RegulaTutor: A Theory-Informed Framework for Long-Term Personalized Learning

Yonggang Li; Boqian Han; Rui Sheng; Yushi Sun; Zixin Chen

cs.AIOct 9, 2026

RegulaTutor: A Theory-Informed Framework for Long-Term Personalized Learning

Authors: Yonggang Li, Boqian Han, Rui Sheng, Yushi Sun, Zixin Chen

Organizations: The Hong Kong University of Science and Technology · The Chinese University of Hong Kong

Abstract

Long-term personalized tutoring requires language models to translate a learner's evolving history into appropriate instructional support. Existing LLM-based tutoring systems use memory and retrieval to personalize responses, but the pedagogical rationale linking historical evidence to teaching strategies is not always explicit. We introduce RegulaTutor, a theory-informed framework for long-term personalized tutoring that connects historical evidence, learner interpretation, and learner-facing instruction. Guided by self-regulated learning (SRL) research, its tutoring harness operationalizes a cognitive, affective, metacognitive, and motivational (CAMM) framework for deriving evidence-supported learner interpretations and teaching policies. The resulting policies retain links to their supporting evidence and are updated as new observations arrive. This staged workflow also supports systematic refinement through PairRoute, an offline procedure that uses intermediate execution records to distinguish harness, model, and mixed failures. PairRoute proposes and evaluates targeted harness revisions, then constructs reviewed stage-level supervision for confirmed model failures remaining under the selected harness. We focus this refinement on historical evidence acquisition, which underpins personalized instruction and allows outputs to be checked against learning records and reference answers. RegulaTutor improves historical-evidence accuracy, learner diagnosis, and judged teaching quality on average across evaluated model configurations. PairRoute results show an endpoint improvement in standalone-model historical-evidence accuracy over the refinement trajectory. Together, these results highlight RegulaTutor's potential to support lifelong personalized education through instructional policies that evolve with learner histories and targeted improvements to the tutoring system.

Figures & tables

Figure 1: RegulaTutor connecting learner history to instructional decisions. The learner–tutor setting (left) motivates three questions (top): which records are relevant, what interpretations they support, and how those interpretations should guide teaching. RegulaTutor makes these connections explicit through CAMM-guided learner interpretation and evidence-linked teaching policies, with learner history and policies updated as new observations arrive. PairRoute (bottom) uses execution traces to guide offline harness revisions and construct reviewed stage-level supervision for residual model errors.

Figure 2: RegulaTutor adapts at two timescales. During tutoring, accumulated learner history supports evidence acquisition, CAMM-guided interpretation, and learner-specific instructional policies that update with new interactions. Offline, PairRoute attributes execution failures to the harness, model, or both and routes them to targeted harness revision or reviewed model supervision. The updated model–harness pair is evaluated before the next round or deployment.

Local Qwen checkpoints ( $n=4$ )
Model / system	Method	Evidence	Diagnosis	Teaching
Qwen3.5-4B ( $M_{0}$ )	Model only	20.0	29.7	2.63
	RegulaTutor	56.2 ∗ $\,(\uparrow 36.2)$	50.8 ∗ $\,(\uparrow 21.1)$	2.76 $\,(\uparrow 0.13)$
Qwen3.5-4B ( $M_{1}$ )	Model only	21.2	31.3	2.67
	RegulaTutor	56.4 ∗ $\,(\uparrow 35.2)$	49.6 ∗ $\,(\uparrow 18.3)$	2.73 $\,(\uparrow 0.06)$
Qwen3.5-4B ( $M_{2}$ )	Model only	27.9	28.0	2.79

Table 1: LongTutor Human Gold1000 (199-record histories). RegulaTutor uses final harness

H_{1}

. Green arrows show gains over model-only inference; mean rows average gains within each group. Evidence and Diagnosis gains are percentage points; Teaching gains are score points. Bold marks each model’s best score; ∗ marks a positive gain with a paired 95% interval excluding zero. Codex uses GPT-5.6-sol; † marks the backbone also used as Teaching judge.

Variant	Evidence	Diagnosis	Teaching
Full RegulaTutor	37.6	44.9	3.340
Without CAMM interpretation	35.6 (-2.0)	44.8 (-0.1)	3.176 (-0.164)
Static policy	36.1 (-1.5)	44.8 (-0.1)	3.196 (-0.144)
Without compiled directives	43.3 (+5.7)	44.2 (-0.7)	3.228 (-0.112)

Table 2: Component ablations in the completed LongTutor ablation batch. The within-batch reference scores are 37.6 Evidence, 44.9 Diagnosis, and 3.340 Teaching; absolute scores are not merged with the main

H_{1}

run because the batch configuration differs. Parentheses report the ablated variant minus the reference.

Pair	Model update	Evidence	Evidence (%)	Diagnosis	Teaching
$M_{0}H_{0}$	Initial model and harness	208/300	69.3	43	2.690
$M_{0}H_{1}$	Initial model, selected harness	212/300	70.7	40	2.955
$M_{1}H_{1}$	PairRoute SFT, round 1	230/300	76.7	50	3.055
$M_{2}H_{1}$	PairRoute SFT, round 2	234/300	78.0	50	2.965
$M_{3}H_{1}$	PairRoute SFT, round 3	250/300	83.3	48	2.935

Table 3: PairRoute trajectory on the repeatedly used dev100 set.

M_{0}H_{0}

is the initial pair; the model-training series uses the selected harness, with

H_{2}=H_{3}=H_{1}

. Evidence is correct answers among 300 queries; Diagnosis is accuracy (%); Teaching is the four-dimension mean. Bold indicates the highest value in each column.

Model checkpoint	Model only			$H_{0}$			$H_{1}$
	E	D	T	E	D	T	E	D	T
$M_{0}$ (pretrained)	20.0	29.7	2.631	59.5	51.6	2.752	56.2	50.8	2.763
$M_{1}$ (round 1)	21.2	31.3	2.671	67.3	52.7	2.721	56.4	49.6	2.731
$M_{2}$ (round 2)	27.9	28.0	2.793	49.3	52.1	2.715	43.9	51.6	2.721
$M_{3}$ (round 3)	28.2	27.2	2.789	59.9	52.0	2.774	43.7	51.3	2.733

Table 4: LongTutor Gold1000 results for Qwen3.5-4B checkpoints crossed with inference conditions.

M_{0}

is the pretrained model;

M_{1}

–

M_{3}

follow successive PairRoute stage-supervised training rounds.

H_{0}

is the initial harness and

H_{1}

the final RegulaTutor harness. E and D are Evidence and Diagnosis accuracy (%); T is judged Teaching (1–5). Bold is reserved for the highest values supporting the positive results discussed in the main text.

Appendix figures & tables14 assets

Supplementary material from the paper’s appendix.

Appendix

Setting	Value
Bounded history / recent-history window	10,000 / 10 events
Initial retrieval / ERL evidence top- $k$	8 / 48
Mapper chunk size	40 events
Maximum ERL rounds	2
Internal output limit / temperature	12,000 tokens / 0
CAMM interpretation / evidence admission	Deterministic / ERL-cited events

Appendix

Table 5: Core runtime settings. History and retrieval budgets count events; output limits count tokens per model call.

Observed evidence	Instructional support	Inference boundary
Repeated errors on a concept	Stepwise explanation and a focused check, grounded in a prior attempt	Local difficulty does not imply global inability or low motivation
Supported prior success	Concise explanation and retrieval practice	Prior accuracy does not establish general mastery
Explicit strategy, reflection, confidence, or self-check signal	Strategy comparison and self-checking	An observed action does not establish a stable metacognitive trait
Explicit motivational or affective self-report	Acknowledge the signal and adapt support to its context	Incorrect answers alone do not establish motivation or emotion

Appendix

Table 6: CAMM links between learner evidence and instructional support. Rules apply only to admitted observations; absence of a signal does not establish a learner trait.

Disposition	Criterion and action
Harness	Evidence access or the call interface is defective; propose a harness repair.
Model	Evidence and instructions are sufficient, but execution is incorrect; review a correction target.
Mixed	Both defects occur; repair the interface before reassessing model supervision.
Success	The task meets its evaluation criterion; independently review stages for retention.
External	A source, reference, or evaluation problem prevents a clean correction target.
Defer	Attribution remains uncertain; withhold the case from confirmed corrections.

Appendix

Table 7: Routing decisions based on the evidence visible to the implicated model call.

Panel of Figure 3 — Figure 3: A PairRoute round. Harness selection precedes the construction of model supervision. Trajectories may be reused when the selected model–harness pair is unchanged.

Update	Cases	Corrections	Retention	Total	Learning rate
$M_{0}\rightarrow M_{1}$	256	264	137	401	$2\times 10^{-5}$
$M_{1}\rightarrow M_{2}$	121	87	70	157	$10^{-5}$
$M_{2}\rightarrow M_{3}$	111	60	60	120	$10^{-5}$

Appendix

Table 8: Training data and model updates. Corrections and retention count unique stage examples; each corpus has equal IE/MR/HC supervised-token mass.

Set	Cases/tasks	Purpose
Discovery	369	Harness failure diagnosis, targeted candidate checks, and stage supervision
Probe	32	Harness candidate screening
Development	100	Adaptive assessment of model–harness updates
LongTutor Gold1000	1,000	System, harness, and model–harness pair evaluation
TeachArena dialogue	114	Situated multi-turn tutoring
TeachArena workflows	136	Tool-mediated Canvas tasks

Appendix

Table 9: Data used for refinement and evaluation. The three LongTutor adaptation sets are pairwise disjoint and have no overlap with Human Gold1000 in case, learner, or complete-history identity.

System	Recorded coverage	Configuration boundary
Direct inference	LT: nine model/checkpoint settings; TA-D/TA-W: three backbones	Public inputs and benchmark agent contract
DeepTutor	LT: deepseek-v4-pro only	Real v1.5.1 chat engine; task-local sessions
Native Codex	LT: GPT-5.6-sol agent condition	Own agent runtime and execution budget
RegulaTutor $H_{0}$	LT: $M_{0}$ – $M_{3}$ and deepseek-v4-pro	Frozen initial harness, distinct from direct inference
RegulaTutor $H_{1}$	LT: nine settings; TA-D/TA-W: three backbones	Final PairRoute-refined harness; later $H_{2},H_{3}$ retain it

Appendix

Table 10: System configurations and recorded evaluation coverage. LT denotes LongTutor; TA-D and TA-W denote TeachArena dialogue and workflow tasks.

Variant	Intervention	What the contrast measures
Without CAMM pathway	Disable interpretation and its downstream policy/directive pathway; retain evidence inputs and static support	Combined contribution of the CAMM-conditioned pathway, not the compiler alone
Static policy	Keep CAMM and its direct implications but fix policy fields to their default values	Contribution of adaptive policy-field selection beyond direct CAMM implications
Without compiled directives	Keep internal interpretation/policy computation but remove compiled directives from the final prompt; freeze other field exposure	Contribution of explicit instruction compilation under the recorded exposure policy

Appendix

Table 11: Component interventions for testing the evidence-to-instruction pathway. The completed score table is reported in Table 2 .

Checkpoint	Interface	Evidence	Diagnosis	Teaching
G1	Direct	30.9	31.6	2.768
G2	Direct	30.1	28.0	2.758
G1	RegulaTutor $H_{1}$	47.2	49.0	2.917
G2	RegulaTutor $H_{1}$	64.6	48.3	2.884
G1 $\rightarrow$ G2 under $H_{1}$		+17.3	$-0.7$	$-0.034$

Appendix

Table 12: GRPO training-path probe on LongTutor Gold1000. The same checkpoints are evaluated with direct inference and with the final

H_{1}

harness. Parentheses report the paired change from G1 to G2; Evidence and Diagnosis are percentages, and Teaching is on a 1–5 scale.

Backbone	Response mode	Reward	Scored cases
Qwen3.5-4B	Strict schema	.282	130/136
	JSON object	.001	2/136
DeepSeek-v4-pro	Strict schema	.430	101/136
	JSON object	.531	127/136
Gemini-3.7-flash	Strict schema	$\approx.000$	—
	JSON object	.554	120/136

Appendix

Table 13: TeachArena workflow response-mode controls within

H_{1}

. Reward uses all 136 tasks; scored cases reached evaluation. The dash denotes an unavailable count, not zero.

Backbone	Evidence $\Delta$ [95% CI]	Diagnosis $\Delta$ [95% CI]	Teaching $\Delta$ [95% CI]
Qwen $M_{0}$	+36.17 [34.1, 38.2]	+21.10 [17.2, 24.9]	+.132 [.064, .200]
Qwen $M_{1}$	+35.23 [33.1, 37.2]	+18.30 [14.1, 22.3]	+.060 [–.006, .127]
Qwen $M_{2}$	+16.00 [13.9, 18.1]	+23.60 [19.3, 27.9]	–.072 [–.138, –.006]
Qwen $M_{3}$	+15.50 [13.4, 17.6]	+24.10 [19.9, 28.2]	–.057 [–.124, .012]
DeepSeek-v4-pro	+10.87 [8.7, 13.0]	+.90 [–2.1, 3.8]	+.220 [.172, .268]
Gemini-3.7-flash	+18.23 [16.6, 20.0]	–7.90 [–11.7, –4.1]	+.506 [.458, .553]

Appendix

Table 14: Paired effects of the final RegulaTutor harness

H_{1}

relative to Direct on LongTutor. Evidence and Diagnosis differences are percentage points; Teaching differences use the 1–5 scale. Every interval uses 3,000 paired case-bootstrap resamples over the same 1,000 cases. † marks the evaluator backbone, excluded from across-backbone averages.

Backbone	IE $\Delta$ [95% CI]	MR $\Delta$ [95% CI]	HC $\Delta$ [95% CI]
Qwen $M_{0}$	+43.2 [39.4, 47.0]	+17.9 [14.9, 20.8]	+47.4 [44.1, 50.7]
Qwen $M_{1}$	+39.7 [35.8, 43.6]	+18.3 [15.3, 21.4]	+47.7 [44.6, 51.0]
Qwen $M_{2}$	+2.5 [–1.5, 6.5]	+1.1 [–1.6, 3.8]	+44.4 [41.1, 47.7]
Qwen $M_{3}$	+3.1 [–.8, 7.2]	+1.9 [–1.0, 4.7]	+41.5 [38.1, 44.7]
DeepSeek-v4-pro	–33.4 [–37.5, –29.2]	+23.6 [19.8, 27.2]	+42.4 [39.3, 45.5]
Gemini-3.7-flash	+25.0 [22.1, 27.9]	+25.3 [22.0, 28.5]	+4.4 [2.2, 6.6]

Appendix

Table 15: Per-query Evidence differences for final RegulaTutor

H_{1}

relative to Direct. Values are percentage points with 95% paired bootstrap intervals over 1,000 cases. IE, MR, and HC denote information extraction, multi-session reasoning, and hallucination control. † marks the evaluator backbone.

Task	Backbone	Direct	$H_{1}$	$n$	$\Delta$	95% CI	W/L/T
Dialogue	Qwen3.5-4B	.572	.587	106	+.015	[–.003,.034]	36/24/46
	DeepSeek-v4-pro	.672	.621	107	–.010	[–.024,.002]	22/29/56
	Gemini-3.7-flash	.666	.641	111	–.007	[–.021,.006]	23/28/60
Workflows	Qwen3.5-4B	.547	.282	122	–.290	[–.362,–.217]	18/87/17
	DeepSeek-v4-pro	.682	.531	127	–.129	[–.201,–.061]	30/59/38
	Gemini-3.7-flash	.646	.554	120	–.011	[–.072,.051]	29/43/48

Appendix

Table 16: TeachArena results. Full means assign zero to failed executions. Paired means and confidence intervals use task identifiers completed by both Direct and

H_{1}

. W/L/T gives

H_{1}

wins, losses, and ties.

Comparison	Evidence $\Delta$ [95% CI]	Diagnosis $\Delta$ [95% CI]	Teaching $\Delta$ [95% CI]
$M_{0}$ : $H_{1}-H_{0}$	$-3.37\;[-5.30,-1.50]$	$-0.80\;[-2.90,1.20]$	$+0.011\;[-0.035,0.061]$
$M_{1}$ : $H_{1}-H_{0}$	$-10.83\;[-12.60,-9.10]$	$-3.10\;[-5.10,-1.20]$	$+0.010\;[-0.041,0.061]$
$M_{2}$ : $H_{1}-H_{0}$	$-5.40\;[-7.30,-3.40]$	$-0.50\;[-2.30,1.30]$	$+0.006\;[-0.045,0.061]$
$M_{3}$ : $H_{1}-H_{0}$	$-16.20\;[-18.20,-14.30]$	$-0.70\;[-2.40,0.90]$	$-0.041\;[-0.094,0.011]$
DeepSeek: $H_{1}-H_{0}$	$+1.97\;[-0.10,4.10]$	$+4.60\;[1.60,7.70]$	$-0.010\;[-0.067,0.050]$

Appendix

Table 17: Harness compatibility on the same 1,000 cases. Differences are

H_{1}-H_{0}

; Evidence and Diagnosis use percentage points. Teaching uses score units. Intervals are unadjusted paired case-bootstrap intervals.

Self-Regulated Learning

See all 8 papers

Apr 10, 2026

DeepTutor: Towards Agentic Personalized Tutoring

Education is one of the most promising real-world applications for Large Language Models (LLMs). However, current LLMs rely on static pre-training knowledge and lack adaptation to individual learners, while existing RAG systems fall short in delivering personalized, guided feedback. To bridge this gap, we present DeepTutor, a fully open-source agentic framework that unifies citation-grounded problem tutoring with difficulty-calibrated question generation. A hybrid personalization engine couples static knowledge grounding with dynamic learner memory, continuously adapting each interaction to the student's evolving needs. The same personalization substrate further extends to adaptive learning workflows, interactive books, and proactive multi-channel tutoring agents. To evaluate personalized tutoring, we introduce TutorBench, an interactive benchmark incorporating customized learner profiles grounded in university-level curricula across five domains. We further propose an LLM-based first-person interactive evaluation protocol that conducts assessments via a profile-driven student simulator. Complementary evaluations on established benchmarks, supported by human-alignment and ablation studies, confirm the framework's robustness and general utility. Results show that DeepTutor improves personalized metrics by 10.8% on average and strengthens general agentic reasoning across five backbone models by 29.4%.

Bingxi Zhao, Jiahao Zhang, Xubin Ren +4

The University of Hong Kong

LLM Personalization Intelligent Tutoring Systems User Modeling Memory-Augmented Language Model Agents

Ask PDF

Sep 17, 2026

CoLearn: An Agentic Tutor that Learns its Learner in a Human--AI Co-Learning Loop

Good tutoring adapts to the individual: it tracks what a learner knows, notices why they go wrong, and asks the next question that will help most. Most deployed tutoring tools instead serve fixed item banks and treat a wrong answer as a single bit of signal. We present CoLearn, an interactive, agentic tutor that supports an iterative tutoring loop: the learner practises, and the system builds an evidence-grounded memory of the learner's mastery and misconceptions. This memory is updated as evidence accumulates and is used to generate the next personalised question. CoLearn has three components: (i) a persistent learner-state memory that updates per-topic mastery with a soft-evidence variant of Bayesian Knowledge Tracing, where a large language model acts as a continuous observation function; (ii) adaptive question generation that targets the learner's weakest topic and recurring misconceptions; and (iii) an evidence view that makes personalisation visible and testable through live progress visualisation and blind A/B comparison. In blind A/B evaluation, questions conditioned on this memory are preferred over non-personalised ones 68-69% of the time, and in persona simulations with hidden ground-truth mastery the agent's belief converges toward the learner's true mastery.

Kailai He, Zhihao Wu, Linhai Zhang +3

King’s College London

Intelligent Tutoring Systems Adaptive Learning

Ask PDF

May 28, 2026

PEARL: Training Socratic Tutors with Pedagogically Aligned Reinforcement Learning

Large Language Models (LLMs) show strong potential as educational tutors. Existing approaches typically train them to solve problems and provide correct answers, but this problem-solving-centered paradigm overlooks key requirements of effective tutoring: progressive guidance and the coordination of multiple pedagogical objectives across multi-turn interactions. Developing such tutors remains challenging because student behavior varies substantially with individual knowledge states, pedagogical effectiveness depends on multiple factors beyond final-answer correctness, and coordinating these objectives over tutor-student interactions is inherently difficult. To address these challenges, we propose PEARL, a PEdagogically Aligned Reinforcement Learning framework for training Socratic tutoring agents. First, we introduce a controllable student simulator that disentangles latent cognitive states from response generation, enabling simulation of diverse abilities and misconceptions. Second, we develop a pedagogically aligned reward model that jointly assesses pedagogical quality and objective correctness. Finally, we propose a stable multi-objective reinforcement learning approach that balances competing pedagogical objectives during tutor training. Experiments across multiple benchmarks show that PEARL performs competitively against tutoring-specific open-source systems and leading proprietary LLMs.

Qikai Chang, Zhenrong Zhang, Linbo Chen +4

University of Science and Technology of China · iFLYTEK Research

Multi-Objective Reinforcement Learning Intelligent Tutoring Systems Socratic Tutoring RL for LLM Agents

Ask PDF

Abstract

Self-Regulated Learning

Explore similar work

DeepTutor: Towards Agentic Personalized Tutoring

CoLearn: An Agentic Tutor that Learns its Learner in a Human--AI Co-Learning Loop

PEARL: Training Socratic Tutors with Pedagogically Aligned Reinforcement Learning