Related papers: Herding CATs: ALARA for Agent Harness Engineering …
As AI agents transition from research prototypes to enterprise production systems, the tool interfaces they consume remain rooted in human-oriented CRUD paradigms. This paper identifies five fundamental architectural mismatches between…
In this paper, we introduce a high-level controller synthesis framework that enables teams of heterogeneous agents to assist each other in resolving environmental conflicts that appear at runtime. This conflict resolution method is built…
Agentic AI represents a paradigm shift in enhancing the capabilities of generative AI models. While these systems demonstrate immense potential and power, current evaluation techniques primarily focus on assessing their efficacy in…
Single-agent systems (SAS) have become the default pattern for LLM-driven scientific workflows, but routing planning, tool use, and synthesis through a single context window comes with a well-known cost: as tool specifications and…
Harnesses are now central to coding-agent performance, mediating how models interact with tools and execution environments. Yet harness engineering remains a manual craft, because automating it faces a heterogeneous action space across…
On-device AI agents offer the potential for personalized, low-latency assistance, but their deployment is fundamentally constrained by limited memory capacity, which restricts usable context. This reduced practical context window creates a…
Learning interpretable communication is essential for multi-agent and human-agent teams (HATs). In multi-agent reinforcement learning for partially-observable environments, agents may convey information to others via learned communication,…
The consensus strategies used in collaborative multi-agent systems (MAS) face notable challenges related to adaptability, scalability, and convergence certainties. These approaches, including structured workflows, debate models, and…
In this paper, we present a novel framework for enhancing the capabilities of large language models (LLMs) by leveraging the power of multi-agent systems. Our framework introduces a collaborative environment where multiple intelligent agent…
The performance of large language model (LLM) agents depends critically on the execution harness, the system layer that orchestrates tool use, context management, and state persistence. Yet this same architectural centrality makes the…
Artificial Intelligence (AI) has transformed robotics, healthcare, industry, and scientific discovery, yet a major frontier may lie beyond Earth. Space exploration and settlement offer vast environments and resources, but impose constraints…
AI-based systems, currently driven largely by LLMs and tool-using agentic harnesses, are increasingly discussed as a possible threat to software engineering. Foundation models get stronger, agents can plan and act across multiple steps, and…
Autonomous agents driven by Large Language Models (LLMs) offer enormous potential for automation. Early proof of this technology can be found in various demonstrations of agents solving complex tasks, interacting with external systems to…
Specialized visual tools can augment large language models or vision language models with expert knowledge (e.g., grounding, spatial reasoning, medical knowledge, etc.), but knowing which tools to call (and when to call them) can be…
Enabling large language models to scale and reliably use hundreds of tools is critical for real-world applications, yet challenging due to the inefficiency and error accumulation inherent in flat tool-calling architectures. To address this,…
Multi-agent applications often execute complex tasks as multi-stage workflows, where each stage is an LLM call whose output becomes part of context for subsequent steps. Existing LLM serving systems largely assume homogeneous clusters with…
Deploying agentic AI in regulated contexts requires principled reasoning about two design dimensions: agency (what the system can do) and autonomy (how much it acts without human involvement). Though often treated independently, they are…
Recent advanced LLM-powered agent systems have exhibited their remarkable capabilities in tackling complex, long-horizon tasks. Nevertheless, they still suffer from inherent limitations in resource efficiency, context management, and…
Affordance grounding requires identifying where and how an agent should interact in open-world scenes, where actionable regions are often small, occluded, reflective, and visually ambiguous. Recent systems therefore combine multiple skills…
Despite recent advances, autonomous agents often struggle to solve complex tasks in enterprise domains that require coordinating multiple tools and processing diverse data sources. This struggle is driven by two main limitations. First,…