cs.AINov 3, 2026
SaveGlucoAgent: Personalized Glucose Forecasting from Multimodal Personal Context
Organizations: Yale University · Meta Reality Labs Research
Abstract
Continuous glucose monitors, smartwatches, meal logs, and health profiles form a rich multimodal personal context that can significantly enhance glucose forecasting. However, existing methods struggle to effectively utilize these signals to improve glucose prediction because the relevance of different modalities varies drastically across individuals and time. We present GlucoAgent, an LLM-based agentic system that addresses this challenge through dynamic, case-by-case analysis at inference time. For each forecast, GlucoAgent writes and runs code over an individual's multimodal context and returns predictions with a reason and supporting evidence. The generated programs are highly diverse, ranging from retrieving similar past meals to fitting and back-testing physiological and statistical models. On CGMacros, a multimodal glucose dataset, GlucoAgent outperforms time series foundation models on every forecasting horizon, achieving an average RMSE of 22.5 mg/dL compared to 23.5 mg/dL of Chronos-2, the leading multimodal time series foundation model. Furthermore, GlucoAgent is highly effective at leveraging multimodal data. The addition of multimodal data reduces its average RMSE by 1.4 mg/dL (24.0 mg/dL to 22.5 mg/dL), compared to a marginal 0.3 mg/dL (23.8 mg/dL to 23.5 mg/dL) improvement for Chronos-2. This advantage is most pronounced in challenging post-meal windows, where GlucoAgent uses multimodal context to reduce 60-minute forecast RMSE by 4.6 mg/dL (31.0 mg/dL to 26.5 mg/dL), far exceeding the 0.8 mg/dL (31.9 mg/dL to 31.1 mg/dL) reduction achieved by Chronos-2.
Figures & tables
Figure 1: One person’s multimodal context enters GlucoAgent. The agent writes and runs code to construct a case-by-case analysis, then submits a forecast with a reason and supporting evidence. (a) Time series foundation models receive the last twelve hours of glucose and return a forecast without a reason. (b) GlucoAgent receives one person’s glucose, heart rate, activity, logged meals and health profile. (c) The agent writes and runs code over that context, reads the outputs and continues until submission. (d) It returns each forecast with a reason and supporting evidence. In this example, it combines responses to the person’s past large meals with a regression fitted and validated on that person’s history.
| Method | 30 min | 60 min | 90 min | 120 min |
|---|---|---|---|---|
| Reference | ||||
| Persistence | 20.429 (5.574) | 29.151 (11.147) | 34.646 (14.176) | 38.003 (16.954) |
| Glucose only, 12 hours of history | ||||
| TimesFM-2.5 | 17.853 (5.027) | 25.586 (10.228) | 29.495 (12.924) | 31.354 (15.047) |
| Moirai-2.0 | 18.446 (5.625) | 27.011 (10.841) | 31.587 (14.169) | 33.886 (16.853) |
| Timer † | 20.089 (6.603) | 27.342 (11.607) | 30.779 (14.495) | 31.559 (16.221) |
Table 1: Adding the multimodal context reduces GlucoAgent’s RMSE more than Chronos-2’s, and GlucoAgent has lower RMSE with the multimodal context at all four horizons. Participant-level RMSE in mg/dL, mean (standard deviation) over the nine participants. Bold marks the lowest and underlining the second lowest error within a setting ( † Timer’s input handling is described in Appendix D ).
Figure 2: The multimodal context reduces GlucoAgent’s RMSE more than Chronos-2’s. (a) Mean participant-level RMSE over the four horizons as the input expands from twelve hours of glucose to the full glucose history and then the multimodal context. (b) The RMSE reduction from the multimodal context in four forecast situations. (c) The same reduction at each forecast horizon.
Figure 3: The cited programs differ across forecast situations. Each bar shows the percentage of origins in a situation for which the cited programs read the logged meals or fit a model. The subsample contains 576 origins: 279 quiet, 91 post-meal, 97 post-exercise, and 109 meal + exercise.
Figure 4: Three case-by-case analyses constructed from personal history. Each row reconstructs one forecast from the agent’s cited programs and submitted reason. The rows show a search for similar past meals, a physiological model fitted to an ongoing rise, and three rules for continuing a falling glucose trend back-tested on earlier windows.
| Model | Effort | 30 min | 60 min | 90 min | 120 min |
|---|---|---|---|---|---|
| Claude Opus 5 (ours) | high | 16.357 (3.605) | 22.132 (8.220) | 25.163 (9.663) | 26.450 (11.333) |
| Claude Opus 5 | medium | 17.016 (3.683) | 23.746 (8.594) | 27.308 (10.659) | 28.999 (12.550) |
| Claude Sonnet 5 | high | 18.595 (4.177) | 26.613 (8.857) | 31.108 (11.528) | 34.511 (14.200) |
| Gemini 3.1 Pro | high | 18.964 (5.404) | 25.389 (10.162) | 29.277 (11.128) | 30.693 (13.674) |
| GPT-5.6-sol | high | 17.202 (4.263) | 23.300 (8.562) | 26.436 (9.079) | 27.753 (10.995) |
Table 2: Claude Opus 5 at high reasoning effort has the lowest RMSE at every horizon among the tested configurations. Participant-level RMSE in mg/dL, mean (standard deviation) over the nine participants. Bold marks the lowest and underlining the second lowest error at each horizon.
| Dataset | Persistence | Chronos-2 | Moirai-2.0 | Timer | TimesFM-2.5 | GlucoAgent |
| Hall2018 | 13.90 (7.75) | 13.27 (6.72) | 12.96 (6.94) | 14.27 (8.10) | 12.92 (6.49) | 13.59 (6.21) |
| BIG IDEAS Lab | 15.63 (4.04) | 14.21 (3.84) | 14.29 (3.97) | 15.95 (5.19) | 13.78 (3.80) | 14.51 (3.71) |
| ShanghaiT1DM | 17.64 (8.13) | 12.51 (5.27) | 11.89 (4.56) | 19.59 (9.00) | 12.06 (5.22) | 11.04 (4.75) |
| ShanghaiT2DM | 15.03 (5.02) | 11.77 (3.80) | 11.47 (3.51) | 15.40 (5.76) | 11.14 (3.66) | 11.13 (3.57) |
| HUPA-UCM | 21.58 (8.19) | 18.04 (7.57) | 17.12 (6.86) | 24.49 (7.81) | 17.35 (7.42) | 16.35 (6.69) |
| T1DM-UOM | 25.46 (6.11) | 22.01 (5.53) | 22.62 (6.08) | 24.99 (6.47) | 22.34 (5.83) | 21.24 (5.45) |
Table 3: With its configuration unchanged, GlucoAgent has the lowest RMSE on five of nine datasets and the second lowest on two. Forecasting under the GlucoFM-Bench protocol: twelve hours of glucose history, a 30-minute horizon and participant-level RMSE in mg/dL as mean (standard deviation), on at most 32 origins per participant. Bold marks the best and underlining the second best method on each dataset.
Appendix figures & tables35 assets
Supplementary material from the paper’s appendix.
Appendix
| Component | Frozen setting |
|---|---|
| Language model | Claude Opus 5 |
| Provider model identifier | us.anthropic.claude-opus-5 |
| Transport | Bedrock Converse-compatible proxy |
| Reasoning setting | High, adaptive |
| Sampling temperature and top- | Not set; provider defaults |
| Model calls per origin | at most 16 |
Table 4: Frozen runtime settings for the multimodal forecasting agent.
| Element | Definition |
|---|---|
| Inputs | The supplied context up to the cutoff, covering glucose, heart rate, activity, logged meals and the baseline profile, together with the timestamps of the meal photographs. |
| State | The accumulated messages and a case-local filesystem. Files persist across programs; each program starts a fresh interpreter. |
| Actions | Run Python code, or submit one glucose value per requested timestamp with a reason and, after any successful program, supporting evidence references. |
| Termination | The first valid submission is accepted; otherwise the episode ends when the model-call budget is exhausted. |
Table 5: Inputs, state, actions and termination condition.
| Quantity | Minimum | Median | Maximum |
|---|---|---|---|
| Pre-cutoff history (hours) | 25.5 | 132.0 | 237.1 |
| Five-minute rows | 306 | 1,584 | 2,845 |
| Logged meal events | 3 | 22 | 61 |
| Glucose coverage | 0.92 | 0.99 | 1.00 |
| Heart-rate coverage | 0.56 | 0.99 | 1.00 |
| Activity-energy coverage | 0.90 | 1.00 | 1.00 |
Table 6: Contents of the case file across the 576-origin subsample of held-out CGMacros forecasts. Coverage is the fraction of five-minute rows carrying an observation for that signal. METs are absent entirely for some participants, which is why the minimum is zero.
| Path | Access | Contents |
|---|---|---|
| /input/case.json | read-only | the single cutoff-safe case file |
| /work | read-write | private scratch, seeded with the helper modules |
| one further mount | read-only | version-locked Python 3.9.25 with NumPy, SciPy, pandas, scikit-learn and statsmodels |
| /usr , /proc , /dev , /tmp | read-only or virtual | base system runtime |
Table 7: The complete filesystem visible inside the sandbox. Our source code, the user’s home directory, the evaluation harness, the ground truth, credentials and all other forecast origins are absent.
| Tool | What it returns |
|---|---|
| read a time series | the values of chosen signals over a chosen interval, paginated |
| summarize an interval | deterministic summary statistics for chosen signals over a chosen interval |
| list events | the recorded events in a chosen interval, optionally filtered by kind, paginated |
| read the interval around an event | chosen signals for a chosen number of minutes before and after a chosen event, paginated |
| list meal photographs | metadata for the photographs available before the cutoff, optionally restricted to an interval or one event, paginated |
| attach a meal photograph | the pixels of one chosen photograph, inserted into the model’s context |
Table 8: The hand-designed interface. Every access pattern available to the agent is one of these seven calls.
| GlucoAgent | Hand-designed | |
| Data access | one read-only JSON file | six retrieval tools |
| Computation | arbitrary Python code | none beyond the tools |
| Method guidance in the instruction | none | names tools and analyses |
| Model calls per origin | at most 16 | at most 7 |
| Rounds that may call tools | at most 14 | at most 6 |
| Non-terminal calls | at most 14 Python programs | at most 24 retrieval calls |
Table 9: Differences between the two interfaces. The lower block lists what is held fixed.
| Method | 30 min | 60 min | 90 min | 120 min | Mean-4 |
|---|---|---|---|---|---|
| Hand-designed faithful port (high effort) | 17.193 (3.559) | 23.985 (8.333) | 27.186 (10.737) | 28.575 (12.852) | 24.235 (8.730) |
| Hand-designed faithful port (medium effort) | 17.897 (4.202) | 25.631 (9.483) | 28.762 (12.085) | 30.258 (14.567) | 25.637 (9.842) |
| Chronos-2 (fuller multimodal) | 17.246 (5.125) | 23.711 (9.586) | 26.052 (11.527) | 26.866 (12.887) | 23.469 (9.658) |
| GlucoAgent (agent-designed multimodal) | 16.357 (3.605) | 22.132 (8.220) | 25.163 (9.663) | 26.450 (11.333) | 22.526 (8.078) |
Table 10: Comparison with the hand-designed tool interface on 1,903 exactly matched CGMacros HOLDOUT origins. Cells report participant-level RMSE mean (sample standard deviation), in mg/dL. Mean-4 is computed per participant across the four horizons before aggregation.
| Input setting | Language model (effort) | 30 | 60 | 90 | 120 | Mean |
|---|---|---|---|---|---|---|
| Glucose only, 12 h | Claude Opus 5 (high), ours | 18.68 | 27.21 | 31.08 | 33.19 | 27.54 |
| Claude Opus 5 (medium) | 19.59 | 28.73 | 32.32 | 34.15 | 28.70 | |
| Claude Sonnet 5 (high) | 19.59 | 29.39 | 34.62 | 38.72 | 30.58 | |
| Glucose only, full history | Claude Opus 5 (high), ours | 17.42 | 24.19 | 26.58 | 27.66 | 23.96 |
| Claude Opus 5 (medium) | 18.62 | 26.24 | 29.04 | 30.33 | 26.06 | |
| Claude Sonnet 5 (high) | 19.03 | 27.12 | 31.64 | 34.36 | 28.04 |
Table 11: The same agent driven by three language models and reasoning settings. Participant-level RMSE (mg/dL) in the three input settings. Mean is over the four horizons. Bold marks the lowest error within a setting. Every row gains from the longer history, and the gain from the non-glucose signals is 1.4, 1.8 and 0.3 mg/dL on the mean for the three rows. Standard deviations are in Table 12 and two models from other families in Table 2 .
| Input setting | Model | Effort | 30 min | 60 min | 90 min | 120 min | Mean-4 |
|---|---|---|---|---|---|---|---|
| Multimodal | Claude Opus 5 (ours) | high | 16.357 (3.605) | 22.132 (8.220) | 25.163 (9.663) | 26.450 (11.333) | 22.526 (8.078) |
| Claude Opus 5 | medium | 17.016 (3.683) | 23.746 (8.594) | 27.308 (10.659) | 28.999 (12.550) | 24.267 (8.711) | |
| Claude Sonnet 5 | high | 18.595 (4.177) | 26.613 (8.857) | 31.108 (11.528) | 34.511 (14.200) | 27.707 (9.486) | |
| CGM only (full history) | Claude Opus 5 (ours) | high | 17.416 (4.930) | 24.187 (9.150) | 26.584 (10.846) | 27.661 (12.395) | 23.962 (9.199) |
| Claude Opus 5 | medium | 18.624 (4.815) | 26.240 (9.921) | 29.042 (12.744) | 30.328 (14.391) | 26.058 (10.348) | |
| Claude Sonnet 5 | high | 19.026 (5.260) | 27.124 (9.915) | 31.639 (12.622) | 34.358 (14.623) | 28.037 (10.492) |
Table 12: Claude-family ablation across matched input settings on 1,903 CGMacros HOLDOUT origins. Cells report participant-level RMSE mean (sample standard deviation), in mg/dL. Mean-4 is computed per participant across the four horizons before aggregation.
| Benchmark | Eligible full size | Evaluated origins | Preserved weighting structure |
|---|---|---|---|
| CGMacros | 1,903 | all 1,903; a 576-origin subsample for the behavior analyses | Equal number of origins per participant; participant-specific situation distribution |
| GlucoFM-Bench | 495,917 | 8,646 | At most 32 origins per participant within each dataset |
| CGM-LSM OhioT1DM | 9,214 | 1,536 | Full-population participant proportions |
Table 13: Full populations and the origins the paper scores.
| A1c | Fasting | Duration | CGM | Logged | |||||
|---|---|---|---|---|---|---|---|---|---|
| Participant | Age | Sex | BMI | (%) | range | (mg/dL) | (days) | readings | meals |
| 001 | 27 | M | 22.3 | 5.4 | Normal | 91 | 10.2 | 14,265 | 43 |
| 003 | 59 | F | 26.9 | 6.5 | Diabetes | 118 | 10.1 | 14,260 | 35 |
| 004 | 33 | F | 42.4 | 5.5 | Normal | 105 | 9.9 | 14,275 | 62 |
| 009 | 34 | F | 37.0 | 5.7 | Prediabetes | 122 | 10.0 | 14,226 | 41 |
| 010 | 54 | F | 35.8 | 5.7 | Prediabetes | 100 | 11.2 | 14,275 | 45 |
Table 14: The nine held-out CGMacros participants. Baseline values are the study-entry laboratory panel released with the dataset; the A1c range applies the ADA thresholds used for the agent’s profile field (normal , prediabetes to , diabetes ). CGM readings are Dexcom G6 Pro samples. Each participant contributes 208 to 212 of the 1,903 forecast origins.
| Method | 30 min | 60 min | 90 min | 120 min |
|---|---|---|---|---|
| Reference | ||||
| Persistence | 12.458 (4.522) | 19.688 (8.463) | 27.021 (10.482) | 31.142 (13.890) |
| CGM only, 12 hours of history | ||||
| TimesFM-2.5 | 11.251 (4.264) | 18.031 (7.723) | 24.303 (9.373) | 27.571 (12.566) |
| Moirai-2.0 | 11.846 (4.353) | 19.066 (7.843) | 25.559 (9.902) | 28.944 (13.196) |
| Timer † | 12.780 (4.311) | 19.736 (7.819) | 25.817 (10.679) | 28.634 (14.156) |
Table 15: CGMacros held-out forecasting in the quiet situation. The same 1,903 held-out origins as Table 1 , restricted to the 917 origins labeled quiet. Situation labels were attached after every forecast was scored; no forecaster saw them and no origin was selected or dropped on them. Within each participant, RMSE uses only that participant’s origins in this situation; cells report the unweighted participant mean (sample standard deviation), in mg/dL.
| Method | 30 min | 60 min | 90 min | 120 min |
|---|---|---|---|---|
| Reference | ||||
| Persistence | 30.784 (9.262) | 39.157 (18.489) | 43.479 (23.900) | 44.780 (27.697) |
| CGM only, 12 hours of history | ||||
| TimesFM-2.5 | 26.346 (8.134) | 33.645 (15.404) | 34.887 (18.755) | 33.224 (19.600) |
| Moirai-2.0 | 27.007 (9.072) | 35.251 (17.287) | 38.646 (22.768) | 38.503 (25.151) |
| Timer † | 29.782 (11.482) | 35.191 (17.008) | 35.825 (20.696) | 33.515 (20.388) |
Table 16: CGMacros held-out forecasting in the post-meal situation. The same 1,903 held-out origins as Table 1 , restricted to the 300 origins labeled post-meal. Situation labels were attached after every forecast was scored; no forecaster saw them and no origin was selected or dropped on them. Within each participant, RMSE uses only that participant’s origins in this situation; cells report the unweighted participant mean (sample standard deviation), in mg/dL.
| Method | 30 min | 60 min | 90 min | 120 min |
|---|---|---|---|---|
| Reference | ||||
| Persistence | 18.136 (8.220) | 28.654 (16.165) | 37.273 (25.090) | 40.046 (24.255) |
| CGM only, 12 hours of history | ||||
| TimesFM-2.5 | 15.359 (7.798) | 25.014 (12.495) | 32.365 (17.927) | 32.730 (19.018) |
| Moirai-2.0 | 14.995 (9.016) | 23.956 (14.580) | 31.975 (17.666) | 33.629 (20.251) |
| Timer † | 15.677 (8.442) | 24.071 (15.233) | 30.717 (18.444) | 31.687 (19.734) |
Table 17: CGMacros held-out forecasting in the post-exercise situation. The same 1,903 held-out origins as Table 1 , restricted to the 325 origins labeled post-exercise. Situation labels were attached after every forecast was scored; no forecaster saw them and no origin was selected or dropped on them. Within each participant, RMSE uses only that participant’s origins in this situation; cells report the unweighted participant mean (sample standard deviation), in mg/dL.
| Method | 30 min | 60 min | 90 min | 120 min |
|---|---|---|---|---|
| Reference | ||||
| Persistence | 26.867 (12.443) | 39.380 (18.906) | 40.101 (16.033) | 39.878 (16.410) |
| CGM only, 12 hours of history | ||||
| TimesFM-2.5 | 22.189 (7.766) | 33.313 (16.995) | 32.727 (17.060) | 30.835 (18.338) |
| Moirai-2.0 | 21.248 (7.222) | 34.472 (15.486) | 34.440 (15.992) | 33.004 (17.916) |
| Timer † | 26.043 (12.630) | 36.845 (21.400) | 34.868 (18.070) | 30.815 (16.197) |
Table 18: CGMacros held-out forecasting in the meal + exercise situation. The same 1,903 held-out origins as Table 1 , restricted to the 361 origins labeled meal + exercise. Situation labels were attached after every forecast was scored; no forecaster saw them and no origin was selected or dropped on them. Within each participant, RMSE uses only that participant’s origins in this situation; cells report the unweighted participant mean (sample standard deviation), in mg/dL.
Figure 5: The CGMacros held-out results at each horizon, without averaging across horizons. Panel (a) places every forecast origin by its recent carbohydrate and recent moderate exertion, each discounted by how long ago it happened, and the two fixed cuts that define quiet, post-meal, post-exercise and meal + exercise (for the scores and cuts see Appendix C ); the labels were attached after every forecast was scored, and no method saw them. Panel (b) repeats the three input settings at each horizon. Panel (c) reports the RMSE each method gains when the non-glucose signals are added, split by situation, on one shared scale. The gain for GlucoAgent is concentrated at 60 minutes: 2.1 mg/dL overall and 4.6 mg/dL after a meal, against 1.1, 1.4 and 1.2 mg/dL overall at 30, 90 and 120 minutes. All panels use the full held-out set of 1,903 forecast origins from nine participants.
Figure 6: Behavior census on the audited subsample of 576 held-out CGMacros forecast origins from nine participants. (a) The share of forecasts whose programs read the logged meals, defined a function of their own, or fitted a model, split by the four situations. Reading the logged meals rises from 48% on quiet origins to 90% shortly after a meal, while fitting a model falls from 55% to 47%. (b) The share of forecasts whose submitted reason states each kind of argument. These labels are assigned by a language-model judge reading the recorded reason against a fixed rubric, with every positive label carrying a verbatim span from the text. Reliability was checked against a second judge from a different model family on 120 of the forecasts, and only rubric items the two judges agree on at least 80% of the time are shown; two of the six items fail that gate and are omitted. A further 24 forecasts were re-read by hand, agreeing with the judge on 96.5% of 144 judgments, but that audit was performed by the same assistant that built this analysis rather than by an independent rater, so it is a consistency check and not an independent validation.
| Quantity | Value |
|---|---|
| Cases (participants) | 1903 (9) |
| Programs requested / executed / successful | 14852 / 14846 / 14468 |
| Executed failures and timeouts | 378 (166 timeouts) |
| Failures followed by a later success | 373 / 378 |
| Successful programs parsed for AST facts | 14468 / 14468 |
| Successful programs per case, median [IQR] | 7 [6–9], range 4–14 |
Table 19: What the agent executed across the full 1,903-origin CGMacros HOLDOUT cohort. Every quantity is counted from recorded run artifacts; the AST rows state the coverage within which the behavioural rates in the following tables hold.
| Modality | Read | Cited | Named | Cited + named |
|---|---|---|---|---|
| glucose | 100.0 | 100.0 | 99.6 | 99.6 |
| heart rate | 96.3 | 95.2 | 55.8 | 54.2 |
| activity | 96.4 | 95.5 | 76.7 | 73.8 |
| meals | 67.1 | 65.5 | 99.5 | 65.1 |
| baseline profile | 100.0 | 2.8 | 15.0 | 1.4 |
Table 20: Use of each modality in the executed programs, cited programs, and submitted reasons, as a percentage of the 1,903 held-out forecast origins. Read means a program subscripted a field of that modality; cited means the submission cited such a program; named means the submitted reason mentions the modality. The final column requires all three.
| Operation | Early | Middle | Late | First |
|---|---|---|---|---|
| reads glucose | 71.7 | 99.7 | 98.3 | 3 |
| reads heart rate | 68.5 | 38.2 | 11.0 | 3 |
| reads activity | 68.4 | 41.3 | 15.8 | 3 |
| reads meals | 36.0 | 46.2 | 28.7 | 3 |
| reads profile | 99.5 | 0.0 | 0.0 | 2 |
| writes a function | 2.5 | 36.5 | 54.4 | 6 |
Table 21: Share of the 1,903 HOLDOUT cases performing each operation in the early, middle and late third of their own program sequence, so the table does not depend on how many programs a case ran. The final column is the median program number at which the operation first appears.
| Package or module | Cases | Any use | Cited use |
|---|---|---|---|
| numpy | 100.0 | 100.0 | |
| pandas | 91.3 | 90.9 | |
| scikit-learn | 25.4 | 24.7 | |
| scipy | 5.8 | 4.7 | |
| statsmodels | 5.7 | 5.0 | |
| numpy | 1903 | 100.0 | 100.0 |
Table 22: What the agent imported, as a percentage of the 1,903 HOLDOUT cases. Packages are shown first, then every module imported in at least four cases. Module names are taken verbatim from the import statement, so they are exact.
| Symbol | Cases | Any use | Cited use |
|---|---|---|---|
| Model fitting | |||
| Ridge | 464 | 24.4 | 23.5 |
| polyfit | 255 | 13.4 | 12.0 |
| lstsq | 223 | 11.7 | 10.6 |
| curve_fit | 70 | 3.7 | 2.7 |
| AutoReg | 33 | 1.7 | 1.6 |
Table 23: Every symbol in the two printed sets that define fits a model and validates out of sample , with the number and percentage of the 1,903 HOLDOUT cases that called it. Membership of these sets is the whole definition of the two behaviors, so symbols never observed remain listed.
Figure 7: Case studies (d) to (f), the first half of the six forecasts that pass the recorded selection filter and are not shown in the main text. Each row uses the same layout as the main-text figure: the person’s context around the forecast cutoff, what the agent’s own programs computed, in order, a verbatim fragment of the reason it submitted, and the forecast against the truth and against the multimodal foundation-model baseline. The three rows show a ridge regression evaluated with time-series cross-validation and blended with past meal responses, a curve fit that is rejected in favor of two past days, and a forecast that works out when the rise arrives before working out how large it is. In (d) the fitted model runs only 0.2 to 1.4 mg/dL ahead of persistence at the four horizons; in (e) the two past days the agent did not use are drawn faint, and one of them rises to 212 mg/dL, above the chart; in (f) the middle chart keeps six of the nine rises the agent printed, selected by hand, with their average, and the shading on the right is the other peak sizes it tried.
Figure 8: Case studies (g) to (i), the second half of the six forecasts that pass the recorded selection filter and are not shown in the main text. The layout is the one used in Figure 7 . The three rows are a model trained on the earlier history and scored on the later history, a fit of how this person’s rise scales with the size of a meal, and a forecast built on the observation that this person dips for about an hour before rising. In (g) the model is off by 12 mg/dL on the scored history and persistence by 19; in (h) the estimate labeled “by eye” is typed into the reason rather than computed; in (i) the right chart shows the best and worst of the six held-out meals, and the forecast used both.
| Dataset | Model | Full dense | Subset | Full | Subset | |
|---|---|---|---|---|---|---|
| Hall2018 | Chronos-2 | 13.41 (6.93) | 13.27 (6.72) | -0.15 | 47 | 47 |
| Moirai-2.0 | 13.16 (6.06) | 12.96 (6.94) | -0.20 | 48 | 47 | |
| Timer | 14.05 (7.11) | 14.27 (8.10) | +0.22 | 48 | 47 | |
| TimesFM-2.5 | 12.96 (5.83) | 12.92 (6.49) | -0.04 | 48 | 47 | |
| BIG IDEAS Lab | Chronos-2 | 15.17 (3.04) | 14.21 (3.84) | -0.96 | 16 | 16 |
| Moirai-2.0 | 15.18 (3.24) | 14.29 (3.97) | -0.89 | 16 | 16 |
Table 24: Sensitivity of reproduced GlucoFM-Bench TSFM results to the evaluation population. Full uses all eligible dense stride-1 origins; subset uses the evaluated selection of at most 32 origins per eligible participant. Cells report participant-level RMSE mean (sample standard deviation), in mg/dL, at the 30-minute horizon. is subset minus full.
| Method | 0–30 min | 0–60 min | 0–120 min |
|---|---|---|---|
| CGM-LSM ∗ (reported) | 9.024 (0.168) | 15.895 (0.283) | 26.876 (0.430) |
| Chronos-2 (zero-shot) | 9.059 (0.398) | 15.865 (0.676) | 25.780 (0.982) |
| Moirai-2.0 (zero-shot) | 9.232 (0.417) | 16.218 (0.701) | 26.726 (1.035) |
| Timer † (zero-shot) | 10.485 (0.426) | 17.204 (0.682) | 26.825 (0.930) |
| TimesFM-2.5 (zero-shot) | 8.902 (0.397) | 15.686 (0.667) | 25.488 (0.967) |
| Persistence | 11.089 (0.490) | 18.649 (0.771) | 29.537 (1.113) |
Table 25: OhioT1DM under the CGM-LSM-matched protocol. Exact local rows use the evaluated subset ( ). Cells report mean per-instance cumulative-window rMSE (Student- 95% confidence half-width), in mg/dL; the parenthesized quantity is not a standard deviation.
| Dataset | Model | Published | Reproduced | ||
|---|---|---|---|---|---|
| Hall2018 | Persistence | 13.65 (4.52) | 13.66 (4.52) | +0.006 | 52 |
| Chronos-2 | 13.24 (6.96) | 13.41 (6.93) | +0.173 | 47 | |
| Moirai-2.0 | 13.16 (6.06) | 13.16 (6.06) | -0.004 | 48 | |
| Timer | 14.05 (7.11) | 14.05 (7.11) | +0.002 | 48 | |
| TimesFM-2.5 | 12.96 (5.83) | 12.96 (5.83) | -0.001 | 48 | |
| BIG IDEAS Lab | Persistence | 16.91 (4.03) | 16.92 (4.03) | +0.006 | 16 |
Table 26: Reproduction of accessible per-dataset zero-shot cells for the datasets retained in this paper from GlucoFM-Bench Table 2. RMSE is in mg/dL at 12 hours of context and a 30-minute horizon; values are participant-level mean (sample standard deviation).
| Dataset | Method | Reproduced | Published | |||
|---|---|---|---|---|---|---|
| 15 min | 30 min | 60 min | 90 min | 30 min | ||
| AZT1D | Persistence | 14.11 (2.20) | 23.36 (3.39) | 36.94 (5.55) | 46.09 (7.54) | 23.36 (3.39) |
| Chronos-2 | 12.04 (2.42) | 20.77 (3.34) | 34.14 (5.29) | 42.60 (7.28) | 20.77 (3.34) | |
| TimesFM-2.5 | 11.87 (2.47) | 20.53 (3.29) | 33.45 (5.22) | 41.66 (7.32) | 20.53 (3.29) | |
| Timer | 14.23 (2.52) | 23.83 (3.93) | 36.68 (6.75) | 43.71 (9.25) | 23.83 (3.93) | |
| Moirai-2.0 | 12.25 (2.44) | 21.23 (3.34) | 35.09 (5.26) | 44.27 (7.48) | 21.23 (3.34) | |
Table 27: Full zero-shot GlucoFM-Bench reproduction with the available published comparison. Entries are participant-level RMSE mean (sample standard deviation), in mg/dL, with a 12-hour context and dense stride-1 origins. Reproduced horizon columns score the final step; the final column is the only per-dataset horizon published by GlucoFM-Bench (Table 2).
| Method | Result source | 0–30 min | 0–60 min | 0–120 min |
|---|---|---|---|---|
| CGM-LSM ∗ | reported, trained | 9.024 (0.168) | 15.895 (0.283) | 26.876 (0.43) |
| Chronos-2 | reproduced, zero-shot | 9.007 (0.164) | 15.772 (0.275) | 25.654 (0.397) |
| TimesFM-2.5 | reproduced, zero-shot | 8.864 (0.165) | 15.622 (0.273) | 25.460 (0.393) |
| Persistence | reproduced | 11.198 (0.199) | 18.619 (0.315) | 29.447 (0.453) |
Table 28: TSFM comparison with CGM-LSM on its exact OhioT1DM evaluation protocol. The zero-shot and persistence rows are reproduced on the same 9,214-instance set. Cells report mean rMSE (Student- 95% confidence half-width), in mg/dL.
| Model | Input setting | 30 min | 60 min | 90 min | 120 min |
|---|---|---|---|---|---|
| Persistence | Last observed CGM | 13.512 (3.827) | 19.710 (7.136) | 23.878 (9.796) | 26.614 (11.706) |
| TimesFM-2.5 | CGM only (12 h) | 11.729 (3.125) | 17.133 (6.332) | 20.196 (8.623) | 21.978 (10.029) |
| CGM only (full history) | 11.386 (3.157) | 16.156 (6.031) | 18.604 (8.131) | 19.712 (9.488) | |
| Moirai-2.0 | CGM only (12 h) | 12.322 (3.726) | 18.381 (6.919) | 21.818 (9.790) | 23.756 (11.455) |
| CGM only (full history) | 11.521 (3.301) | 16.316 (5.910) | 18.687 (7.854) | 20.042 (9.123) | |
| Timer † | CGM only (12 h) | 13.618 (4.427) | 18.974 (7.863) | 21.930 (10.231) | 22.990 (11.572) |
Table 29: CGMacros HOLDOUT MAE sensitivity analysis on the full 1,903-origin set. Cells report participant-level MAE mean (sample standard deviation), in mg/dL; standard deviations use . All 12-hour rows use 144 five-minute history steps.
| Dataset | Persistence | Chronos-2 | Moirai-2.0 | Timer | TimesFM-2.5 | GlucoAgent |
| Hall2018 | 10.11 (5.94) | 9.54 (4.83) | 9.39 (5.03) | 10.61 (5.62) | 9.27 (4.60) | 9.68 (4.30) |
| BIG IDEAS Lab | 10.20 (2.75) | 9.56 (2.49) | 9.59 (2.50) | 10.72 (3.08) | 9.17 (2.36) | 9.79 (2.61) |
| ShanghaiT1DM | 13.46 (5.91) | 9.52 (3.69) | 9.03 (3.18) | 15.40 (7.00) | 8.89 (3.39) | 8.12 (2.68) |
| ShanghaiT2DM | 10.80 (3.97) | 8.38 (2.85) | 8.34 (2.72) | 11.05 (4.11) | 7.93 (2.69) | 8.00 (2.72) |
| HUPA-UCM | 15.62 (6.08) | 12.42 (5.34) | 11.97 (4.90) | 18.02 (5.98) | 12.06 (5.37) | 10.97 (4.32) |
| T1DM-UOM | 18.91 (4.77) | 16.43 (3.80) | 16.61 (3.86) | 19.16 (5.18) | 16.28 (3.89) | 15.78 (3.82) |
Table 30: GlucoFM-Bench MAE sensitivity analysis on the largest completed exact local subset ( origins per eligible participant): 12-hour context, 30-minute horizon, and participant-level MAE in mg/dL. Values are mean (sample standard deviation).
| Method | 0–30 min | 0–60 min | 0–120 min |
|---|---|---|---|
| Chronos-2 (zero-shot) | 7.857 (0.352) | 13.507 (0.585) | 21.804 (0.860) |
| TimesFM-2.5 (zero-shot) | 7.688 (0.351) | 13.322 (0.578) | 21.554 (0.845) |
| Persistence | 9.783 (0.443) | 16.148 (0.685) | 25.374 (0.985) |
| GlucoAgent | 7.953 (0.362) | 13.658 (0.596) | 21.893 (0.875) |
Table 31: OhioT1DM MAE sensitivity analysis under the CGM-LSM-matched protocol on the evaluated subset ( ). Cells report mean per-instance cumulative-window MAE (Student- 95% confidence half-width), in mg/dL.
| Model | Effort | 30 min | 60 min | 90 min | 120 min | Mean-4 |
|---|---|---|---|---|---|---|
| Claude Opus 5 (ours) | high | 10.905 (2.559) | 15.153 (4.988) | 17.744 (6.681) | 18.653 (7.548) | 15.614 (5.345) |
| Claude Opus 5 | medium | 11.570 (2.621) | 16.310 (5.195) | 18.869 (6.965) | 20.344 (8.195) | 16.773 (5.628) |
| Claude Sonnet 5 | high | 12.510 (2.950) | 18.532 (5.551) | 21.774 (7.781) | 24.288 (9.443) | 19.276 (6.310) |
| Gemini 3.1 Pro | high | 12.596 (3.424) | 17.388 (6.251) | 20.289 (7.312) | 21.317 (8.963) | 17.898 (6.401) |
| GPT-5.6-sol | high | 11.495 (2.983) | 15.978 (5.366) | 18.519 (6.489) | 19.210 (7.473) | 16.300 (5.484) |
Table 32: Multimodal LLM MAE ablation on the full 1,903-origin CGMacros HOLDOUT set. Cells report participant-level MAE mean (sample standard deviation), in mg/dL. Mean-4 is computed per participant across the four horizons before aggregation.
| Input setting | Model | Effort | 30 min | 60 min | 90 min | 120 min | Mean-4 |
|---|---|---|---|---|---|---|---|
| Multimodal | Claude Opus 5 (ours) | high | 10.905 (2.559) | 15.153 (4.988) | 17.744 (6.681) | 18.653 (7.548) | 15.614 (5.345) |
| Claude Opus 5 | medium | 11.570 (2.621) | 16.310 (5.195) | 18.869 (6.965) | 20.344 (8.195) | 16.773 (5.628) | |
| Claude Sonnet 5 | high | 12.510 (2.950) | 18.532 (5.551) | 21.774 (7.781) | 24.288 (9.443) | 19.276 (6.310) | |
| CGM only (full history) | Claude Opus 5 (ours) | high | 11.613 (3.182) | 16.363 (5.454) | 18.426 (6.990) | 19.333 (7.971) | 16.434 (5.804) |
| Claude Opus 5 | medium | 12.447 (3.071) | 17.703 (5.910) | 19.985 (8.265) | 21.376 (9.515) | 17.878 (6.589) | |
| Claude Sonnet 5 | high | 12.648 (3.254) | 18.250 (5.727) | 21.958 (8.109) | 24.359 (9.704) | 19.303 (6.603) |
Table 33: Claude-family MAE ablation across matched input settings on the full 1,903-origin CGMacros HOLDOUT set. Cells report participant-level MAE mean (sample standard deviation), in mg/dL. Mean-4 is computed per participant across the four horizons before aggregation.
| Method | 30 min | 60 min | 90 min | 120 min | Mean-4 |
|---|---|---|---|---|---|
| Hand-designed faithful port (high effort) | 11.877 (2.528) | 16.520 (5.103) | 18.709 (7.314) | 19.758 (8.622) | 16.716 (5.770) |
| Hand-designed faithful port (medium effort) | 12.317 (2.889) | 17.399 (5.566) | 19.818 (7.944) | 20.970 (9.475) | 17.626 (6.303) |
| Chronos-2 (fuller multimodal) | 11.416 (3.444) | 15.834 (5.943) | 17.881 (7.738) | 18.490 (8.453) | 15.905 (6.307) |
| GlucoAgent (agent-designed multimodal) | 10.905 (2.559) | 15.153 (4.988) | 17.744 (6.681) | 18.653 (7.548) | 15.614 (5.345) |
Table 34: MAE comparison with the hand-designed tool interface on the full 1,903 exactly matched CGMacros HOLDOUT origins. Cells report participant-level MAE mean (sample standard deviation), in mg/dL. Mean-4 is computed per participant across the four horizons before aggregation.
More in this topic
Blood Glucose Forecasting
Blood glucose forecasting predicts future glucose levels from continuous glucose monitor data and clinical context to support diabetes care.
See all 21 papers