Discovering Adaptive Transmission Programs for Collective Innovation

Cédric Colas; Jérémy Perez; Eleni Nisioti; Akhilesh Mocherla; Pierre-Yves Oudeyer; Clément Moulin-Frier; Maxime Derex

cs.AIAug 25, 2026

Discovering Adaptive Transmission Programs for Collective Innovation

Authors: Cédric Colas, Jérémy Perez, Eleni Nisioti, Akhilesh Mocherla, Pierre-Yves Oudeyer, Clément Moulin-Frier, Maxime Derex

Organizations: Flowers AI & CogSci Lab, Inria, France · IT University of Copenhagen, Denmark · Independent Researcher, UK · Institute for Advanced Study in Toulouse, France

Abstract

Human collective intelligence depends on transmission processes: who shares what with whom, how, and when. While these processes emerge from individual cognition, they can also be directed by deliberate top-down protocols. Prior work has studied how transmission shapes collective outcomes primarily through the lens of network structure, varying who shares with whom and when. But networks are state-agnostic: they cannot condition transmission on what agents know or on the state of the collective. Here, we formalize transmission protocols as state-aware programs that route information and resources based on agent and collective states, and we use LLM-guided evolutionary search to design effective protocols in a collective discovery task. Evolved protocols increase collective performance over standard baselines from the literature by up to 37%. Ablations confirm that state-awareness drives this advantage: removing content-dependence while preserving network topology and timing eliminates performance gains. We find that evolved protocols also transfer across domain variations and agent populations. These results demonstrate that effective and generalizable transmission protocols can be discovered in silico, suggesting a path toward AI-assisted design of coordination infrastructure that enhances human collective intelligence.

Figures & tables

Figure 1: Discovering adaptive transmission protocols in silico . (a) State-aware transmission protocols (TPs) route information and resources between agents based on agent and collective states. (b) We search for effective TPs with an evolutionary algorithm that leverages large language models (LLMs) to generate and refine candidate protocols expressed as stateful programs. (c) Best evolved protocols increase collective performance in simulation by 37% over baselines (mean

\pm

sem, N=5, p<0.001).

Panel of Figure 2 — Figure 2: LLM-guided search uncovers high-performing transmission protocols . (a) Collective performance of best protocols (one per evolutionary run) and baselines across game steps (mean $\pm$ sem over 30 simulations). (b) Comparison of performance measures at 150 game steps. Stars indicate significance of one-sided t-tests (all $p<0.001$ ).

Figure 3: State-awareness ablation . Collective performance (mean

\pm

sem) for top-20 and bottom-20 protocols per evolutionary run (100 in each set), under original (full) and ablated (random content) conditions. Ablation eliminates the performance advantage of top protocols, reducing them to baseline levels, while bottom protocols are unaffected.

Figure 4: Generalization across population and domain configurations . Evolved protocols (blue) outperform baseline protocols (gray) across all population configurations and domain variants. Mean

\pm

sem, N=5, p<0.01 (), p<0.001 (*).

Appendix figures & tables6 assets

Supplementary material from the paper’s appendix.

Appendix

Group	Feature	Definition
Content	Recency bias	Discovery step of shared recipe / transmission step. Higher values indicate sharing recent discoveries.
	Rarity bias	Among successful recipes, $1-(\text{fraction of agents who own }r)$ . Higher values indicate sharing rarer items.
	Item novelty	Among successful recipes, fraction where $r$ is not in the learner’s inventory.
	Actionable has- $k$	Fraction of transmissions where the learner owns exactly $k$ ingredients AND the result item is novel to the learner. Combines routing with content novelty.
	Success bias	Whether the shared recipe is successful ( $r\neq\text{null}$ ) minus the teacher’s base success rate at that step.
Routing	Has- $k$ fraction	Fraction of transmissions where the learner owns exactly $k$ ingredients of the shared recipe.

Appendix

Table 1: Behavioral features computed from transmission logs. Each feature is averaged across all transmissions (or per-step aggregations) and then across evaluation seeds. Notation: recipe

=(i_{1},i_{2},r)

where

i_{1},i_{2}

are ingredients and

r

is the result (

r=\text{null}

for failures). Features indexed by

k\in\{0,1,2\}

are computed separately for each value.

Figure 5: Fitness of best evolved protocol as a function of search step .

Figure 6: LLM-guided search uncovers high-performing protocols for populations of 10 empowerment agents . Fitness of best protocols (one per search run) and extended set of baselines across 300 game steps (mean

\pm

sem over 30 simulations).

Figure 7: Program search discovers transmission protocols that diverge from the generative prior . (left) t-SNE projections of discovered protocols, with per-run best-performing protocols marked with stars. (right) Maximum mean discrepancy (MMD) measuring distributional divergence across search runs; evolved protocols are more distant from generated protocols than from each other.

Figure 8: Transmission protocol effectiveness is not correlated with transmission volume . The quantity of information transmitted is measured as the number of memories received by an agent that had not experienced this memory on its own at the time of reception.

Group	Feature	$\boldsymbol{\rho}$
Content	Recency bias	$+0.64$
Routing	Cond. recency has-2	$+0.63$
Routing	Cond. recency has-1	$+0.58$
Routing	Targeted failure rate	$-0.54$
Content	Actionable has-0	$+0.49$
Routing	Cond. recency has-0	$+0.48$

Appendix

Table 2: Ablation analysis results across

{\sim}1{,}000

independently generated protocols. For each feature, we compute the per-protocol difference between original and content-randomized (ablated) values, and correlate this difference with fitness (Spearman

\rho

\boldsymbol{n}

indicates the number of protocols for which the feature was defined. Significance after Benjamini–Hochberg FDR correction: **

p<0.01

, ***

p<0.001

. Features sorted by

|\rho|

Multi-Agent Communication

Multi-agent communication studies how autonomous agents exchange information to coordinate decisions, share knowledge, and act together under constraints.

See all 380 papers

Collaborative Principle Evolution via Evidence Transfer for Scientific Discovery
Sep 28, 2026Yingming Pu, Hongyu Chen, Tao LinMulti-Agent Collaboration Multi-Agent Systems
Zhejiang University, Hangzhou, Zhejiang, China · Westlake University, Hangzhou, Zhejiang, China
When Agents Coordinate: Measuring Coordination in Multi-Agent AI Coding
Aug 17, 2026Giuseppe Destefanis, Tomaso AsteMulti-Agent Coordination Multi-Agent Coding
Department of Computer Science, University College London, UK
Artificial collectives of specialists and generalists excel at different tasks
Jun 18, 2026John Meluso, Laurent Hébert-Dufresne, Christoph Riedl +1Multi-Agent Coordination Multi-Agent Collaboration
Cornell University · University of Vermont · Santa Fe Institute +1

Sep 28, 2026J/K move · Enter open · S save

Collaborative Principle Evolution via Evidence Transfer for Scientific Discovery

Yingming Pu, Hongyu Chen, Tao Lin

Zhejiang University, Hangzhou, Zhejiang, China · Westlake University, Hangzhou, Zhejiang, China

Multi-Agent Collaboration Multi-Agent Systems Large Language Model-Guided Scientific Discovery Autonomous Research Agents

Open paper AskPDF arXiv

Large Language Model (LLM)-based agents promise to automate scientific discovery, yet exploring the vast hypothesis space remains costly. Existing principle-evolution methods accelerate this loop, but operate sequentially, which caps exploration breadth and wastes wall-clock time on challenging problems. To address this, we formulate collaborative scientific discovery as evidence transfer between parallel principle-evolution branches. We present COEVOLVE, which realizes this transfer through a coordination core over parallel branches. By integrating value-of-information-gated routing and context-discounted likelihood injection, COEVOLVE enables branches to collaborate through shared measurements while keeping their principle posteriors separate. Across six scientific-discovery tasks under a matched evaluation budget, COEVOLVE attains a mean solution quality of 66.5% versus 57.0% for single-branch principle evolution, with a 1.80x mean wall-clock speedup on the GPT-5.6-Terra backbone; on five auto-research tasks delegated to an autonomous research harness, it is the only arm whose mean stays above the published SOTA anchor on every task. These results establish when evidence sharing accelerates parallel discovery and when transfer safeguards are necessary to limit negative or inert transfers

Abstract

Multi-Agent Communication

Explore similar work

Collaborative Principle Evolution via Evidence Transfer for Scientific Discovery

When Agents Coordinate: Measuring Coordination in Multi-Agent AI Coding

Artificial collectives of specialists and generalists excel at different tasks