RecSys Factory: Bounding LLM Agent Autonomy to Decision Points in the Industrial Recommender Lifecycle

• URL: http://arxiv.org/abs/2608.11241v1
• Date: Fri, 31 Jul 2026 15:42:45 GMT
• Title: RecSys Factory: Bounding LLM Agent Autonomy to Decision Points in the Industrial Recommender Lifecycle
• Abstract summary: We present RecSys Factory, an LLM-agent platform deployed for 78 days across three recommender business lines.<n>The design principle is autonomy at decision points, not over generalizations.<n>Across the 78-day window the platform recorded 1,624 CLI-tool dispatches at a 78.6% aggregate success rate.
• Score: 2.424372451932308
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deploying LLM agents into industrial recommender operations exposes a three-way tension we frame as the autonomy-determinism-efficiency trilemma: general autonomy (interpreting operator intent, generating glue code zero-shot), industrial determinism (schema-conforming feature extraction, non-crashing A/B, zero compliance-path hallucination), and end-to-end efficiency. Any two can be maximized against the third. We present RecSys Factory, an LLM-agent platform deployed for 78 days across three heterogeneous Tencent recommender business lines. The design principle is autonomy at decision points, not over pipelines, made concrete through three deconstructions that each discharge one vertex of the trilemma. Runtime is deconstructed into three host-emitted event sources (Claude Code Stop hooks, corporate-IM webhooks, workflow scheduler APIs): the platform carries no long-running daemon during the wait phase and consumes zero CPU during the 94% of wall-clock spent waiting on Spark or GPU jobs. Capability is deconstructed into a 29-file skill ecosystem (8,971 lines of SKILL.md) whose per-skill pitfall tables mechanically compile into a 400-entry PitfallStore, confining autonomy to bounded typed decision surfaces inside pre-committed pipelines. Deployment spans three business lines with disjoint label semantics, A/B layer topologies, and operator personas; an onboarding-time compression is observed on two of the three and is reported as a case-study observation, not a generalization claim, and not measured against a controlled pre-platform baseline. The human is retained at the diagnostic-versus-execution boundary via a human-in-the-loop card protocol, deployed as an audit-trail primitive (schema-validated, idempotent, replayable) and reported from an 8-day 16-run pilot. Across the 78-day window the platform recorded 1,624 CLI-tool dispatches at a 78.6% aggregate success rate.

Related papers

• SENTINEL-RL: Offloading Topological Reasoning from LLM Agents in the Security Operations Center [0.0]
  Sentinel-RL is an agentic-SOC architecture that decouples topological reasoning from semantic reasoning.<n>We instantiate the system on the LANL Comprehensive, Multi-Source Cyber-Security Events dataset and the Indiana University Quartz HPC cluster.
  arXiv  Detail & Related papers  (2026-09-03T17:49:12Z)
• From Production Traffic to Post-Training: Building a Self-Hosted LLM That Covers the Corporate Request Mix [55.08143827481755]
  We consolidate traffic from over 200 internal applications onto a single model.<n>We train a separate GRPO expert per axis and merge them via two-stage SLERP.<n>The model absorbs 50% of platform traffic, 116M requests per month, at a fraction of the serving cost.
  arXiv  Detail & Related papers  (2026-09-01T17:39:26Z)
• Memory as Infrastructure: Reliability Engineering for Persistent Agent Memory in Months-Long LLM-Assisted Development [0.0]
  We report on a research project under a single continuous Claude Code session line since January 2026.<n>We describe SIx Harness, the open-source memory continuity infrastructure.<n>We present what we believe is the first months-scale instrumented operational record of a persistent agent-memory subsystem.
  arXiv  Detail & Related papers  (2026-08-31T03:28:35Z)
• DREAM Technical Report [53.37525197047151]
  We present DREAM, an autonomous optimization control architecture that adds a perception-aware, orchestrable, and auditable policy layer atop existing pipelines without replacing them.<n> DREAM has two core components. First, a three-tier Intent Engine fuses on-device signals into structured L0/L1/L2 intent representations; its edge-cloud trigger chain reduces reporting volume to approximately 8.7%.<n>Second, a Meta Engine uses a MetaModel for layered M1-to-M2-to-M3 reasoning: intent summarization, strategy planning informed by Strategy Memory, and parameter translation. It dispatches the resulting parameters through a unified outlet with
  arXiv  Detail & Related papers  (2026-08-10T10:35:32Z)
• Agentic Coding in the Wild: Characterizing GitHub Copilot Traces at Production Scale [6.287658270510339]
  AI coding agents like GitHub Copilot, Claude Code, and Codex interleave multi-step LLM inference with tool execution.<n>We present the first production-scale characterization of this workload using sampled GitHub Copilot traces from June 2026.
  arXiv  Detail & Related papers  (2026-07-30T20:51:51Z)
• Stop Means Stop: Measuring and Repairing the Enforcement Gap in Agent-Framework Control Primitives [0.0]
  This contract holds on none of six widely used open-source frameworks.<n>Model-free differential probes isolate a recurring sibling leak.<n>SoundGATE is an environment-external Rust gate through which every side effect must be admitted.
  arXiv  Detail & Related papers  (2026-07-15T05:55:38Z)
• Time-Lag-Aware Deep Reinforcement Learning for Flexible Job-Shop Scheduling in PPVC Module Factories [13.958047178810189]
  long post-operation time-lags caused by concrete curing, watertightness ponding tests, and paint drying.<n>We adapt a state-of-the-art dual-attention deep reinforcement learning solver through three minimally invasive, individually ablatable extensions.<n>On held-out instances the learned policy is the strongest solver-free scheduler.
  arXiv  Detail & Related papers  (2026-07-13T15:50:00Z)
• LocalNav: Distilling Frontier VLMs and Embodied RL for On-Device Object Goal Navigation [53.88286427894783]
  Vision Language Models (VLMs) have emerged in the robotic domain as a powerful tool that enables environmental perception with language context.<n>Yet, their computational footprint typically confines them to cloud execution, hindering low-latency inference with local deployment on resource-constrained robots.<n>We present a distillation strategy that transfers complex spatial-semantic reasoning from large frontier models into a lightweight, 4B- parameter local VLM for edge execution on embedded GPU devices.
  arXiv  Detail & Related papers  (2026-06-26T09:11:59Z)
• WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation [88.10947115397971]
  This work presents WildClawBench, a native-runtime benchmark of 60 human-authored, bilingual, multimodal tasks spanning six thematic categories.<n>Each task averages roughly 8 minutes of wall-clock time and over 20 tool calls.<n> Grading is hybrid, combining deterministic rule-based checks, environment-state auditing of side effects, and an LLM/VLM judge for semantic verification.
  arXiv  Detail & Related papers  (2026-05-11T17:49:43Z)
• Rethinking AI Hardware: A Three-Layer Cognitive Architecture for Autonomous Agents [8.951500258016974]
  Tri-Spirit is a cognitive framework that decomposes intelligence into planning, reasoning, and execution.<n>It reduces mean task latency by 75.6 percent and energy consumption by 71.1 percent.<n>Results suggest that cognitive decomposition, rather than model scaling alone, is a primary driver of system-level efficiency in AI hardware.
  arXiv  Detail & Related papers  (2026-04-15T11:43:01Z)
• SpecEyes: Accelerating Agentic Multimodal LLMs via Speculative Perception and Planning [104.01865949020304]
  Agentic multimodal large language models (MLLMs) achieve remarkable reasoning capabilities through iterative visual tool invocation.<n>However, the cascaded perception, reasoning, and tool-calling loops introduce significant sequential overhead.<n>This overhead, termed agentic depth, incurs prohibitive latency and seriously limits system-level throughput.<n>We propose SpecEyes, an agentic-level speculative acceleration framework that breaks this sequential bottleneck.
  arXiv  Detail & Related papers  (2026-03-24T17:45:47Z)
• OrgForge-IT: A Verifiable Synthetic Benchmark for LLM-Based Insider Threat Detection [0.0]
  We present a verifiable synthetic benchmark in which a deterministic simulation engine maintains ground truth and language models generate only surface prose.<n>The corpus spans 51 simulated days, 2,904 telemetry records at a 96.4% noise rate, and four detection scenarios designed to defeat single-surface and single-day triage strategies.
  arXiv  Detail & Related papers  (2026-03-23T19:03:53Z)
• SOPBench: Evaluating Language Agents at Following Standard Operating Procedures and Constraints [59.645885492637845]
  SOPBench is an evaluation pipeline that transforms each service-specific SOP code program into a directed graph of executable functions.<n>Our approach transforms each service-specific SOP code program into a directed graph of executable functions and requires agents to call these functions based on natural language SOP descriptions.<n>We evaluate 18 leading models, and results show the task is challenging even for top-tier models.
  arXiv  Detail & Related papers  (2025-03-11T17:53:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.