capture execution context

Current large language model (LLM) agents lack verifiability, debuggability, and auditability, and relying solely on the accuracy of final answers fails to reveal their underlying reasoning. To address this, this work proposes the first unified provenance framework for LLM agents, systematically modeling causal relationships in tool usage, memory access, and environmental interactions. It introduces a comprehensive provenance taxonomy encompassing source, granularity, representation format, and trust functions. By integrating provenance-aware representation modeling, evidence attribution, runtime safeguards, provenance-informed memory management, and trajectory observability analysis, the study shifts the evaluation paradigm from outcome correctness to process accountability. The framework consolidates existing benchmarks to define a clear pathway for process-level trustworthiness assessment and highlights key challenges, including standardized trajectory schemas, semantic-level provenance, and privacy-preserving auditing.

Hardware cache prefetching, memory scheduling, and channel interleaving obscure program context, hindering context-aware memory management. Method: This paper proposes a lightweight context-aware memory system that encodes program execution markers and object address ranges—i.e., contextual state—directly into standard memory read address streams as detectable metadata packets, requiring no privileged access or custom drivers. It integrates metadata injection, HMU-based telemetry hardware, and near-memory computing to enable bidirectional embedding and parsing of context within the address stream. Contribution/Results: A prototype demonstrates highly reliable metadata decoding from real address traces, enabling runtime fine-grained data scheduling, priority-aware memory management, and dynamic reconfiguration of memory devices. To our knowledge, this is the first end-to-end verifiable, zero-intrusion, fully user-space context-aware memory architecture.

Existing query-first data synthesis approaches struggle to generate valid and executable tool-use sequences. This work proposes SyntheticAgentTraceQA, a novel framework that introduces an "execution-first" paradigm: it first constructs high-level workflows, maps and validates feasible tool trajectories, and then synthesizes corresponding natural language tasks and reference answers. The method integrates dependency-aware tool assignment, trajectory validation in a controlled environment, and reasoning-augmented annotation generation, followed by fine-tuning and evaluation using the Qwen model. Experimental results demonstrate that this framework substantially improves large language model (LLM) agents’ tool execution accuracy, trajectory consistency, and answer quality. Furthermore, the study reveals that masked supervision outperforms full supervision for models at the 9B scale.

To address the challenges of fine-grained provenance capture and efficient querying in data preparation workflows, this paper proposes a tensor-based in-memory indexing mechanism. The method innovatively integrates both backward- and forward-looking provenance information, employing an enhanced tensor model to explicitly encode record-level and attribute-level input–output mappings, thereby enabling expressive lineage analysis. Unlike conventional approaches, its memory-efficient index design substantially reduces storage overhead while accelerating diverse provenance queries—including origin tracing, impact analysis, and dependency exploration. Experimental evaluation on real-world and synthetic datasets demonstrates that our approach consistently outperforms state-of-the-art baselines in both query latency and memory footprint. The proposed solution thus provides scalable, high-performance provenance support for critical downstream tasks such as debugging, model interpretability, fairness auditing, and data quality diagnostics.

This work addresses the challenge of automatically recovering traceability links among software architecture documentation, models, and source code—a longstanding barrier to effective system maintenance and consistency assurance. To bridge this gap, we present the first end-to-end ecosystem for architecture-level traceability recovery, comprising a RESTful API supporting four distinct tracing pipelines, an interactive web-based frontend named TraceView, and TraceViz, an embedded visualization plugin for Visual Studio Code. The system integrates seamlessly into developer workflows through asynchronous task processing and caching optimizations, enabling intuitive exploration of traceability links directly within the IDE. All components are publicly deployed, and preliminary user studies indicate that TraceViz significantly enhances developers’ cognitive efficiency during software comprehension tasks.

This work addresses the limitations of existing AI agent workflows, which rely on implicit dialogue states and struggle to ensure stability of intermediate artifacts, isolate irrelevant updates, and propagate changes precisely. To overcome these challenges, the paper proposes modeling AI-native workflows as directed acyclic graphs (DAGs) and introduces the concept of execution lineage. By leveraging explicit dependency tracking, identity-based identification of intermediate artifacts, and an identity-aware replay mechanism, this approach achieves deterministic computation graphs in AI agents for the first time. The method guarantees precise change propagation, zero contamination across unrelated branches, and preserves both upstream stability and cross-artifact consistency. Evaluated on a policy memo updating task, DAG-based replay attains 100% fidelity in final outputs, substantially outperforming iterative baseline approaches.

This study addresses the opacity of AI-generated code, which often hinders traceability to its origins and underlying rationale. The work presents the first systematic formulation of a four-dimensional traceability problem for AI-generated code and introduces a novel research framework that integrates causal inference with explainability techniques. This framework enables an automated post-hoc tracing mechanism that links generated code to its prompt, specific training data instances, global data characteristics, and internal model components. Through large-scale empirical evaluation and user studies, the research not only substantiates the necessity of explainable provenance tracing but also identifies key challenges and outlines a feasible technical pathway toward realizing a new paradigm for CodeGenAI.

This work addresses the limited reproducibility of behavioral validation in robotic simulation testing, which often stems from insufficiently documented test configurations, execution protocols, and post-processing procedures. To overcome this, the study proposes a deep integration of data provenance and FAIR (Findable, Accessible, Interoperable, Reusable) principles throughout the entire test generation pipeline—rather than merely appending them to final datasets. The authors extend an existing simulation testing framework by embedding machine-readable, structured metadata at every stage, thereby enabling end-to-end traceable validation workflows. This approach significantly enhances the reproducibility of mobile robot navigation datasets. Additionally, the project distills practical FAIR implementation guidelines tailored to robotics, identifying key challenges such as vocabulary alignment, attribute selection, and adoption of community standards, and offers actionable recommendations for addressing them.

Existing Model Cards and Data Cards describe only static models and datasets, lacking documentation of the execution context surrounding generation, transformation, and evaluation processes—thereby limiting reproducibility and bias analysis. This work proposes Workflow Cards, which extend the structured documentation paradigm to dynamic workflow executions for the first time. Built upon provenance data, Workflow Cards generate machine-readable, structured summaries interpretable by both humans and large language models (LLMs), and incorporate a template designed to answer typical execution-related questions. Experimental results demonstrate that Workflow Cards substantially enhance understanding of workflow executions compared to schema-based query interfaces, nearly doubling answer quality and achieving superior performance under both LLM-as-a-Judge and human evaluations.

This work addresses the challenge of reliably tracing the provenance of tensors and operators through graph rewrites—particularly non-injective transformations—in AI compilers. The authors propose a lightweight, generative provenance method grounded in observational semantics, which infers origins by analyzing the behavioral effects of graph transformations rather than relying on identifier propagation. For the first time, they introduce coalgebraic modeling and bisimulation to this domain, guaranteeing provenance consistency even after intermediate nodes are eliminated. The approach requires no invasive compiler modifications and naturally supports non-injective rewrites. Evaluated within COVAN, a prototype AI compiler, the method demonstrates stable, low-overhead provenance tracking throughout an end-to-end compilation pipeline.