Related papers: Beyond Max Tokens: Stealthy Resource Amplification…

The rapid adoption of Large Language Model (LLM) agents and multi-agent systems enables remarkable capabilities in natural language processing and generation. However, these systems introduce security vulnerabilities that extend beyond…

In recent years, Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse NLP tasks. Extensive research has explored how to enhance the logical reasoning abilities such as Chain-of-Thought, Chain-of-Thought with…

This paper introduces a simple and scalable approach to improve the data efficiency of large language model (LLM) training by augmenting existing text data with thinking trajectories. The compute for pre-training LLMs has been growing at an…

Modern large language model (LLM) services increasingly rely on complex, often abstract operations, such as multi-step reasoning and multi-agent collaboration, to generate high-quality outputs. While users are billed based on token…

AI agents, powered by large language models (LLMs), have transformed human-computer interactions by enabling seamless, natural, and context-aware communication. While these advancements offer immense utility, they also inherit and amplify…

The Model Context Protocol (MCP) is emerging as a standard interface through which large language model (LLM) agents discover and invoke external tools. However, existing MCP evaluations fall short along three key axes: realistic multi-step…

Most flagship language models generate explicit reasoning chains, enabling inference-time scaling. However, producing these reasoning chains increases token usage (i.e., reasoning tokens), which in turn increases latency and costs. Our…

Most discussions about Large Language Model (LLM) safety have focused on single-agent settings but multi-agent LLM systems now create novel adversarial risks because their behavior depends on communication between agents and decentralized…

Test-time scaling (TTS) enhances the performance of large language models (LLMs) by allocating additional compute resources during inference. However, existing research primarily investigates TTS in single-stage tasks; while many real-world…

The remarkable performance of large language models (LLMs) in generation tasks has enabled practitioners to leverage publicly available models to power custom applications, such as chatbots and virtual assistants. However, the data used to…

Large Language Model (LLM)-based agents have demonstrated remarkable capabilities in reasoning, planning, and tool usage. The recently proposed Model Context Protocol (MCP) has emerged as a unifying framework for integrating external tools…

Language models (LMs) are becoming increasingly dependent on external tools. LM-based agentic frameworks frequently interact with their environment via such tools to search files, run code, call APIs, etc. Further, modern reasoning-based…

Tool-augmented LLM agents tend to call tools indiscriminately, even when the model can answer directly. Each unnecessary call wastes API fees and latency, yet no existing benchmark systematically studies when a tool call is actually needed.…

Large Language Models (LLMs) have demonstrated strong capabilities as autonomous agents through tool use, planning, and decision-making abilities, leading to their widespread adoption across diverse tasks. As task complexity grows,…

Recent advances in the Model Context Protocol (MCP) have enabled large language models (LLMs) to invoke external tools with unprecedented ease. This creates a new class of powerful and tool augmented agents. Unfortunately, this capability…

The development of autonomous machine learning (ML) agents capable of end-to-end data science workflows represents a significant frontier in artificial intelligence. These agents must orchestrate complex sequences of data analysis, feature…

Large Language Models (LLM) are increasingly being explored for problem-solving tasks. However, their strategic planning capability is often viewed with skepticism. Recent studies have incorporated the Monte Carlo Tree Search (MCTS)…

As LLMs advance into autonomous agents with tool-use capabilities, they introduce security challenges that extend beyond traditional content-based LLM safety concerns. This paper introduces Sequential Tool Attack Chaining (STAC), a novel…

Multi-agent large language model (LLM) architectures increasingly rely on response-level aggregation, such as Majority Voting (MAJ), to raise reasoning ceilings. However, in open environments, agents are highly susceptible to stealthy…

Large Language Models (LLMs) remain vulnerable to jailbreak attacks that bypass their safety mechanisms. Existing attack methods are fixed or specifically tailored for certain models and cannot flexibly adjust attack strength, which is…