Related papers: In-Context Prompting Obsoletes Agent Orchestration…
In the age of large language models (LLMs), autonomous agents have emerged as a powerful paradigm for achieving general intelligence. These agents dynamically leverage tools, memory, and reasoning capabilities to accomplish user-defined…
Tool-using large language model (LLM) agents often face a fundamental tension between answer quality and execution cost. Fixed workflows are stable but inflexible, while free-form multi-step reasoning methods such as ReAct may improve task…
Improving Large Language Model (LLM) agents for sequential decision-making tasks typically requires extensive task-specific knowledge engineering--custom prompts, curated examples, and specialized observation/action spaces. We investigate a…
Comprehensive planning agents have been a long term goal in the field of artificial intelligence. Recent innovations in Natural Language Processing have yielded success through the advent of Large Language Models (LLMs). We seek to improve…
Recent Large Audio Language Models (LALMs) excel in understanding but often lack transparent reasoning. To address this "black-box" limitation, we organized the Audio Reasoning Challenge at Interspeech 2026, the first shared task dedicated…
Multi-agent LLM orchestration systems suffer from context pollution: when N concurrent agents compete for the orchestrator's context window, each agent's task state, partial outputs, and pending questions contaminate the steering…
Strategies for orchestrating the interactions between multiple agents, both human and artificial, can wildly overestimate performance and underestimate the cost of orchestration. We design a framework to orchestrate agents under realistic…
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…
Automatic search for Multi-Agent Systems has recently emerged as a key focus in agentic AI research. Several prior approaches have relied on LLM-based free-form search over the code space. In this work, we propose a more structured…
We introduce Context Kubernetes, an architecture for orchestrating enterprise knowledge in agentic AI systems, with a prototype implementation and eight experiments. The core observation is that delivering the right knowledge, to the right…
Agentic applications are LLMs that iteratively invoke external tools to accomplish complex tasks. Such tool-based agents are rapidly becoming the dominant paradigm for deploying language models in production. Unlike traditional single-turn…
The dominant paradigm for building LLM based agents is the Agent Loop, an iterative cycle where a single language model decides what to do next by reading an ever growing context window. This paradigm has three structural weaknesses:…
Multi-agent large language model frameworks are promising for complex multi step reasoning, yet existing systems remain weak for scientific and knowledge intensive domains due to static prompts and agent roles, rigid workflows, and…
LLM-driven GUI agents are increasingly used in production systems to automate workflows and simulate users for evaluation and optimization. Yet most GUI-agent evaluations emphasize task success and provide limited evidence on whether agents…
The rapid proliferation of LLM agent frameworks has forced developers to choose between vendor lock-in through provider-specific SDKs and complex multi-package ecosystems that obscure control flow and hinder reproducibility. Integrating…
Recent advances in Large Language Models (LLMs) have propelled intelligent agents from reactive responses to proactive support. While promising, existing proactive agents either rely exclusively on observations from enclosed environments…
The remarkable performance of pre-trained large language models has revolutionised various natural language processing applications. Due to huge parametersizes and extensive running costs, companies or organisations tend to transfer the…
LLM-based web agents show immense promise for information seeking, yet their effectiveness on long-horizon tasks is hindered by a fundamental trade-off in context management. Prevailing ReAct-based agents suffer from context saturation as…
Language agents powered by large language models (LLMs) have demonstrated remarkable capabilities in understanding, reasoning, and executing complex tasks. However, developing robust agents presents significant challenges: substantial…
Multi-agent systems built on Large Language Models (LLMs) show exceptional promise for complex collaborative problem-solving, yet they face fundamental challenges stemming from context window limitations that impair memory consistency, role…