mlsanityData to 7 Oct 2026

Agentic Control in Variational Language Models

arXiv 2604.12513 ↗First posted 14 Apr 2026cs.LGcited by 0

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

We study whether a variational language model can support a minimal and measurable form of agentic control grounded in its own internal evidence. Our model combines local variational hidden computation (EVE), a homeostatic latent regulator, structurally aware checkpoint retention and a calibrated uncertainty-aware controller operating on top of the retained model. Rather than treating uncertainty as a passive diagnostic measured after prediction, we treat it as an operational signal that can regulate training, support checkpoint retention and guide inference-time intervention. The resulting framework is deliberately focused. It studies a closed-loop form of internal control in which structural and predictive signals become actionable. Empirically, the variational backbone improves over a matched deterministic reference on the language-modeling task while also exhibiting a richer and more usable uncertainty profile. On top of this backbone, the calibrated controller remains active, uses multiple actions under a full agentic evaluation and yields a positive quality-cost trade-off. These results support a precise claim: internal uncertainty can serve not only as a descriptive property of a variational language model, but also as a practical control interface for regulation, checkpoint retention and minimal agentic routing.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 14 of its 15 references that are in the map. First posted on arXiv 14 Apr 2026.

Builds on

14 of 15 references.

References · 14

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  3. 2017On Calibration of Modern Neural Networkscited by 4,860
  4. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  5. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  6. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  7. 2017Selective Classification for Deep Neural Networkscited by 799
  8. 2015Weight Uncertainty in Neural Networkscited by 554
  9. 2019SelectiveNet: A Deep Neural Network with an Integrated Reject Optioncited by 333
  10. 2022MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoningcited by 153
  11. 2024Large Language Models Must Be Taught to Know What They Don't Knowcited by 99
  12. 2021Bayesian Transformer Language Models for Speech Recognitioncited by 22
2 more
  1. 2022BayesFormer: Transformer with Uncertainty Estimationcited by 19
  2. 2026Variational Neurons in Transformers for Language Modelingcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026From Passive Metric to Active Signal: The Evolving Role of Uncertainty Quantification in Large Language Models
  2. 2024Controlling Large Language Model Agents with Entropic Activation Steering
  3. 2026Latent Memory Palace: Reasoning for Control as Autoregressive Variational Inference
  4. 2026Multi-Head Latent Control: A Unified Interface for LLM Agent Decision Making
  5. 2026Hierarchical Prompt-Domain Control and Learning for Resource-Constrained Agentic Language Models
  6. 2026The "I Don't Know" Filter: Enhancing Agentic Reliability in Function Calling
  7. 2026Agent-BRACE: Decoupling Beliefs from Actions in Long-Horizon Tasks via Verbalized State Uncertainty
  8. 2026Thinking Outside the Box: Can Language Models Rely on External Guidance Selectively?