arXiv:2607. 29496v1 Announce Type: new Abstract: We study transcript management for fixed, finite-precision causal Transformers.
arXiv:2609. 11326v2 Announce Type: replace-cross Abstract: We ask whether it can be certified algorithmically that a self-modifying computational system preserves a safety property at its next step (preservation) and along its whole evolution (persistence).
arXiv:2607. 26988v1 Announce Type: cross Abstract: What types of decision problems can a causally masked, finite-precision transformer solve for inputs of arbitrary length?
arXiv:2606. 12502v1 Announce Type: cross Abstract: We propose that value -- the quantity goal-directed agents create, destroy, and exchange -- is a lawful structural quantity in the same category as information.
The study investigates how different message formats affect the fidelity of information as it passes through multiple LLM agent relays. Using a controlled testbed, the authors encode twelve atomic facts in five formats (free natural language, precision‑instructed NL, JSON, triples, key‑value) across six hops and evaluate recall against programmatic ground truth. Results show that strong relays maintain near‑lossless recall for all formats, while weaker relays exhibit significant format‑dependent recall loss, and that any injected error is faithfully propagated across all formats without causing collateral damage.
arXiv:2607. 09678v1 Announce Type: new Abstract: When LLM agents hand off information to one another, does the message format matter?
The paper investigates exact factorization and canonical presentations of languages relative to a fixed finite‑monoid observation. It shows that unique factorization does not guarantee a finite relative presentation property (FRP) by presenting a 36‑element quotient with infinite valid prime‑return rules, and introduces the stronger finite‑state relative presentation property (FSRP). The authors further define prime‑target left‑division determinism (PTLD), prove its implications for factorization and rule bounds, and provide efficient learning algorithms for the canonical PTLD presentation and FSRP controller.
arXiv:2607. 17469v1 Announce Type: cross Abstract: A randomized algorithm may terminate almost surely even though exceptional random tapes make it run forever.
arXiv:2608. 08282v1 Announce Type: new Abstract: Tool-using language-model agents face constraints whose meaning changes with observations and prior actions.
arXiv:2607. 14571v1 Announce Type: cross Abstract: We introduce \emph{gate-zero growth}, a function-preserving (FP) operator for continual learning that adds new residual blocks through a zero-initialised gate.
arXiv:2609.07065v1 Announce Type: new Abstract: Agent-to-agent (A2A) alpha discovery is slowed by repeated feedback cycles between mining and evaluation agents, whose hand-offs, in contemporary LLM m...
arXiv:2608.28553v2 Announce Type: replace Abstract: Modern agent systems assemble capabilities at runtime, and this dynamic composition has recently received a complete formal treat ment in the spati...
arXiv:2608. 01548v3 Announce Type: replace Abstract: Test-time emergence in LLM systems has a deployment boundary: additional computation can realize decisions already supported by the deployed information--execution structure, while evidence, tools, memory, and executable semantics can change the class inherited by later computation.