We present a hybrid multi-robot coordination framework that combines decentralized path planning with centralized conflict resolution. In our approach, each robot autonomously plans its path and shares this information with a centralized node. The centralized system detects potential conflicts and allows only one of the conflicting robots to proceed at a time, instructing others to stop outside the conflicting area to avoid deadlocks. Unlike traditional centralized planning methods, our system does not dictate robot paths but instead provides stop commands, functioning as a virtual traffic light. In simulation experiments with multiple robots, our approach increased the success rate of robots reaching their goals while reducing deadlocks. Furthermore, we successfully validated the system in real-world experiments with two quadruped robots and separately with wheeled Duckiebots.

Human language is one of the most expressive tools for conveying intent, yet most artificial or biological systems lack mechanisms to interpret or respond meaningfully to it. Bridging this gap could enable more natural forms of control over complex, decentralized systems. In AI and artificial life, recent work explores how language can specify high-level goals, but most systems still depend on engineered rewards, task-specific supervision, or rigid command sets, limiting generalization to novel instructions. Similar constraints apply in synthetic biology and bioengineering, where the locus of control is often genomic rather than environmental perturbation. A key open question is whether artificial or biological collectives can be guided by free-form natural language alone, without task-specific tuning or carefully designed evaluation metrics. We provide one possible answer here by showing, for the first time, that simple agents' collective behavior can be guided by free-form language prompts: one AI model transforms an imperative prompt into an intervention that is applied to simulated cells; a second AI model scores how well the prompt describes the resulting cellular dynamics; and the former AI model is evolved to improve the scores generated by the latter. Unlike previous work, our method does not require engineered fitness functions or domain-specific prompt design. We show that the evolved system generalizes to unseen prompts without retraining. By treating natural language as a control layer, the system suggests a future in which spoken or written prompts could direct computational, robotic, or biological systems to desired behaviors. This work provides a concrete step toward this vision of AI-biology partnerships, in which language replaces mathematical objective functions, fixed rules, and domain-specific programming.

To mitigate these costs and address challenges related to scalability and data security, there is a growing shift towards decentralized systems for deploying such models. In these decentralized environments, efficient inference acceleration becomes crucial to manage computational resources effectively and enhance system responsiveness. In this work, we address the challenge of selecting optimal acceleration methods in decentralized systems by introducing a meta-learning-based framework. This framework automates the selection process by learning from historical performance data of various acceleration techniques across different tasks. Unlike traditional methods that rely on random selection or expert intuition, our approach systematically identifies the best acceleration strategies based on the specific characteristics of each task. We demonstrate that our meta-learning framework not only streamlines the decision-making process but also consistently outperforms conventional methods in terms of efficiency and performance. Our results highlight the potential of meta-learning to revolutionize inference acceleration in decentralized AI systems, offering a path towards more democratic and economically feasible artificial intelligence solutions. The advancement of large-scale models such as large language models (LLMs) and sophisticated image generation systems has dramatically increased computational demands, necessitating significant innovation in deployment architectures (Brown et al., 2020; Ramesh et al., 2022). Traditional centralized systems, while powerful, encounter critical limitations in terms of scalability, data security, and operational costs (Li et al., 2022).

A flurry of recent work has demonstrated that pre-trained large language models (LLMs) can be effective task planners for a variety of single-robot tasks. The planning performance of LLMs is significantly improved via prompting techniques, such as in-context learning or re-prompting with state feedback, placing new importance on the token budget for the context window. An under-explored but natural next direction is to investigate LLMs as multi-robot task planners. However, long-horizon, heterogeneous multi-robot planning introduces new challenges of coordination while also pushing up against the limits of context window length. It is therefore critical to find token-efficient LLM planning frameworks that are also able to reason about the complexities of multi-robot coordination. In this work, we compare the task success rate and token efficiency of four multi-agent communication frameworks (centralized, decentralized, and two hybrid) as applied to four coordination-dependent multi-agent 2D task scenarios for increasing numbers of agents. We find that a hybrid framework achieves better task success rates across all four tasks and scales better to more agents. We further demonstrate the hybrid frameworks in 3D simulations where the vision-to-text problem and dynamical errors are considered. See our project website https://yongchao98.github.io/MIT-REALM-Multi-Robot/ for prompts, videos, and code.

We consider the setting where a team of robots is tasked with tracking multiple targets with the following property: approaching the targets enables more accurate target position estimation, but also increases the risk of sensor failures. Therefore, it is essential to address the trade-off between tracking quality maximization and risk minimization. In the previous work [1], a centralized controller is developed to plan motions for all the robots - however, this is not a scalable approach. Here, we present a decentralized and risk-aware multi-target tracking framework, in which each robot plans its motion trading off tracking accuracy maximization and aversion to risk, while only relying on its own information and information exchanged with its neighbors. We use the control barrier function to guarantee network connectivity throughout the tracking process. Extensive numerical experiments demonstrate that our system can achieve similar tracking accuracy and risk-awareness to its centralized counterpart.

One of the boons of cryptocurrency is meant to be that no particular company, central bank or government has control. That might not be true. Researchers for a report commissioned by the Defense Advanced Research Projects Agency (DARPA) found there can be "unintended centralities" in these supposed decentralized systems. Cryptocurrency power is concentrated among people or organizations with a large chunk of the pie. "Unintended centralities" was the term used, defined as circumstances where an entity has sway over a so-called decentralized system.

Eric: Hello, good afternoon Matrixians, and greetings to our CEO Owen, it's good to see you again. Owen: Hi Eric, good to see you. Eric: How time flies, it's another month, so I just can recall the last time we had the AMA shooting, so it's another month again. So I'm sure that you have some exciting progress, and we will keep updating the Matrixians through the year bi-weekly reports and also the AMAs, and also through our education-based articles to enable all to know the rationales of our project and to answer, to understand the progress of our projects. And today I got something to share with the Matrixians.

The Navy is progressively phasing artificial intelligence (AI) into its ship systems, weapons, networks, and command and control infrastructure as computer automation becomes more reliable and advanced algorithms make once-impossible discernments and analyses. Previously segmented data streams on ships, drones, aircraft, and even submarines are now increasingly able to share organized data in real-time, in large measure due to breakthrough advances in AI and machine learning. AI can, for instance, enable command and control systems to identify moments of operational relevance from among hours or days or surveillance data in milliseconds, something which saves time, maximizes efficiency, and performs time-consuming procedural tasks autonomously at an exponentially faster speed. "Multiple data bytes of information will be passed around on the networks here in the near future. So as we think about big data, and how do we handle all that data and turn it into information without getting overloaded, this will be a key part of AI, then we're talking about handling decentralized systems," Nathan Husted of the Naval Surface Warfare Center, Carderock told an audience at the 2022 Sea Air Space Symposium.

Incentive mechanisms play a pivotal role in collecting correct and reliable information from self-interested agents. Peer-prediction mechanisms are game-theoretic mechanisms that incentivize agents for reporting the information truthfully, even when the information is unverifiable in nature. Traditionally, a trusted third party implements these mechanisms. We built Infochain, a decentralized system for information elicitation. Infochain ensures transparent, trustless and cost-efficient collection of information from self-interested agents without compromising the game-theoretical guarantees of the peer-prediction mechanisms. In this paper, we address various non-trivial challenges in implementing these mechanisms in Ethereum and provide experimental analysis.

Classification-as-a-Service (CaaS) is widely deployed today in machine intelligence stacks for a vastly diverse set of applications including anything from medical prognosis to computer vision tasks to natural language processing to identity fraud detection. The computing power required for training complex models on large datasets to perform inference to solve these problems can be very resource-intensive. A CaaS provider may cheat a customer by fraudulently bypassing expensive training procedures in favor of weaker, less computationally-intensive algorithms which yield results of reduced quality. Given a classification service supplier $S$, intermediary CaaS provider $P$ claiming to use $S$ as a classification backend, and customer $C$, our work addresses the following questions: (i) how can $P$'s claim to be using $S$ be verified by $C$? (ii) how might $S$ make performance guarantees that may be verified by $C$? and (iii) how might one design a decentralized system that incentivizes service proofing and accountability? To this end, we propose a variety of methods for $C$ to evaluate the service claims made by $P$ using probabilistic performance metrics, instance seeding, and steganography. We also propose a method of measuring the robustness of a model using a blackbox adversarial procedure, which may then be used as a benchmark or comparison to a claim made by $S$. Finally, we propose the design of a smart contract-based decentralized system that incentivizes service accountability to serve as a trusted Quality of Service (QoS) auditor.