1 More Paper

Frontkom

Listen to the latest research on how organizations adopt AI, reshape work, and govern its use. Full papers, read verbatim (by AI).

  1. 9h ago

    A critical juncture: Integrating large language models in biostatistical workflows — Sahu (2026)

    This Full Reading presents the paper's text as an audio edition. Authors: V. Sahu Publication date: 2026 Read the paper Source license: Creative Commons Attribution 4.0 International Narration: Read verbatim by an AI-generated voice. The authors and publisher do not sponsor or endorse this recording.

  2. 4d ago

    Safe, Persistent, and Evolving Agent Harness for Understanding Partially Observable Worlds — Gao et al. (2026)

    Large language model agents can invoke tools fluently, but enterprise workflows demand more than selecting the right tools: actions must strictly comply with organizational policies, tool feedback often conceals hidden side effects under partial observability, and long-horizon tasks require persistent state tracking across multiple records. To address these challenges, we introduce E-Ledger, a multi-agent harness for safe and persistent execution. E-Ledger employs a code approval layer that checks every proposed action against policy before execution, and maintains a world ledger of verified hidden rules alongside evidence-backed dynamic state. Because hidden rules are typically unknown a priori, we further propose WorldAbduct, an abductive, world-model-driven harness evolution framework. WorldAbduct diagnoses execution trajectories across four complementary views (state consistency, world-observation gap, policy-gate correctness, and goal judgment) to hypothesize latent rules, and verifies them through targeted abductive interactions before integrating them into the ledger. On the enterprise benchmark World of Workflows, E-Ledger with WorldAbduct improves safe task completion across four LLM backbones, outperforming the strongest evolution baseline by 5--15 percentage points. Experiments in ScienceWorld and DiscoveryWorld further show that abductive harness evolution carries over to scientific environments. Our code is available at https://github.com/HKUST-KnowComp/E-LEDGER-WorldAbduct. This Full Reading presents the paper's text as an audio edition. Authors: Yisen Gao, Yue Guo, Qing Zong, Yiwen Guo, Yangqiu Song Abstract source: DOI metadata Published in: arXiv Publication date: 2026-10-08 Read the paper Narration: Read verbatim by an AI-generated voice. The authors and publisher do not sponsor or endorse this recording. Brief episode

  3. 4d ago

    Evaluating Local Language Model Agents for Reproducible Data Engineering: An Empirical Software Engineering Study of Mobility Workflows — García-Carrasco et al. (2026)

    Context: Large language model (LLM) agents are increasingly used as software and data-engineering assistants, yet evidence about locally deployable open-weight agents remains limited. Existing evaluations often emphasize textual responses or isolated code generation rather than the validity of complete engineering artifacts. Objectives: We evaluate whether local LLM agents can produce correct and reproducible data-engineering artifacts, quantify the effect of a closed-loop workspace condition, and examine trade-offs in model scale, architecture, quantization, runtime, tool use, and failure. Methods: We introduce a benchmark of fifteen mobility-workflow tasks covering data discovery, connectors, transport-feed processing, semantic enrichment, feature engineering, validation, visualization, and reporting. Deterministic checkers assess generated scripts, tables, structured files, figures, and reports. Ten local configurations are evaluated in one-shot and closed-loop conditions, with five repetitions per model, mode, and task, yielding 1,500 scored attempts on a consumer-grade GPU. Results: Among models larger than two billion parameters, the workspace condition increases pass rates by 26.7-52.0 percentage points over one-shot generation. The strongest configuration reaches 85.3% artifact-level success, and a quantized 9-billion-parameter model reaches 69.3% with an approximately 6.5 GB memory footprint. Gains are largest when intermediate artifacts expose errors the agent can inspect and repair. Conclusion: Local open-weight agents can support a meaningful subset of software-intensive data-engineering work, but reliability depends on model capability, task verifiability, and deterministic validation. The benchmark provides a reproducible method for evaluating complete agent configurations before adoption in engineering workflows. This Full Reading presents the paper's text as an audio edition. Authors: Jorge García-Carrasco, Javier Sanchis, Alejandro Reina-Reina, Alejandro Maté, Juan Trujillo Abstract source: DOI metadata Published in: arXiv Publication date: 2026-10-08 Read the paper Narration: Read verbatim by an AI-generated voice. The authors and publisher do not sponsor or endorse this recording. Brief episode

  4. 5d ago

    Agentic Agile-V: From Vibe Coding to Verified Engineering in Software and Hardware Development — Koch (2026)

    Agentic AI coding systems can inspect repositories, plan implementation steps, edit files, call tools, run tests, and submit pull requests. These capabilities make software and hardware development faster in some settings, but current evidence does not support the simple claim that autonomous code generation automatically improves engineering outcomes. Controlled studies report productivity gains in some enterprise tasks, slowdowns in mature open-source work, moderate but heterogeneous meta-analytic effects, and persistent failures in repository setup, dependency handling, permission gating, and hardware verification. This paper argues that the central problem is no longer prompt engineering; it is engineering process control. It synthesizes evidence from agentic software engineering, GitHub-scale adoption studies, repository-level agent configuration, productivity trials, issue-resolution benchmarks, and hardware/RTL verification research. It proposes Agentic Agile-V, a process framework that uses Agile-V as the lifecycle backbone and a task-level SCOPE-V loop - Specify, Constrain, Orchestrate, Prove, Evolve, and Verify - to convert conversational intent into structured engineering artifacts and acceptance evidence. The paper contributes: (i) a taxonomy of minimum input artifacts for agentic software, firmware, and hardware work; (ii) a conversation-to-contract gate that separates exploratory dialogue from implementation; (iii) risk-adaptive feature, bug-fix, testing, and hardware workflows; and (iv) an evidence-bundle acceptance model for agent-generated artifacts. The paper concludes that agentic AI does not eliminate engineering discipline; it increases the value of requirements, constraints, traceability, independent verification, and human approval. This Full Reading presents the paper's text as an audio edition. Abstract source: doi-metadata Authors: Christopher Koch Published in: arXiv Publication date: 2026-05-19 Read the paper Narration: Read verbatim by an AI-generated voice. The authors and publisher do not sponsor or endorse this recording. Brief episode

  5. Oct 9

    Living guidelines on the responsible use of generative AI in research — European Commission (2026)

    This Full Reading presents the paper's text as an audio edition. Abstract source: unavailable Authors: European Commission, Directorate-General for Research and Innovation Literature type: Report Peer review: Not stated in supplied metadata Publication date: 2026-05 Read the report Source license: Creative Commons Attribution 4.0 International Narration: Read verbatim by an AI-generated voice. The authors and publisher do not sponsor or endorse this recording.

  6. Oct 9

    Symbolic Separation: Grounding Deep Agents in Knowledge Graphs for Trustworthy Operational Data Analytics — Davletiyarov et al. (2026)

    Generative AI promises natural language access to the massive numerical telemetry of data centers and Industry 4.0 installations, yet text-to-query and tool-using agents stay unreliable: even frontier models answer little more than half of real-world database questions, and far fewer of the multi-step, operational ones, because the LLM must compose how heterogeneous sources relate and hallucinates the relations, not just the fields. We propose symbolic separation: a deep agent reasons freely but may act on data only through an ontology-constrained Virtual Knowledge Graph with deterministic pre-execution validation. Unlike a tool API's interface contract, this domain-semantic contract turns a complex question into one validated graph traversal instead of LLM-inferred joins. Instantiated as the Neurosymbolic Deep Analyst and evaluated on 49.9 TB of superconputer telemetry against a rigid workflow and a non-symbolic ablation, it raises end-to-end task success from 43% to 86%, prevents silent data-integrity errors that no syntactic check catches, and cuts token cost by 2.4x, letting a smaller on-premise model outperform a larger one. This Full Reading presents the paper's text as an audio edition. Abstract source: doi-metadata Authors: Baibek Davletiyarov, Junaid Ahmed Khan, Andrea Bartolini Published in: arXiv Publication date: 2026-09-15 Read the paper Source license: Creative Commons Attribution 4.0 International Narration: Read verbatim by an AI-generated voice. The authors and publisher do not sponsor or endorse this recording. Brief episode

  7. Oct 9

    Intelligent Agents For Enterprise Knowledge Management-Construction And Application Based On Large Language Models — Tian et al. (2026)

    This Full Reading presents the paper's text as an audio edition. Abstract source: unavailable Authors: S. Tian, H. Li, Y. Chen Publication date: 2026 Read the paper Source license: Creative Commons Attribution 4.0 International Narration: Read verbatim by an AI-generated voice. The authors and publisher do not sponsor or endorse this recording.

  8. Oct 9

    From AI Adoption to AI Transformation: The AX-5R Framework for Socio-Technical Work System Redesign — Shin et al. (2026)

    Generative artificial intelligence (AI) has diffused rapidly, yet adoption has not reliably progressed to AI transformation (AX). Firms grant tool access but fail to redesign workflows, clarify accountability, govern risks, or measure value. The gap is a socio-technical systems problem, not a productivity problem: AI tools are inserted into existing routines without redesigning task interdependencies, decision rights, oversight loops, or performance feedback. This paper develops AX-5R, a socio-technical systems architecture that converts fragmented AI use into accountable, governable, and measurable work systems. Synthesizing seven literature streams, it maps failure modes to five interdependent design functions: readiness, redesign, role, risk, and return. AX-5R treats transformation as joint optimization of technical and social subsystems requiring configurational alignment. A supplementary ablation probe generated 252 artifacts across three workflows and seven prompt arms from two language models, scored by blinded cross-provider judges; the full frame outscored a sham five-part control and its four artifact-relevant ablations, significant under two-sided Holm-corrected testing, with an independent human-expert-rating check. With a failure-mode derivation matrix, implementation artifacts, and six testable propositions, the framework specifies a minimum architecture in which readiness sets boundaries, redesign restructures tasks, role assigns accountability, risk establishes control, and return supplies learning feedback. This Full Reading presents the paper's text as an audio edition. Abstract source: doi-metadata Authors: K.S. Shin, I.S. Kang, M. Lee Publication date: 2026 Read the paper Source license: Creative Commons Attribution 4.0 International Narration: Read verbatim by an AI-generated voice. The authors and publisher do not sponsor or endorse this recording. Brief episode

See All (207)

About

Listen to the latest research on how organizations adopt AI, reshape work, and govern its use. Full papers, read verbatim (by AI).

Information

  • Creator
    Frontkom
  • Years Active
    2026
  • Episodes
    207
  • Rating
    Clean
  • Copyright
    © Frontkom
  • Show Website
    1 More Paper