CAPIRE Intervention Lab: An Agent-Based Policy Simulation Environment for Curriculum-Constrained Engineering Programmes

• URL: http://arxiv.org/abs/2511.18145v1
• Date: Sat, 22 Nov 2025 18:14:15 GMT
• Title: CAPIRE Intervention Lab: An Agent-Based Policy Simulation Environment for Curriculum-Constrained Engineering Programmes
• Authors: H. R. Paz,
• Abstract summary: Engineering programmes in Latin America produce dropout rates that remain stubbornly high despite increasingly accurate early-warning models.<n> Predictive learning analytics can identify students at risk, but they offer limited guidance on which concrete combinations of policies should be implemented.<n>This paper presents the CAPIRE Intervention Lab, an agent-based simulation environment designed to complement predictive models.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Engineering programmes in Latin America combine high structural rigidity, intense assessment cultures and persistent socio-economic inequality, producing dropout rates that remain stubbornly high despite increasingly accurate early-warning models. Predictive learning analytics can identify students at risk, but they offer limited guidance on which concrete combinations of policies should be implemented, when, and for whom. This paper presents the CAPIRE Intervention Lab, an agent-based simulation environment designed to complement predictive models with in silico experimentation on curriculum and teaching policies in a Civil Engineering programme. The model is calibrated on 1,343 students from 15 cohorts in a six-year programme with 34 courses and 12 simulated semesters. Agents are initialised from empirically derived trajectory archetypes and embedded in a curriculum graph with structural friction indicators, including backbone completion, blocked credits and distance to graduation. Each agent evolves under combinations of three policy dimensions: (A) curriculum and assessment structure, (B) teaching and academic support, and (C) psychosocial and financial support. A 2x2x2 factorial design with 100 replications per scenario yields over 80,000 simulated trajectories. Results show that policy bundles targeting early backbone courses and blocked credits can reduce long-term dropout by approximately three percentage points and substantially increase the number of courses passed by structurally vulnerable archetypes, while leaving highly regular students almost unaffected. The Intervention Lab thus shifts learning analytics from static prediction towards dynamic policy design, offering institutions a transparent, extensible sandbox to test curriculum and teaching reforms before large-scale implementation.

Related papers

• Compositional Planning with Jumpy World Models [70.74595987225908]
  We study agents that compose pre-trained policies as temporally extended actions, enabling solutions to complex tasks that no constituent alone can solve.<n>Motivated by the geometric policy composition framework introduced in arXiv:2206.08736, we address these challenges by learning predictive models of multi-step dynamics.
  arXiv  Detail & Related papers  (2026-02-23T09:22:21Z)
• Toward Quantitative Modeling of Cybersecurity Risks Due to AI Misuse [50.87630846876635]
  We develop nine detailed cyber risk models.<n>Each model decomposes attacks into steps using the MITRE ATT&CK framework.<n>Individual estimates are aggregated through Monte Carlo simulation.
  arXiv  Detail & Related papers  (2025-12-09T17:54:17Z)
• Quantised Academic Mobility: Network and Cluster Analysis of Degree Switching, Plan Changes, and Re-entries in an Engineering Faculty (1980-2019) [0.0]
  This study challenges the traditional binary view of student progression (retention versus dropout) by conceptualising academic trajectories as complex, quantised pathways.<n>We introduce CAPIRE, an analytical framework that differentiates between degree major switches, curriculum plan changes, and same-plan re-entries.<n>The analysis identifies six distinct student archetypes, including 'Switchers' (10.7 per cent) who reorient vocationally, and 'Stable Re-entrants' (6.9 per cent) who exhibit stop-out behaviours without changing discipline.
  arXiv  Detail & Related papers  (2025-12-04T10:26:33Z)
• When Administrative Networks Fail: Curriculum Structure, Early Performance, and the Limits of Co-enrolment Social Synchrony for Dropout Prediction in Engineering Education [0.0]
  Social integration theories suggest students embedded in supportive peer networks are less likely to drop out.<n>In learning analytics, this has motivated the use of social network analysis (SNA) from institutional co-enrolment data to predict attrition.<n>This study tests whether such administrative network features add predictive value beyond a leakage-aware, curriculum-graph-informed model.
  arXiv  Detail & Related papers  (2025-11-21T19:38:25Z)
• The Promotion Wall: Efficiency-Equity Trade-offs of Direct Promotion Regimes in Engineering Education [0.0]
  Article uses a calibrated agent-based model to examine how alternative progression regimes reconfigure dropout, time-to-degree, equity and students' psychological experience.
  arXiv  Detail & Related papers  (2025-11-21T12:04:31Z)
• An Agent-Based Simulation of Regularity-Driven Student Attrition: How Institutional Time-to-Live Constraints Create a Dropout Trap in Higher Education [0.0]
  "The Regularity Trap" is a phenomenon where rigid assessment timelines decouple learning from accreditation.<n>We operationalize the CAPIRE framework into a calibrated Agent-Based Model (ABM) simulating 1,343 student trajectories across a 42-course Civil Engineering curriculum.<n>Results reveal that 86.4% of observed dropouts are driven by normative mechanisms (expiry cascades) rather than purely academic failure.
  arXiv  Detail & Related papers  (2025-11-20T11:21:39Z)
• The CAPIRE Curriculum Graph: Structural Feature Engineering for Curriculum-Constrained Student Modelling in Higher Education [0.0]
  This paper introduces the CAPIRE Curriculum Graph, a structural feature engineering layer embedded within the CAPIRE framework for student attrition prediction.<n>We derive nine structural features at the student-semester level that capture how students navigate the prerequisite network over time.<n>These features include backbone completion rate, bottleneck approval ratio, blocked credits due to incomplete prerequisites, and graph distance to graduation.
  arXiv  Detail & Related papers  (2025-11-19T15:33:00Z)
• Provable Benefit of Curriculum in Transformer Tree-Reasoning Post-Training [76.12556589212666]
  We show that curriculum post-training avoids the exponential complexity bottleneck.<n>Under outcome-only reward signals, reinforcement learning finetuning achieves high accuracy with sample complexity.<n>We establish guarantees for test-time scaling, where curriculum-aware querying reduces both reward oracle calls and sampling cost from exponential to order.
  arXiv  Detail & Related papers  (2025-11-10T18:29:54Z)
• Agentic World Modeling for 6G: Near-Real-Time Generative State-Space Reasoning [70.56067503630486]
  We argue that sixth-generation (6G) intelligence is not fluent token prediction but calibrated the capacity to imagine and choose.<n>We show that WM-MS3M cuts mean absolute error (MAE) by 1.69% versus MS3M with 32% fewer parameters and similar latency, and achieves 35-80% lower root mean squared error (RMSE) than attention/hybrid baselines with 2.3-4.1x faster inference.
  arXiv  Detail & Related papers  (2025-11-04T17:22:22Z)
• Stabilizing Policy Gradients for Sample-Efficient Reinforcement Learning in LLM Reasoning [77.92320830700797]
  Reinforcement Learning has played a central role in enabling reasoning capabilities of Large Language Models.<n>We propose a tractable computational framework that tracks and leverages curvature information during policy updates.<n>The algorithm, Curvature-Aware Policy Optimization (CAPO), identifies samples that contribute to unstable updates and masks them out.
  arXiv  Detail & Related papers  (2025-10-01T12:29:32Z)
• Beyond classical and contemporary models: a transformative AI framework for student dropout prediction in distance learning using RAG, Prompt engineering, and Cross-modal fusion [0.4369550829556578]
  This paper introduces a transformative AI framework that redefines dropout prediction.<n>The framework achieves 89% accuracy and an F1-score of 0.88, outperforming conventional models by 7% and reducing false negatives by 21%.
  arXiv  Detail & Related papers  (2025-07-04T21:41:43Z)
• Beyond Scaling: Measuring and Predicting the Upper Bound of Knowledge Retention in Language Model Pre-Training [68.94373533768501]
  We model knowledge retention, the capacity of a pre-trained language model to memorize factual information from its corpus, and introduce a principled method to estimate it prior to training.<n>We propose Size-dependent Mutual Information (SMI), an information-theoretic predictor that integrates knowledge frequency, knowledge specificity, and model size to forecast closed-book question answering (QA) accuracy.
  arXiv  Detail & Related papers  (2025-02-06T13:23:53Z)
• Hierarchical Programmatic Reinforcement Learning via Learning to Compose Programs [58.94569213396991]
  We propose a hierarchical programmatic reinforcement learning framework to produce program policies. By learning to compose programs, our proposed framework can produce program policies that describe out-of-distributionally complex behaviors. The experimental results in the Karel domain show that our proposed framework outperforms baselines.
  arXiv  Detail & Related papers  (2023-01-30T14:50:46Z)

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.