RECORD
Look Before You Leap: Thermodynamic Arbitration of Parametric and Non-Parametric Knowledge in LLM Agents via Self-Regulating Memory Architectures
Artificial Intelligence · Submitted 4 Oct 2026
abstract compiled · 2026-10-06 · no language-model review
The authors' main claim Our approach suggests that giving agents the capacity for introspection can restore a more efficient balance between internal knowledge and external information.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
The architecture of modern LLMs consists of a profound cognitive polarization. LLMs possess implicit intuition encoded in their parameters, yet rely on a disconnected, explicit mechanism to access the outside world. Agentic frameworks have not bridged this gap; instead, models are often compelled into pathological "induced amnesia." Under the prevailing "Retrieve-Always" paradigm, agents must distrust their internal knowledge, making every user interaction a "tabula rasa" event that must be checked externally. This creates reflexive dependence that can be thermodynamically wasteful, cognitively fragile, and susceptible to irrelevant context. We propose a return to first principles, operationalizing the biological maxim "Look Before You Leap." We introduce MARTA (Metacognitive Adaptive Retrieval and Thought Architecture), a neuro-symbolic framework that bridges parametric and non-parametric knowledge. Rather than treating retrieval as mandatory, MARTA models it as a cost, taking the leap only when perceived internal inadequacy warrants external information. By allowing the agent to gauge the entropy of its own thoughts before acting, MARTA enables deliberative retrieval and uncertainty-aware decision making. Our approach suggests that giving agents the capacity for introspection can restore a more efficient balance between internal knowledge and external information.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | The architecture of modern LLMs consists of a profound cognitive polarization. | background 1.00 | 0.07 | 0.03 | asserted 1.00 |
| s1 | LLMs possess implicit intuition encoded in their parameters, yet rely on a disconnected, explicit mechanism to access the outside world. | background 0.98 | 0.06 | 0.03 | asserted 1.00 |
| s2 | Agentic frameworks have not bridged this gap; instead, models are often compelled into pathological "induced amnesia." Under the prevailing "Retrieve-Always" paradigm, agents must distrust their internal knowledge, making every user interaction a "tabula rasa" event that must be checked externally. | background 0.69 | 0.05 | 0.04 | asserted 0.99 |
| s3 | This creates reflexive dependence that can be thermodynamically wasteful, cognitively fragile, and susceptible to irrelevant context. | background 0.88 | 0.05 | 0.05 | asserted 0.74 |
| s4 | We propose a return to first principles, operationalizing the biological maxim "Look Before You Leap." We introduce MARTA (Metacognitive Adaptive Retrieval and Thought Architecture), a neuro-symbolic framework that bridges parametric and non-parametric knowledge. | contribution 0.95 | 0.81 | 0.20 | asserted 1.00 |
| s5 | Rather than treating retrieval as mandatory, MARTA models it as a cost, taking the leap only when perceived internal inadequacy warrants external information. | method 0.89 | 0.50 | 0.23 | asserted 1.00 |
| s6 | By allowing the agent to gauge the entropy of its own thoughts before acting, MARTA enables deliberative retrieval and uncertainty-aware decision making. | method 0.77 | 0.41 | 0.23 | asserted 0.97 |
| s7 | Our approach suggests that giving agents the capacity for introspection can restore a more efficient balance between internal knowledge and external information. | interpretation 1.00 | 0.23 | 0.71 | hedged possibility 1.00 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
The architecture of modern LLMs consists of a profound cognitive polarization. LLMs possess implicit intuition encoded in their parameters, yet rely on a disconnected, explicit mechanism to access the outside world. Agentic frameworks have not bridged this gap; instead, models are often compelled into pathological "induced amnesia." Under the prevailing "Retrieve-Always" paradigm, agents must distrust their internal knowledge, making every user interaction a "tabula rasa" event that must be checked externally. This creates reflexive dependence that can be thermodynamically wasteful, cognitively fragile, and susceptible to irrelevant context. We propose a return to first principles, operationalizing the biological maxim "Look Before You Leap." We introduce MARTA (Metacognitive Adaptive Retrieval and Thought Architecture), a neuro-symbolic framework that bridges parametric and non-parametric knowledge. Rather than treating retrieval as mandatory, MARTA models it as a cost, taking the leap only when perceived internal inadequacy warrants external information. By allowing the agent to gauge the entropy of its own thoughts before acting, MARTA enables deliberative retrieval and uncertainty-aware decision making. Our approach suggests that giving agents the capacity for introspection can restore a more efficient balance between internal knowledge and external information.
Human review
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.