Related papers: AgentEval: DAG-Structured Step-Level Evaluation fo…
Fault Localization (FL) is an essential step during the debugging process. With the strong capabilities of code comprehension, the recent Large Language Models (LLMs) have demonstrated promising performance in diagnosing bugs in the code.…
Large language model agents increasingly operate through environment-facing scaffolds that expose files, web pages, APIs, and logs. These observations influence tool use, state tracking, and action sequencing, yet their reliability and…
We study networked binary classification on a directed acyclic graph (DAG) where each agent observes only a subset of the feature columns of a shared dataset. Agents act sequentially along the DAG: each receives prediction columns from its…
Existing tool-use benchmarks for LLM agents are overwhelmingly linear: our analysis of six benchmarks shows 55 to 100% of instances are simple chains of 2 to 5 steps. We introduce The Amazing Agent Race (AAR), a benchmark featuring directed…
Drug discovery frequently loses momentum when data, expertise, and tools are scattered, slowing design cycles. To shorten this loop we built a hierarchical, tool using agent framework that automates molecular optimisation. A Principal…
While AI agents demonstrate remarkable capabilities in reasoning and tool use, they remain fundamentally reactive: they compute responses only after explicit user prompts. This paradigm ignores a critical opportunity: the idle time between…
Dialogue policy plays an important role in task-oriented spoken dialogue systems. It determines how to respond to users. The recently proposed deep reinforcement learning (DRL) approaches have been used for policy optimization. However,…
With the advancement of Agentic AI, researchers are increasingly leveraging autonomous agents to address challenges in software engineering (SE). However, the large language models (LLMs) that underpin these agents often function as black…
We introduce TDFlow, a novel test-driven agentic workflow that frames repository-scale software engineering as a test-resolution task, specifically designed to solve human-written tests. Given a set of tests, TDFlow repeatedly proposes,…
Large Language Models (LLMs) increasingly rely on agentic capabilities-iterative retrieval, tool use, and decision-making-to overcome the limits of static, parametric knowledge. Yet existing agentic frameworks treat external information as…
As the industry increasingly adopts agentic AI systems, understanding their unique vulnerabilities becomes critical. Prior research suggests that security flaws at the model level do not fully capture the risks present in agentic…
While individual components of agentic architectures have been studied in isolation, there remains limited empirical understanding of how different design dimensions interact within complex multi-agent systems. This study aims to address…
User comments on online programming platforms such as Stack Overflow play a vital role in maintaining the correctness and relevance of shared code examples. However, the majority of comments express gratitude or clarification, while only a…
The application of Large Language Models (LLMs) in healthcare is expanding rapidly, with one potential use case being the translation of formal medical reports into patient-legible equivalents. Currently, LLM outputs often need to be edited…
Large Language Models have evolved from single-round generators into long-horizon agents, capable of complex text synthesis scenarios. However, current evaluation frameworks lack the ability to assess the actual synthesis operations, such…
The rapid proliferation of Claude agent skills has raised the central question of how to effectively leverage, manage, and scale the agent skill ecosystem. In this paper, we propose AgentSkillOS, the first principled framework for skill…
Leveraging multiple Large Language Models(LLMs) has proven effective for addressing complex, high-dimensional tasks, but current approaches often rely on static, manually engineered multi-agent configurations. To overcome these constraints,…
Enterprise agents increasingly operate inside scoped retrieval systems, delegated workflows, and policy-constrained evidence environments. In these settings, access control can be enforced correctly while the system still produces an answer…
Despite remarkable advances in Large Language Model capabilities, tool retrieval for agent-based systems remains fundamentally limited by reliance on semantic similarity, which fails to capture functional viability. Current methods often…
Modern AI agents execute real-world side effects through tool calls such as file operations, shell commands, HTTP requests, and database queries. A single unsafe action, including accidental deletion, credential exposure, or data…