Related papers: MIRAGE: Online LLM Simulation for Microservice Dep…

Large Language Models (LLMs) are increasingly integrated into everyday applications, but their prevalent cloud-based deployment raises growing concerns around data privacy and long-term sustainability. Running LLMs locally on mobile and…

Modern microservice systems exhibit continuous structural evolution in their runtime call graphs due to workload fluctuations, fault responses, and deployment activities. Despite this complexity, our analysis of over 500,000 production…

The rapid advancement of large language models (LLMs) has spurred significant interest in tool learning, where LLMs are augmented with external tools to tackle complex tasks. However, existing tool environments face challenges in balancing…

Large language models (LLMs) have emerged as a powerful foundation for intelligent reasoning and decision-making, demonstrating substantial impact across a wide range of domains and applications. However, their massive parameter scales and…

Autonomous agents deployed in regulated domains must produce a verification artifact per consequential output: a record an auditor can re-execute offline, capturing what was claimed, against what source, by whom, when, and how. Production…

Active learning aims to efficiently build a labeled training set by strategically selecting samples to query labels from annotators. In this sequential process, each sample acquisition influences subsequent selections, causing dependencies…

Reconstructing numerical simulations from control systems research papers is often hindered by underspecified parameters and ambiguous implementation details. We define the task of Paper to Simulation Recoverability, the ability of an…

Large language models (LLMs) are prone to hallucinations and sensitive to prompt perturbations, often resulting in inconsistent or unreliable generated text. Different methods have been proposed to mitigate such hallucinations and…

AI agents that execute tasks via tool calls frequently hallucinate results - fabricating tool executions, misstating output counts, or presenting inferences as facts. Recent approaches to verifiable AI inference rely on zero-knowledge…

Deploying large language model (LLM)-driven conversational agents in enterprise settings requires prompts that are simultaneously correct at launch and resilient to the non-deterministic behavioral drift that characterizes production LLM…

The rapid growth of generative AI and its integration into everyday workflows have significantly increased the demand for large language model (LLM) inference services. While proprietary models remain popular, recent advancements in…

Large language model (LLM) agents on multi-step tasks suffer reasoning degradation, looping, drift, stuck states, at rates up to 30% on hard tasks. Current solutions include hard step limits (abrupt) or LLM-as-judge monitoring (10-15%…

Large language models (LLMs) inference is both expensive and slow. Local caching of responses offers a practical solution to reduce the cost and latency of LLM queries. In research contexts, caching also enhances reproducibility and…

Application Programming Interfaces (APIs) are crucial in modern software development. Large Language Models (LLMs) assist in automated code generation but often struggle with API hallucination, including invoking non-existent APIs and…

As large language models (LLMs) increasingly integrate native code interpreters, they enable powerful real-time execution capabilities, substantially expanding their utility. However, such integrations introduce potential system-level…

Appreciating multi-figure paintings requires understanding how characters relate through subtle cues like gaze alignment, gesture, and spatial arrangement. We present MIRAGE, an evidence-centric framework designed to scaffold the…

Code review is a key practice in software engineering, ensuring quality and collaboration. However, industrial Merge Request (MR) workflows often deviate from standardized review processes, with many MRs serving non-review purposes (e.g.,…

The interactive nature of Large Language Models (LLMs) theoretically allows models to refine and improve their answers, yet systematic analysis of the multi-turn behavior of LLMs remains limited. In this paper, we propose the FlipFlop…

LLM-powered coding agents increasingly make software supply chain decisions. They generate imports, recommend packages, and write installation commands. Prior work showed that these systems can hallucinate non-existent package names, which…

Online imitation learning is the problem of how best to mimic expert demonstrations, given access to the environment or an accurate simulator. Prior work has shown that in the infinite sample regime, exact moment matching achieves value…