English
Related papers

Related papers: Trace-Level Analysis of Information Contamination …

200 papers

Hierarchical task decomposition is a method used in many agent systems to organize agent knowledge. This work shows how the combination of a hierarchy and persistent assertions of knowledge can lead to difficulty in maintaining logical…

Artificial Intelligence · Computer Science 2011-06-27 J. E. Laird , R. E. Wray

Language models (LMs) can perform complex reasoning either end-to-end, with hidden latent state, or compositionally, with transparent intermediate state. Composition offers benefits for interpretability and safety, but may need workflow…

Computation and Language · Computer Science 2023-01-06 Justin Reppert , Ben Rachbach , Charlie George , Luke Stebbing , Jungwon Byun , Maggie Appleton , Andreas Stuhlmüller

LLM agents have begun to find real security vulnerabilities that human auditors and automated fuzzers missed for decades, in source-available targets where the analyst can build and instrument the code. In practice the work is split among…

Cryptography and Security · Computer Science 2026-04-23 Hanzhi Liu , Chaofan Shou , Xiaonan Liu , Hongbo Wen , Yanju Chen , Ryan Jingyang Fang , Yu Feng

The AI trustworthiness crisis threatens to derail the artificial intelligence revolution, with regulatory barriers, security vulnerabilities, and accountability gaps preventing deployment in critical domains. Current AI systems operate on…

Cryptography and Security · Computer Science 2025-11-26 Vineeth Sai Narajala , Manish Bhatt , Idan Habler , Ronald F. Del Rosario , Ads Dawson

Information-theoretic arguments focus on modeling the reliability of information transmission, assuming availability of infinite data at sources, thus ignoring randomness in message generation times at the respective sources. However, in…

Networking and Internet Architecture · Computer Science 2009-09-29 K. C. V. Kalyanarama Sesha Sayee

Multi-agent Large Language Model (LLM) systems have emerged as powerful architectures for complex task decomposition and collaborative problem-solving. However, their long-term behavioral stability remains largely unexamined. This study…

Artificial Intelligence · Computer Science 2026-01-08 Abhishek Rath

Large language models are increasingly being used to support network operations (NetOps) and artificial intelligence for IT operations (AIOps), including incident investigation, root-cause analysis, configuration synthesis, and limited…

Networking and Internet Architecture · Computer Science 2026-05-14 Muhammad Bilal , Jon Crowcroft , Ruizhi Wang , Xiaolong Xu , Schahram Dustdar

The rapid proliferation of misinformation in digital media demands solutions that go beyond isolated Large Language Model(LLM) or AI Agent based detection methods. This paper introduces a novel multi-agent framework that covers the complete…

Multiagent Systems · Computer Science 2025-05-26 Aditya Gautam

We present a deductive approach for the analysis of secure information flows with support for fine-grained policies that include declassifications in the form of delimited information release. By explicitly tracking the dependencies of…

Logic in Computer Science · Computer Science 2015-09-15 Bart van Delft , Richard Bubel

As generative models are advancing in quality and quantity for creating synthetic content, deepfakes begin to cause online mistrust. Deepfake detectors are proposed to counter this effect, however, misuse of detectors claiming fake content…

Artificial Intelligence · Computer Science 2025-10-29 Neslihan Kose , Anthony Rhodes , Umur Aybars Ciftci , Ilke Demir

Agentic applications based on large language models increasingly rely on multi-step interaction loops involving planning, action execution, and environment feedback. While such systems are now deployed at scale, improving them…

Artificial Intelligence · Computer Science 2026-04-02 Shuguang Chen , Adil Hafeez , Salman Paracha

Generative AI shifts interaction toward intent-based outcome specification, despite user intents being inherently vague, fluid, and evolving. While a growing body of HCI research has proposed diverse interaction techniques to support this…

Human-Computer Interaction · Computer Science 2026-01-29 Yoonsu Kim , Kihoon Son , Seoyoung Kim , Brandon Chin , Juho Kim

Large language models can deceive by subtly manipulating truthful information -- omitting key facts, shifting focus, or obscuring meaning -- making such behavior difficult to detect. Existing black-box methods rely on coarse-grained…

Computation and Language · Computer Science 2026-05-20 Linyue Cai , Samuel Yeh , Jwala Dhamala , Rahul Gupta , Sharon Li

To support operations and passenger-facing services, transit agencies need reliable passenger load trajectories. Currently, load estimates are typically inferred from imperfect sensing systems rather than fully observed, and the accuracy of…

Machine Learning · Computer Science 2026-05-20 Yiyao Xu , Hao Zhou , Yuhang Wang , Jingran Sun

Typical active learning strategies are designed for tasks, such as classification, with the assumption that the output space is mutually exclusive. The assumption that these tasks always have exactly one correct answer has resulted in the…

Computer Vision and Pattern Recognition · Computer Science 2019-12-10 Khaled Jedoui , Ranjay Krishna , Michael Bernstein , Li Fei-Fei

This research paper addresses the limitations of semantic search in complex enterprise document ecosystems. Traditional RAG pipelines often fail to capture hierarchical and interconnected information, leading to retrieval inaccuracies. We…

Information Retrieval · Computer Science 2026-04-17 Koushik Chakraborty , Koyel Guha

Information flow analysis prevents secret or untrusted data from flowing into public or trusted sinks. Existing mechanisms cover a wide array of options, ranging from lightweight taint analysis to heavyweight information flow control that…

Cryptography and Security · Computer Science 2019-06-28 Cristian-Alexandru Staicu , Daniel Schoepe , Musard Balliu , Michael Pradel , Andrei Sabelfeld

Knowledge graphs serve as critical resources supporting intelligent systems, but they can be noisy due to imperfect automatic generation processes. Existing approaches to noise detection often rely on external facts, logical rule…

Machine Learning · Computer Science 2025-03-14 Jiaqi Sun , Yujia Zheng , Xinshuai Dong , Haoyue Dai , Kun Zhang

Diagnosing failures in LLM agents remains largely manual. Practitioners inspect a small subset of execution traces, form ad-hoc hypotheses, and iterate. This process misses patterns that only emerge across trace populations and does not…

Artificial Intelligence · Computer Science 2026-05-22 Akshay Manglik , Apaar Shanker , Kaustubh Deshpande , Jason Qin , Yash Maurya , Veronica Chatrath , Vijay S. Kalmath , Levi Lentz , Yuan , Xue

Agentic frameworks are the software layer through which AI agents act in the world. Existing safety methods intervene on the model and therefore remain conditional on unverifiable properties of learned behavior. We introduce containment…

Artificial Intelligence · Computer Science 2026-05-12 Royce Moon , Lav R. Varshney