Related papers: Undetectable Conversations Between AI Agents via P…
Communicating in natural language is a powerful tool in multi-agent settings, as it enables independent agents to share information in partially observable settings and allows zero-shot coordination with humans. However, most prior works…
In this paper, we extended the method proposed in [21] to enable humans to interact naturally with autonomous agents through vocal and textual conversations. Our extended method exploits the inherent capabilities of pre-trained large…
We present Portable Agent Memory, an open protocol and reference implementation for transferring persistent memory state across heterogeneous AI agents. Modern AI agents accumulate rich context -- episodic events,semantic knowledge,…
Humans are remarkably adept at collaboration, able to infer the strengths and weaknesses of new partners in order to work successfully towards shared goals. To build AI systems with this capability, we must first understand its building…
Effective collaboration between embodied agents requires more than acting in a shared environment; it demands communication grounded in each agent's evolving understanding of the world. When agents can only partially observe their…
Real-world requests to AI agents are fundamentally underspecified. Natural human communication relies on shared context and unstated constraints that speakers expect listeners to infer. Current agentic benchmarks test explicit…
Multi-party dialogue machine reading comprehension (MRC) brings tremendous challenge since it involves multiple speakers at one dialogue, resulting in intricate speaker information flows and noisy dialogue contexts. To alleviate such…
Inclusion is important for meeting effectiveness, which is in turn central to organizational functioning. One way of improving inclusion in meetings is through feedback, but social dynamics make giving feedback difficult. We propose that AI…
The current increasing need for privacy-preserving voice communications is leading to new ideas for securing voice transmission. This paper refers to a relatively new concept of sending encrypted speech as pseudo-speech in the audio domain…
We consider distributed computations between two parties carried out over a noisy channel that may erase messages. Following a noise model proposed by Dani et al. (2018), the noise level observed by the parties during the computation in our…
In the artificial intelligence space, as we transition from isolated large language models to autonomous agents capable of complex reasoning and tool use. While foundational architectures and local context management protocols have been…
We develop model free PAC performance guarantees for multiple concurrent MDPs, extending recent works where a single learner interacts with multiple non-interacting agents in a noise free environment. Our framework allows noisy and resource…
AI Agents can perform complex operations at great speed, but just like all the humans we have ever hired, their intelligence remains fallible. Miscommunications aren't noticed, systemic biases have no counter-action, and inner monologues…
We consider a coded cooperative data exchange problem with the goal of generating a secret key. Specifically, we investigate the number of public transmissions required for a set of clients to agree on a secret key with probability one,…
We investigate the problem of covert and secret key generation over a state-dependent discrete memoryless channel with one-way public discussion in which an adversary, the warden, may arbitrarily choose the channel state. We develop an…
The growing prevalence of Large Language Models (LLMs) is reshaping online text-based communication; a transformation that is extensively studied as AI-mediated communication. However, much of the existing research remains bound by…
We explore the potential for productive team-based collaboration between humans and Artificial Intelligence (AI) by presenting and conducting initial tests with a general framework that enables multiple human and AI agents to work together…
Natural Language Processing (NLP) for low-resource languages remains fundamentally constrained by the lack of textual corpora, standardized orthographies, and scalable annotation pipelines. While recent advances in large language models…
The impressive capabilities of Large Language Models (LLMs) raise the possibility that synthetic agents can serve as substitutes for real participants in human-subject research. To evaluate this claim, prior research has largely focused on…
This work addresses private communication with distributed systems in mind. We consider how to best use secret key resources and communication to transmit signals across a system so that an eavesdropper is least capable to act on the…