arXiv Machine Learning
Emergence, Not Bandwidth: Physical Coupling and the Limits of Learned Multi-Agent Communication
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
Sep 23
Minimal Recurrent Behavioral Memory for Imitation under Partial Observability
arXiv:2609.25757v1 Announce Type: new Abstract: What is the least recurrent memory needed to reproduce a specified expert under partial observability? The instantaneous requirement is the conditional...
arXiv AI
Aug 6
Interoceptive Attention as Dynamic Homeostatic Prioritization in a Foraging Agent
arXiv:2608. 04232v1 Announce Type: new Abstract: Biological systems must regulate competing needs under limited perceptual bandwidth, where sharpening one estimate costs the capacity to sharpen the others.
arXiv Machine Learning
Aug 4
Training Small LLMs as Spatial Multi-Agent Policies
arXiv:2608. 01425v1 Announce Type: cross Abstract: Training LLM-based multi-agent systems with multi-agent reinforcement learning is rapidly gaining traction, and a parallel line of work argues that such systems should be judged by their behavior, not only their reward.
arXiv AI
Aug 18
UC-PSRO: Utility-Conditioned Policy-Space Response Oracles with a Communication-Dropout Curriculum for Game-Theoretic Course-of-Action Generation in Adversarial Swarms
arXiv:2608. 15372v1 Announce Type: new Abstract: We study generating game-theoretically optimized Courses of Action (COAs) for a Blue UAS swarm against an adaptive Red adversary in a communication-degraded environment, motivated by (but not derived from) a public U.
arXiv AI
Sep 2
Explore More, Drift Less: Outcome-Only Reinforcement Learning Can Suffice for Long-Horizon Interactive Agents
The paper proposes CANOPY, a minimalist reinforcement learning protocol that addresses two common pitfalls—signal starvation and policy drift—in outcome‑only RL for long‑horizon interactive tasks. By scaling same‑task exploration, keeping updates on‑policy, and anchoring updates with KL divergence, CANOPY enables a Qwen3‑14B agent to achieve top leaderboard results on the AppWorld coding benchmark without auxiliary supervision or elaborate scaffolding. The approach also improves performance on SWE‑bench for a Qwen3.5‑9B model.
arXiv Machine Learning
Jul 21
PRIME: Plasticity Recovery in Multi-Agent Environments for UAV-Assisted Emergency Communication Networks
arXiv:2607. 17922v1 Announce Type: cross Abstract: Most reinforcement learning controllers for these networks assume stationary conditions, and the few that handle change react to the external environment while leaving the network's internal state unexamined.