Related papers: Crab: A Semantics-Aware Checkpoint/Restore Runtime…
Enterprise software engineering is shifting away from deterministic CRUD/REST architectures toward AI-native systems where large language models act as cognitive orchestrators. This transition introduces a critical security tension:…
Current LLM agents are proficient at calling isolated APIs but struggle with the "last mile" of commercial software automation. In real-world scenarios, tools are not independent; they are atomic, interdependent, and prone to environmental…
Stateful tool-using LLM agents treat the context window as working memory, yet today's agent harnesses manage residency and durability as best-effort, causing recurring failures: lost state after compaction, bypassed flushes on reset, and…
Checkpoint/Restart (C/R) saves the running state of the programs periodically, which consumes considerable system resources. We observe that not every piece of data is involved in the computation in typical HPC applications; such unused…
We propose A-Crab (Actor-Critic Regularized by Average Bellman error), a new practical algorithm for offline reinforcement learning (RL) in complex environments with insufficient data coverage. Our algorithm combines the marginalized…
Rollback recovery strategies are well-known in concurrent and distributed systems. In this context, recovering from unexpected failures is even more relevant given the non-deterministic nature of execution, which means that it is…
AI agents are increasingly deployed to automate complex enterprise workflows, yet evidence of their effectiveness in identity governance is limited. We report results from the first randomized controlled trial (RCT) evaluating an AI agent…
Agentic language-model systems increasingly rely on mutable execution contexts, including files, memory, tools, skills, and auxiliary artifacts, creating security risks beyond explicit user prompts. This paper presents DeepTrap, an…
Agentic exploration, letting LLM-powered agents branch, backtrack, and search across many execution paths, demands systems support well beyond today's pass-at-k resets. Our benchmark of six snapshot/restore mechanisms shows that generic…
Task success can hide process anomalies in real-world agent executions. An agent may pass the final task oracle while still accumulating unresolved ambiguity, unsafe external writes, ignored errors, weakly grounded commitments, or…
When language model agents tackle complex software engineering tasks, they often degrade over long trajectories, which we define as *agent drift*. We focus on two recurring failure modes *overthinking* and *overacting*, i.e., where the…
Recent advances in frontier large language models have enabled code review agents that operate in open-ended, reasoning-intensive settings. However, the lack of standardized benchmarks and granular evaluation protocols makes it difficult to…
Automated Program Repair (APR) has advanced rapidly with Large Language Models (LLMs), but most existing methods remain computationally expensive, and focused on a small set of languages. Ruby, despite its widespread use in web development…
Software engineering agents have shown significant promise in writing code. As AI agents permeate code writing, and generate huge volumes of code automatically -- the matter of code quality comes front and centre. As the automatically…
Agentic reinforcement learning (RL) holds great promise for the development of autonomous agents under complex GUI tasks, but its scalability remains severely hampered by the verification of task completion. Existing task verification is…
Reinforcement Learning (RL) agents are increasingly used to simulate sophisticated cyberattacks, but their decision-making processes remain opaque, hindering trust, debugging, and defensive preparedness. In high-stakes cybersecurity…
This paper presents an empirical study on the feasibility of using Checkpoint/Restore In Userspace (CRIU) for run-time application migration between hosts, with a particular focus on edge computing and cloud infrastructures. The paper…
Existing AI agents typically execute multi-step tasks autonomously and only allow user confirmation at the end. During execution, users have little control, making the confirm-at-end approach brittle: a single error can cascade and force a…
Checkpoint/Restart (C/R) has been widely deployed in numerous HPC systems, Clouds, and industrial data centers, which are typically operated by system engineers. Nevertheless, there is no existing approach that helps system engineers…
Owing to recent advancements, Large Language Models (LLMs) can now be deployed as agents for increasingly complex decision-making applications in areas including robotics, gaming, and API integration. However, reflecting past experiences in…