arXiv AI

Contextual Information Allocation in Shared-State Cognitive Models: An Information-Theoretic Bound

The paper derives an information‑theoretic bound for a shared‑state cognitive architecture that uses an auxiliary variable to mediate context. It shows that the residual dependence of observable behavior on context, given the shared state, is bounded by the information carried by the auxiliary variable and its conditional entropy. A recognition‑memory example illustrates how to compute and compare this bound across different representational choices, providing a framework for analyzing context‑memory‑control trade‑offs in cognitive models and artificial agents.

arXiv AI
Jul 14

Context by Distinct Information: An Auditable Dirichlet-Process Working Memory for Long, Redundant Context Streams

arXiv:2607. 10441v1 Announce Type: cross Abstract: Context engineering decides what information a model carries forward, and current designs meter it in tokens: compressing the past into a bounded recurrent state, keeping a key-value entry for every token, or imposing a fixed budget through a window or eviction rule.

By Siddharth Pal, Viktoria Rojkova
arXiv AI
Sep 12

A Mathematical Theory of Pragmatic Information

The paper introduces a pragmatic information theory that unifies communication, control, and decision-making through the isoteleia mapping, which formalizes equifinality by treating distinct semantic paths that lead to the same optimal action as pragmatically equivalent. It establishes a three-tier hierarchy of syntactic, semantic, and pragmatic information, defines pragmatic entropy, mutual information, channel capacity, and rate-distortion, and proves coding theorems that generalize Shannon’s results. The authors also present pragmatic value and cost of information, a Lagrangian dual framework for cross-layer optimization, and a pragmatic efficiency bound that quantifies the maximum net utility for resource-constrained intelligent systems, extending the theory to continuous messages and dynamic settings.

By Kai Niu, Ping Zhang
arXiv AI
Oct 2

Causal Memory Policy: Making Memory Utility Identifiable by Intervening on Retrieval

The paper introduces Causal Memory Policy (CMP), a framework that identifies the utility of memories in memory‑augmented language models by intervening on retrieval rather than on storage. CMP reserves fixed context slots for memories sampled with known propensities and estimates utility using self‑normalized inverse propensity weighting, providing unbiased estimates and exact variance. Experiments show that CMP improves discrimination between required and non‑required memories and reveals that identified utility alone is insufficient for retention decisions across unseen queries.

By Arman Behnam, Binghui Wang
arXiv Machine Learning
Sep 2

How Do Language Models Choose Between Context and Memory?

The paper investigates how language models decide between contextual information and their internal memory when the two conflict. By estimating "authority directions" from agreement prompts and swapping these directions between matched prompts, the authors show that such interventions can reproduce 30–68% of the shift in source choice across Qwen, Llama, and OLMo models. Cross‑task experiments reveal that authority directions learned on one task transfer only modestly (≈9%) to another, indicating that authority computations are largely task‑specific.

By Benjamin Shih, John Winnicki, Arianna Cao
arXiv Machine Learning
Oct 5

Harnessing LLMs as Agents: What Does It Cost?

The paper introduces the Language Model Agent Machine (LAM), a framework that quantifies the computational resources consumed by language‑model agents’ harnesses—such as bounded context, memory, tools, and verification. It presents four main theoretical results: (1) communication costs mapped to pebbling lower bounds, (2) memory‑access separations revealing a linear gap between random and non‑speculative access, (3) recomputation bounds for bit‑reversal DAGs that show when storing intermediate state is beneficial, and (4) reliability bounds that yield optimal verification intervals. Experiments on GPT‑6 Astra validate the theory’s predictions for communication, reliability, and trade‑offs in practical tasks.

By Zelin Zhao (Georgia Institute of Technology), Xinyu Guo (Georgia Institute of Technology), Jingyuan Zhang (Georgia Institute of Technology), Yuxuan Zhang (Etude AI), Yongxin Chen (Georgia Institute of Technology)
arXiv AI
1d ago

When Does Less Information Pay? An Exact Finite Atlas of Representation, Payoff, and Cost

The paper presents a complete enumeration of all possible representations and binary action rules in a uniform four‑state world, comparing their retained information, payoff (task accuracy), and cost under various tariffs. It shows that a representation with less retained information can sometimes yield higher payoff, while in other cases the more informative representation performs better, and that equal payoff can occur with different information amounts. The study demonstrates how the specific distinctions preserved by a representation, the choice of action rule, and the cost assumptions jointly determine performance, offering a reproducible model for exploring these trade‑offs.

By Aleksandr M. Shtraukh-Adamsky, Vladimir M. Adamsky, Irina G. Voloshina, Artemiy D. Spitsyn