Related papers: CBCL: Safe Self-Extending Agent Communication

Categorical Message Passing Language (CaMPL) is a functional-style concurrent programming language whose semantics is in category theory, more specifically, linear actegories. Its core programming feature is message passing along typed…

Vision-language models (VLMs) have tremendous potential for grounding language, and thus enabling language-conditioned agents (LCAs) to perform diverse tasks specified with text. This has motivated the study of LCAs based on reinforcement…

Reasoning is a fundamental cognitive process underlying inference, problem-solving, and decision-making. While large language models (LLMs) demonstrate strong reasoning capabilities in closed-world settings, they struggle in open-ended and…

AutoGen is an open-source framework that allows developers to build LLM applications via multiple agents that can converse with each other to accomplish tasks. AutoGen agents are customizable, conversable, and can operate in various modes…

Large language models (LLMs) open new possibilities for agentic control in Open RAN, allowing operators to express intents in natural language while delegating low-level execution to autonomous agents. We present A1gent, an agentic RAN…

LLM context is not just tokens; it is a set of commitments. Long-running conversations accumulate goals, constraints, decisions, preferences, tool results, retrieved evidence, artifacts, and safety boundaries that future responses must…

Large language models (LLMs) are evolving into autonomous decision-makers, raising concerns about catastrophic risks in high-stakes scenarios, particularly in Chemical, Biological, Radiological and Nuclear (CBRN) domains. Based on the…

Context. Risk analysis assesses potential risks in specific scenarios. Risk analysis principles are context-less; the same methodology can be applied to a risk connected to health and information technology security. Risk analysis requires…

Large Language Models (LLMs) have emerged as powerful tools for accelerating scientific discovery, yet their static knowledge and hallucination issues hinder autonomous research applications. Recent advances integrate LLMs into agentic…

Communication in multi-agent reinforcement learning (MARL) has been proven to effectively promote cooperation among agents recently. Since communication in real-world scenarios is vulnerable to noises and adversarial attacks, it is crucial…

As a key form in online social platforms, group chat is a popular space for interest exchange or problem-solving, but its effectiveness is often hindered by inactivity and management challenges. While recent large language models (LLMs)…

Agent Skill framework, now widely and officially supported by major players such as GitHub Copilot, LangChain, and OpenAI, performs especially well with proprietary models by improving context engineering, reducing hallucinations, and…

Motivated by the need for accelerating text entry in augmentative and alternative communication (AAC) for people with severe motor impairments, we propose a paradigm in which phrases are abbreviated aggressively as primarily word-initial…

LLM-based agents are deployed in safety-critical applications, yet current guardrail systems fail to prevent violations of temporal safety policies, requirements that govern the ordering and sequencing of agent actions. For instance, agents…

Language models are exhibiting increasing capability in knowledge utilization and reasoning. However, when applied as agents in embodied environments, they often suffer from misalignment between their intrinsic knowledge and environmental…

Large Language Models (LLMs) have become a popular interface for human-AI interaction, supporting information seeking and task assistance through natural, multi-turn dialogue. To respond to users within multi-turn dialogues, the…

Real-world robotic tasks often require agents to achieve sequences of goals while respecting time-varying safety constraints. However, standard Reinforcement Learning (RL) paradigms are fundamentally limited in these settings. A natural…

Adapting Automatic Speech Recognition (ASR) models to new domains results in a deterioration of performance on the original domain(s), a phenomenon called Catastrophic Forgetting (CF). Even monolingual ASR models cannot be extended to new…

OpenClaw-like agents offer substantial productivity benefits, yet they are insecure by default because they combine untrusted inputs, autonomous action, extensibility, and privileged system access within a single execution loop. We use…

Building scalable and reusable multi-agent decision policies from offline datasets remains a challenge in offline multi-agent reinforcement learning (MARL), as existing methods often rely on fixed observation formats and action spaces that…