Related papers: ChromaFlow: A Negative Ablation Study of Orchestra…
Recent advancements in Large Language Models (LLMs) have shown significant progress in understanding complex natural language. One important application of LLM is LLM-based AI Agent, which leverages the ability of LLM as well as external…
Tool-augmented large language models (LLMs) must tightly couple multi-step reasoning with external actions, yet existing benchmarks often confound this interplay with complex environment dynamics, memorized knowledge or dataset…
The adoption of large language models (LLMs) for structured information extraction from financial documents has accelerated rapidly, yet production deployments face fundamental architectural decisions with limited empirical guidance. We…
Driven by Large Language Models, the single-agent, multi-tool architecture has become a popular paradigm for autonomous agents. However, this architecture introduces a severe privacy risk, which we term Tools Orchestration Privacy Risk…
Multi-agent LLM systems have demonstrated impressive capabilities in complex collaborative tasks, yet most frameworks treat communication as instantaneous and free, overlooking a fundamental constraint in real world teamwork, collaboration…
Recent advances in LLM-based agent systems have shown promise on complex, long-horizon tasks, but existing agent protocols (e.g., A2A and MCP) do not adequately support lifecycle-aware coordination across agents, tools, and environments. To…
Collaboration literacy requires adapting to the evolving demands of group work within complex discussions, making it difficult to develop and assess. Traditional analytics metrics capture behavioral signals while missing the semantic…
While integrating tools like Code Interpreter and Search has significantly enhanced Large Language Model (LLM) reasoning in models like ChatGPT Agent and Gemini-Pro, practical guidance on optimal tool use is lacking. The core challenge is…
Autonomous agent systems powered by Large Language Models (LLMs) have demonstrated promising capabilities in automating complex tasks. However, current evaluations largely rely on success rates without systematically analyzing the…
Multi-Agentic AI systems, powered by large language models (LLMs), are inherently non-deterministic and prone to silent failures such as drift, cycles, and missing details in outputs, which are difficult to detect. We introduce the task of…
Agentic systems that chain reasoning, tool use, and synthesis into multi-step workflows are entering production, yet prevailing evaluation practices like end-to-end outcome checks and ad-hoc trace inspection systematically mask the…
Agent orchestration frameworks -- LangGraph, CrewAI, Google ADK, OpenAI Agents SDK, and others -- place an external orchestrator above the LLM, tracking state and injecting routing instructions at every turn. We present a controlled…
Agentic retrieval-augmented reasoning pipelines are increasingly used to structure how large language models (LLMs) incorporate external evidence in clinical decision support. These systems iteratively retrieve curated domain knowledge and…
Recent advances in LLM-based multi-agent systems (MAS) show that workflows composed of multiple LLM agents with distinct roles, tools, and communication patterns can outperform single-LLM baselines on complex tasks. However, most frameworks…
Multi-agent large language model (LLM) systems increasingly consist of agents that observe and respond to one another's outputs. While value alignment is typically evaluated for isolated models, how value perturbations propagate through…
Large Language Model (LLM) agents, which integrate planning, memory, reflection, and tool-use modules, have shown promise in solving complex, multi-step tasks. Yet their sophisticated architectures amplify vulnerability to cascading…
Autonomous agents based on Large Language Models (LLMs) are increasingly being utilized in complex software systems. However, reliability remains a significant challenge due to unpredictable failures such as hallucinations, execution…
Retrieval-Augmented Generation (RAG) is widely employed to mitigate risks such as hallucinations and knowledge obsolescence in medical question answering, yet its predominantly single-round, static retrieval paradigm misaligns with the…
Modern Artificial Intelligence (AI) increasingly relies on multi-agent architectures that blend visual and language understanding. Yet, a pressing challenge remains: How can we trust these agents especially in zero-shot settings with no…
Although LLM-based agents are proven to master tool orchestration in scientific fields, particularly chemistry, their single-task performance remains limited by underlying tool constraints. To this end, we propose tool amplification, a…