English
Related papers

Related papers: AgentEval: DAG-Structured Step-Level Evaluation fo…

200 papers

Agentic AI systems automate enterprise workflows but existing defenses--guardrails, semantic filters--are probabilistic and routinely bypassed. We introduce authenticated workflows, the first complete trust layer for enterprise agentic AI.…

Cryptography and Security · Computer Science 2026-02-12 Mohan Rajagopalan , Vinay Rao

Heavy supervised fine-tuning on a target domain can strongly suppress capabilities that were present in the base model. We study this phenomenon in formal mathematics using Goedel-Prover-V2, an open-source model heavily trained on 1.8…

Artificial Intelligence · Computer Science 2026-04-10 Jui-Hui Chung , Hongzhou Lin , Lai Jiang , Shange Tang , Chi Jin

Code agents resolve 65-70% of SWE-bench Verified issues, but Pass@1 cannot tell us why the rest fail, and, as we show, capable-model failures are systematically misdiagnosed without trajectory data. We introduce TRAJEVAL, a training-free…

The rapid adoption of LLM-based agentic systems has produced a rich ecosystem of frameworks (smolagents, LangGraph, AutoGen, CAMEL, LlamaIndex, i.a.). Yet existing benchmarks are model-centric: they fix the agentic setup and do not compare…

Artificial Intelligence · Computer Science 2026-03-11 Cornelius Emde , Alexander Rubinstein , Anmol Goel , Ahmed Heakl , Sangdoo Yun , Seong Joon Oh , Martin Gubri

Large Language Models (LLMs) are evolving into autonomous agents, yet current "frameless" development--relying on ambiguous natural language without engineering blueprints--leads to critical risks such as scope creep and open-loop failures.…

Artificial Intelligence · Computer Science 2026-02-24 Chanjin Park

Agentic AI shifts LLM serving from isolated prompt-generation requests to stateful, multi-turn executions that repeatedly invoke the model, call tools, and grow context over time. This paper characterizes ReAct-style agents from both the…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-27 Yichao Yuan , Ankita Nayak , Souvik Kundu , Nishil Talati

Agentic retrieval-augmented generation (RAG) formulates question answering as a multi-step interaction between reasoning and information retrieval, and has recently been advanced by reinforcement learning (RL) with outcome-based…

Computation and Language · Computer Science 2026-01-13 Tianhua Zhang , Kun Li , Junan Li , Yunxiang Li , Hongyin Luo , Xixin Wu , James Glass , Helen Meng

Across many domains (e.g., IoT, observability, telecommunications, cybersecurity), there is an emerging adoption of conversational data analysis agents that enable users to "talk to your data" to extract insights. Such data analysis agents…

Artificial Intelligence · Computer Science 2026-03-16 Aadyaa Maddi , Prakhar Naval , Deepti Mande , Shane Duan , Muckai Girish , Vyas Sekar

LLM-powered Multi-Agent Systems (MAS) have demonstrated remarkable capabilities in complex domains but suffer from inherent fragility and opaque failure mechanisms. Existing failure attribution methods, whether relying on direct prompting,…

Artificial Intelligence · Computer Science 2026-03-02 Yawen Wang , Wenjie Wu , Junjie Wang , Qing Wang

Agents aspire to eliminate the need for task-specific prompt crafting through autonomous reason-act-observe loops. Still, they are commonly instructed to follow a task-specific plan for guidance, e.g., to resolve software issues following…

Software Engineering · Computer Science 2026-04-29 Shuyang Liu , Saman Dehghan , Jatin Ganhotra , Martin Hirzel , Reyhaneh Jabbarvand

Agentic AI systems increasingly act through tool-augmented, multi-step workflows whose failures (unsafe tool use, unauthorised actions, social harm) carry deployment-level consequences. Evaluation practice remains fragmented across isolated…

Computation and Language · Computer Science 2026-05-22 Jinhu Qi , Yifan Li , Minghao Zhao , Wentao Zhang , Zijian Zhang , Yaoman Li , Irwin King

As AI agents transition from human-supervised copilots to autonomous platform infrastructure, the ability to analyze their reasoning behavior across populations of investigations becomes a pressing infrastructure requirement. Existing…

Artificial Intelligence · Computer Science 2026-04-13 Neelmani Vispute , Aditya Kadam

AI agents often fail in ways that are difficult to localize because executions are probabilistic, long-horizon, multi-agent, and mediated by noisy tool outputs. We address this gap by manually annotating failed agent runs and release a…

Artificial Intelligence · Computer Science 2026-02-03 Shraddha Barke , Arnav Goyal , Alind Khare , Avaljot Singh , Suman Nath , Chetan Bansal

Multi-Agent Reinforcement Learning (MARL) is increasingly deployed in safety-critical domains, yet methods for interpretable failure detection and attribution remain underdeveloped. We introduce a two-stage gradient-based framework that…

Artificial Intelligence · Computer Science 2026-02-24 Risal Shahriar Shefin , Debashis Gupta , Thai Le , Sarra Alqahtani

As large language models increasingly deployed into agentic systems, existing methods face critical gaps in observing, assessing, and mitigating deployment-specific risks. We present a comprehensive, observability-driven workflow: we…

Computation and Language · Computer Science 2026-04-28 Ilham Wicaksono , Zekun Wu , Rahul Patel , Theo King , Adriano Koshiyama , Philip Treleaven

Agentic Reinforcement Learning (RL) enables LLMs to solve complex tasks by alternating between a data-collection rollout phase and a policy training phase. During rollout, the agent generates trajectories, i.e., multi-step interactions…

Machine Learning · Computer Science 2026-03-31 Zili Zhang , Yinmin Zhong , Chengxu Yang , Chao Jin , Bingyang Wu , Xinming Wei , Yuliang Liu , Xin Jin

Evaluating retrieval-augmented generation (RAG) presents challenges, particularly for retrieval models within these systems. Traditional end-to-end evaluation methods are computationally expensive. Furthermore, evaluation of the retrieval…

Computation and Language · Computer Science 2024-04-23 Alireza Salemi , Hamed Zamani

Scientific workflows are often represented as directed acyclic graphs (DAGs), where vertices correspond to tasks and edges represent the dependencies between them. Since these graphs are often large in both the number of tasks and their…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-07-15 Svetlana Kulagina , Henning Meyerhenke , Anne Benoit

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…

Artificial Intelligence · Computer Science 2025-11-19 Sushant Mehta

Agents, language model-based systems capable of reasoning, planning, and acting are widely adopted in real-world tasks, yet how their performance changes as these systems scale across key dimensions remains underexplored. We introduce…

‹ Prev 1 4 5 6 7 8 10 Next ›