cs.LGNov 2, 2026

The Tower of Babel in artificial intelligence: who should speak, and when it pays to listen

Authors: Mohammad Salahshour

Organizations: Department of Collective Behaviour, Max Planck Institute of Animal Behavior, Konstanz, Germany · Centre for the Advanced Study of Collective Behaviour, University of Konstanz, Konstanz, Germany · Department of Biology, University of Konstanz, Konstanz, Germany

Abstract

Two machines can each recognize an object well and still fail together. We study classifiers that see different parts of one object and send short messages to a receiver that identifies its class. Coordination asks how to design messages together; cooperation asks whether the team outperforms one sender given the whole budget. On three digit datasets, messages designed together beat messages designed apart by 18.07 to 22.68 percentage points on average with two-bit messages, with gains in all 24 configurations. A fixed agreement, you report the row and I the column, recovers about half this gain, with only the receiver learned. Senders that draw the same distinctions waste a narrow vocabulary, and senders whose distinctions cross multiply it. A team has no more possible messages than one sender with the same budget, so a partner must bring evidence the first lacks. A solvable model shows individual statistics alone cannot determine whether a partnership helps. On MNIST digits, six shared bits remove 49.54 percent of the strongest tested solo's errors on average. Paired measurements correctly predicted most sensor teams would reduce average accuracy on new participants. Who should speak is a property of the pair, and must be measured in pairs.

Figures & tables

Explore similar work

May 9, 2026

When Can Human-AI Teams Outperform Individuals? Tight Bounds with Impossibility Guarantees

Human-AI teams fail to outperform their best member in 70% of studies, yet no theory specifies when complementarity is achievable. We derive tight bounds for the broad class of confidence-based aggregation rules by integrating signal detection theory with information-theoretic analysis, yielding four results: (1) a complementarity theorem (teams outperform individuals iff error correlation ρHM<ρ∗ρ_{HM} < ρ^*, with ρ∗≈aρ^* \approx a in the symmetric near-chance regime); (2) minimax bounds showing gains scale as Θ(Δd)Θ(\sqrt{Δd}) with metacognitive sensitivity difference; (3) an impossibility result proving no confidence-based aggregation rule achieves complementarity when ρHM≥ρ∗ρ_{HM} \geq ρ^*; and (4) multi-class generalization ρK∗≈ρ∗/K−1ρ^*_K \approx ρ^*/\sqrt{K-1}. Predictions match observed team accuracy (R=0.94R = 0.94 on ImageNet-16H, R=0.91R = 0.91 on CIFAR-10H) and the multi-class threshold scaling holds on human data (R=0.93R = 0.93, K=16K = 16), with robustness under non-Gaussian distributions. The framework explains why complementarity is rare and provides actionable design formulas; results apply to aggregation, not to interactive deliberation that generates novel answers.
Oct 27, 2026

TeamGym: A Gym for Team Decision-Making by AI Agents with Distributed Information

Many real-world decisions require teams to integrate information distributed across participants. Yet AI agents are still primarily trained and benchmarked in isolation. We introduce TeamGym, an environment for evaluating and training language model-based agents on team decision-making problems constructed from real-world legal, finance, medical, and software engineering corpora. TeamGym introduces a method to identify a minimal set of facts, each element of which is necessary and all of which are collectively sufficient for a correct final decision, which we call pivotal information. This enables TeamGym to both control the distribution of pivotal information and track how well agents identify and integrate pivotal information when making team decisions. Examining 8 language models on 12 source corpora, we find that current AI agents often fail to effectively share information: Distributing pivotal information across participants lowers success rate by 22.9 percentage points on average relative to giving the same information to a single model (a communication gap). We also document that participants do not effectively retrieve decision-relevant information on their own: A team's success rate is lowered by a further 19.9 points when participants must identify and extract pivotal information from source material rather than receiving it directly (a retrieval gap). To help remedy these deficits, we use TeamGym to train policies through reinforcement learning on team decision loss. Across two policy-training experiments, we find that training improves final-decision quality and induces emergent coordination in participation, speaker selection, and communication, even though the reward evaluates only the final decision.
Sep 17, 2026

Scaling Discovery through Test-Time Communication

Science advances not in isolation but through collaboration, yet existing agentic systems capture little of this. Whether communicating agents help remains an open question with mixed prior results. We show that test-time communication can substantially outperform independent parallel attempts on challenging tasks, where sharing a breakthrough can push the whole group forward. We first study the effect of scaling multi-agent test-time communication, where agents have no predefined roles and communicate via a shared directory, on ARC-AGI-3, a benchmark requiring novel problem solving. We find that a team of kk communicating agents, team@kk, matches the success rate of 4k4k independent agents, and this advantage grows with kk, suggesting gains compound with scale. The effect is not merely efficiency: a task that no single agent can solve, a team of agents can solve reliably. Furthermore, these gains transfer to research-oriented tasks, given sufficient compute. On polyomino packing, communicating agents outperform best@kk and exceed the prior best-known score. On MNIST classifier compression, communication surpasses the best-known human solution. A team of four agents produced a 1,957-byte classifier submission achieving 99.4% test accuracy, smaller than both the best-known human solution and the best single-agent result. These gains are not unconditional. Independent agents may outperform communication when compute is limited or when a clear measure of progress is absent. However, under sufficient compute and clear feedback, multi-agent communication consistently yields stronger results.