State Representation and Termination for Recursive Reasoning Systems

• URL: http://arxiv.org/abs/2605.06690v1
• Date: Sat, 02 May 2026 07:40:09 GMT
• Title: State Representation and Termination for Recursive Reasoning Systems
• Abstract summary: Recursive reasoning systems alternate between acquiring new evidence and refining an accumulated understanding.<n>This paper addresses how to represent the evolving reasoning state, and when to stop iterating.<n>We apply the framework to agent loops, tree-of-thought reasoning, theorem proving, and continual learning.
• Score: 3.276545330242602
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recursive reasoning systems alternate between acquiring new evidence and refining an accumulated understanding. Two design choices are typically left implicit: how to represent the evolving reasoning state, and when to stop iterating. This paper addresses both. We represent the reasoning state as an epistemic state graph encoding extracted claims, evidential relations, open questions, and confidence weights. We define the order-gap as the distance between the states reached by expand-then-consolidate versus consolidate-then-expand; a small order-gap suggests that the two orderings agree and further iteration is unlikely to help. Our main result gives a necessary and sufficient condition for the linearised order-gap to be non-degenerate near the fixed point, showing when the criterion is informative rather than algebraically vacuous. This is a local condition, not a global convergence guarantee. We apply the framework to recursive reasoning systems and sketch its application to agent loops, tree-of-thought reasoning, theorem proving, and continual learning.

Related papers

• RecRec: Latent Interests Recursive Reasoning for Sequential Recommendation [52.23179023639867]
  Sequential recommender systems rely on a single forward pass to encode user interaction and predict the next item.<n>How to structure the reasoning process for sequential recommendation remains an open question.<n>Existing approaches couple reasoning and prediction in a single $d$-dimensional state, limiting reasoning depth.<n>We propose RecRec (Recursive Reasoning for Recommendation), an RL-free framework that overcomes fixed $d$-dimensional state of methods.
  arXiv  Detail & Related papers  (2026-07-14T16:28:28Z)
• The Need for an External Observer Formalizing the Sufficiency Gap: A Mathematical Extension of Mixture Identifiability and Contextual Grounding in Sequence Models [0.0]
  We construct a binary mixed-regime process with one deterministic textual regime and one random regime governed by an unobserved latent state.<n>The resulting entropy difference is not an ordinary optimization error; it is a sufficiency gap caused by marginalization over an unobserved state.<n>A corrective signal reverses the posterior odds induced by the textual history exactly when its fidelity exceeds the text-only posterior weight assigned to the misleading regime.
  arXiv  Detail & Related papers  (2026-05-26T08:53:11Z)
• Consolidation-Expansion Operator Mechanics:A Unified Framework for Adaptive Learning [0.0]
  We propose emphConsolidation Operator Mechanics (OpMech), a framework that makes this structure precise.<n>The central object is the emphorder-gap $Ogap(; e)$, the degree to which a consolidation operator$Q$ and an expansion operator$P_e$ fail to commute at a given knowledge state.<n>Because the order-gap is computable from the system's own trajectory, it serves as a real-time control signal.
  arXiv  Detail & Related papers  (2026-05-11T04:19:45Z)
• Indefinite Causal Order from Failure-to-Glue: Contextual Semantics and Parametric Time [0.0]
  Indefinite causal order (ICO) has been studied via higher-order quantum processes.<n>PartI develops a category-theoretic formulation of definite-order explainability as a gluing problem.<n>PartII applies this framework to a quantum-gravity motivated setting.
  arXiv  Detail & Related papers  (2026-01-23T06:44:44Z)
• Translating Informal Proofs into Formal Proofs Using a Chain of States [20.0011959667642]
  We address the problem of translating informal mathematical proofs expressed in natural language into formal proofs in Lean4 under a constrained computational budget.<n>We first extract a Chain of States (CoS), a sequence of intermediate formal proof states aligned with the logical structure of the informal argument.<n>We then generate tactics to transition between adjacent states in the CoS, thereby constructing the full formal proof.
  arXiv  Detail & Related papers  (2025-12-11T06:08:34Z)
• A Unified Formal Theory on the Logical Limits of Symbol Grounding [0.65268245109828]
  We show that meaning within a formal system must arise from a process that is external, dynamic, and non-algorithmic.<n>We extend this limitation to systems with any finite, static set of pre-established meanings.
  arXiv  Detail & Related papers  (2025-09-24T05:40:08Z)
• Think Clearly: Improving Reasoning via Redundant Token Pruning [57.01254508252785]
  We show that deliberately removing redundancy in the reasoning process significantly improves performance.<n>We demonstrate that our method significantly improves overall accuracy across reasoning-intensive benchmarks without any training.
  arXiv  Detail & Related papers  (2025-06-17T06:04:01Z)
• Chain-of-Probe: Examining the Necessity and Accuracy of CoT Step-by-Step [81.50681925980135]
  We propose a method to probe changes in the mind during the model's reasoning.<n>By analyzing patterns in mind change, we examine the correctness of the model's reasoning.<n>Our validation reveals that many responses, although correct in their final answer, contain errors in their reasoning process.
  arXiv  Detail & Related papers  (2024-06-23T15:50:22Z)
• Normative Conditional Reasoning as a Fragment of HOL [0.0]
  We discuss the mechanization of (preference-based) conditional normative reasoning. Our focus is on Aqvist's system E for conditional obligation, and its extensions. We consider two possible uses of the framework.
  arXiv  Detail & Related papers  (2023-08-21T12:47:30Z)
• Language Models with Rationality [57.37201135072838]
  Large language models (LLMs) are proficient at question-answering (QA) It is not always clear how (or even if) an answer follows from their latent "beliefs"
  arXiv  Detail & Related papers  (2023-05-23T17:04:25Z)
• LAMBADA: Backward Chaining for Automated Reasoning in Natural Language [11.096348678079574]
  Backward Chaining algorithm, called LAMBADA, decomposes reasoning into four sub-modules. We show that LAMBADA achieves sizable accuracy boosts over state-of-the-art forward reasoning methods.
  arXiv  Detail & Related papers  (2022-12-20T18:06:03Z)
• MetaLogic: Logical Reasoning Explanations with Fine-Grained Structure [129.8481568648651]
  We propose a benchmark to investigate models' logical reasoning capabilities in complex real-life scenarios. Based on the multi-hop chain of reasoning, the explanation form includes three main components. We evaluate the current best models' performance on this new explanation form.
  arXiv  Detail & Related papers  (2022-10-22T16:01:13Z)
• Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanations [71.2950434944196]
  We develop Maieutic Prompting, which infers a correct answer to a question even from the noisy and inconsistent generations of language models. Maieutic Prompting achieves up to 20% better accuracy than state-of-the-art prompting methods.
  arXiv  Detail & Related papers  (2022-05-24T06:36:42Z)
• Nested Counterfactual Identification from Arbitrary Surrogate Experiments [95.48089725859298]
  We study the identification of nested counterfactuals from an arbitrary combination of observations and experiments. Specifically, we prove the counterfactual unnesting theorem (CUT), which allows one to map arbitrary nested counterfactuals to unnested ones.
  arXiv  Detail & Related papers  (2021-07-07T12:51:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.