Related papers: Beyond Task Success: Measuring Workflow Fidelity i…
Agentic systems for business process automation often require compliance with policies governing conditional updates to the system state. Evaluation of policy adherence in LLM-based agentic workflows is typically performed by comparing the…
We study how runtime enforcement against unsafe actions affects end-to-end task performance in multi-step tool using large language model (LLM) agents. Using tau-bench across Airline and Retail domains, we compare baseline Tool-Calling,…
Recent advances in agentic AI have shifted the focus from standalone Large Language Models (LLMs) to integrated systems that combine LLMs with tools, memory, and other agents to perform complex tasks. These multi-agent architectures enable…
Despite rapid development, large language models (LLMs) still encounter challenges in multi-turn decision-making tasks (i.e., agent tasks) like web shopping and browser navigation, which require making a sequence of intelligent decisions…
We study whether self-learning can scale LLM-based agents without relying on human-curated datasets or predefined rule-based rewards. Through controlled experiments in a search-agent setting, we identify two key determinants of scalable…
LLM-based multi-agent systems are increasingly deployed on long-horizon tasks, but a single decisive error is often accepted by downstream agents and cascades into trajectory-level failure. Existing work frames this as \emph{post-hoc…
Agentic systems are evaluated on benchmarks where agents interact with environments to solve tasks. Most papers report a pass@1 score computed from a single run per task, assuming this gives a reliable performance estimate. We test this…
Information Retrieval is shifting from passive document ranking toward autonomous agentic workflows that operate in multi-step Reason-Act-Observe loops. In such long-horizon trajectories, minor early errors can cascade, leading to…
Agentic Reinforcement Learning (RL) shows promise for complex tasks, but Text-to-SQL remains mostly restricted to single-turn paradigms. A primary bottleneck is the credit assignment problem. In traditional paradigms, rewards are determined…
As the focus in LLM-based coding shifts from static single-step code generation to multi-step agentic interaction with tools and environments, understanding which tasks will challenge agents and why becomes increasingly difficult. This is…
Current agentic AI benchmarks predominantly evaluate task completion accuracy, while overlooking critical enterprise requirements such as cost-efficiency, reliability, and operational stability. Through systematic analysis of 12 main…
Verifiers have been demonstrated to enhance LLM reasoning via test-time scaling (TTS). Yet, they face significant challenges in complex domains. Error propagation from incorrect intermediate reasoning can lead to false positives for…
Advancements in Large Language Models (LLMs) are revolutionizing the development of autonomous agentic systems by enabling dynamic, context-aware task decomposition and automated tool selection. These sophisticated systems possess…
Large language model agents now act on codebases, browsers, operating systems, calendars, files, and tool ecosystems, but their evaluations often collapse behavior into final task success. AgentAtlas reframes agent evaluation as a…
Agentic security systems increasingly audit live targets with tool-using LLMs, but prior systems fix a single coordination topology, leaving unclear when additional agents help and when they only add cost. We treat topology choice as an…
Automatic speech recognition (ASR) is a core component of human--computer interaction and an increasingly important front-end for LLM-based assistants and agents. However, most current ASR systems still follow a single-pass paradigm, which…
Agent orchestration frameworks have proliferated, collectively exceeding 290,000 GitHub stars across LangGraph, CrewAI, Google ADK, OpenAI Agents SDK, Semantic Kernel, Strands, and LlamaIndex. All follow the same pattern: an external…
Failure attribution in LLM multi-agent systems-identifying the agent and step responsible for task failures-provides crucial clues for systems debugging but remains underexplored and labor-intensive. In this paper, we propose and formulate…
We investigated Agentic RL with large language models on the \textsc{TravelPlanner} benchmark. Our approach, \textsc{Planner-R1}, achieved a \textbf{56.9\%} final-pass rate with only 180 training queries, a $2.7\times$ improvement over…
Web agents enable users to perform tasks on web browsers through natural language interaction. Evaluating web agents trajectories is an important problem, since it helps us determine whether the agent successfully completed the tasks.…