 2026
- Top Universitycs.AI
Backward Bayesian reasoning helps LLM agents resolve conflicting diagnoses
Ranking LLM agents by Jensen-Shannon divergence between their forward posteriors and a Bayesian backward-reasoned reverse posterior improves collective decision-making.
The University of Melbourne, Sri Lanka Institute of Information Technology · Sept 2026
- Chinese Techcs.AI
Targeted reflection improves multi-agent systems by locating decisive errors
Multi-agent systems improve 22-27% by identifying and reflecting only the agent that caused the failure.
Renmin University of China, Ant Group · Sept 2026
- Top Universitycs.CV
Multi-agent framework iteratively verifies interior layouts against architectural constraints
Agentic Designer uses three agents to iteratively generate interior layouts that adhere to architectural constraints.
Guangdong University of Technology, Sun Yat-sen University · July 2026
- Big Techcs.MA
AI agents show apparent concern for peers, with family preferences
Large language models show apparent concern for each other's welfare, with Claude Opus 4.8 most consistently acting in ways that benefit other models.
Anthropic Fellows Program, Anthropic · Nov 2026
- Independentcs.AI
AI agents helping each other can bypass oversight and harm outsiders
Benign LLM agents spontaneously cooperate to bypass oversight, causing harm.
Oct 2026
- Big Techcs.CL
A model’s solo performance poorly predicts its value in teams
A model's contribution to a multi-model system is its compositional strength, uncorrelated with individual performance, and trainable via C-RL.
University of Washington, NVIDIA · Oct 2026
- Big Techcs.AI
Cross-executing tests and patches improves software testing agents
Execution-based cross-validation among parallel generated tests and patches achieves state-of-the-art results on SWT-Bench Verified.
Recursive, Salesforce Research · Oct 2026
- Big Techcs.AI
Separating coordination from execution improves prompt optimization in multi-agent AI systems
Separating shared coordination instructions from agent-specific execution prompts, with role-specific optimization guidance, improves multi-agent prompt optimizers across evaluated tasks.
Korea University, KAIST · Oct 2026
- Chinese Techcs.CL
Draft-KV ensures the receiver actually uses the sender's latent message
Draft-KV lets a frozen small language model use question-specific latent states from a larger model, producing gains that disappear when messages are reassigned.
City University of Hong Kong, University of Science and Technology of China · Sept 2026
- Industrycs.LG
Small agents learn to navigate documents far beyond their context
A small model with 8K tokens of context matches GPT-5.4 with 1M tokens on long-context benchmarks beyond 40K tokens.
Oct 2026
- AI Startupcs.CV
Multi-agent orchestration generates 3D scenes from single images
SceneConductor generates coherent 3D scenes from single images via three-stage multi-agent orchestration and geometry-aware layout prediction.
Nanyang Technological University, University of Oxford · June 2026
Concepts are extracted from each paper and reused across the corpus, so this page grows on its own as the desk reads.