Hugging Face Trending Papers August 5, 2026

Computationally Efficient Collaborative Communication Via Regularity-Based Coarsening

Read the original on Hugging Face Trending Papers →

Our results show that the existence of a short high-utility protocol already suffices for efficient communication. In particular, in a game with $n$ possible observations and $m$ actions: (1) For any achievable target utility $α$, we give an algorithm with $\mathrm{poly}(n, m, 1/ε)$ runtime that designs a protocol achieving utility at least $α-ε$ using only $2^{\mathcal O(CC_α(G))}/ε^2$ bits of communication.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

agents

arXiv Machine Learning

Aug 7

Computationally Efficient Collaborative Communication Via Regularity-Based Coarsening

arXiv:2608. 05327v1 Announce Type: cross Abstract: Our results show that the existence of a short high-utility protocol already suffices for efficient communication.

By Mark Bedaywi, Scott Emmons, Nika Haghtalab, Stuart Russell

agents

arXiv AI

Aug 11

Dynamic Coalition Formation and Communication Pricing in Skill-Based Agentic AI Systems

arXiv:2608. 07532v1 Announce Type: new Abstract: Modern agentic AI systems combine multiple large language model agents with heterogeneous skills, yet most architectures either fix communication in advance or allow full broadcast.

By Mojtaba Eslami

llms agents efficiency benchmarks

arXiv Machine Learning

Jul 17

PAC Learning in Turn-Based Stochastic Games with Reachability Objectives: A Decentralized Private Approach via Expected Conditional Distance

arXiv:2607. 14877v1 Announce Type: new Abstract: Reachability is the most fundamental logical objective, yet it is notoriously difficult to learn in reinforcement learning settings: even for Markov decision processes, PAC learning of reachability is impossible without additional assumptions.

By Ali Asadi, Krishnendu Chatterjee, Pavol Kebis

reinforcement-learning safety

arXiv Machine Learning

5d ago

Decentralized Multi-Player Q-Learning in Episodic Markov Decision Processes with Information Asymmetry

arXiv:2608. 12753v1 Announce Type: new Abstract: We study decentralized multi-player reinforcement learning in episodic tabular Markov decision processes (MDPs) under three forms of information asymmetry: (A) unobserved actions with common rewards, (B) observed actions with independent rewards, and (C) unobserved actions with independent rewards.

By Larissa Xu, King Bi, William Chang

agents reinforcement-learning benchmarks

arXiv Machine Learning

Jun 5

Multi-Agent Lipschitz Bandits

arXiv:2602. 16965v2 Announce Type: replace Abstract: We study the decentralized multi-player stochastic bandit problem over a continuous, Lipschitz-structured action space where hard collisions yield zero reward.

By Sourav Chakraborty, Amit Kiran Rege, Claire Monteleoni, Lijun Chen

agents reinforcement-learning

arXiv Machine Learning

Aug 4

Tail-Aware Information-Theoretic Bounds for LLM Alignment under Heavy-Tailed Rewards

arXiv:2604. 10727v2 Announce Type: replace-cross Abstract: Classical information-theoretic learning bounds typically rely on KL mutual information and moment-generating-function (MGF) arguments, which are well matched to bounded or sub-Gaussian losses but can be ineffective when losses or rewards are heavy-tailed.

By Huiming Zhang, Binghan Li, Wan Tian, Qiang Sun

llms reinforcement-learning safety

Related stories

Computationally Efficient Collaborative Communication Via Regularity-Based Coarsening

Dynamic Coalition Formation and Communication Pricing in Skill-Based Agentic AI Systems

PAC Learning in Turn-Based Stochastic Games with Reachability Objectives: A Decentralized Private Approach via Expected Conditional Distance

Decentralized Multi-Player Q-Learning in Episodic Markov Decision Processes with Information Asymmetry

Multi-Agent Lipschitz Bandits

Tail-Aware Information-Theoretic Bounds for LLM Alignment under Heavy-Tailed Rewards