Related papers: Effective AGM Belief Contraction: A Journey beyond the Finitary Realm (Technical Report)

Related papers

Knowing When to Quit: Diagnosing and Training LLMs to Abort Futile Reasoning [109.33717747526583]
Large language models generate computationally expensive yet semantically void reasoning on beyond-capability tasks.<n>We introduce textbfCaRL (textbfCapability-textbfaligned textbfReinforcement textbfL) to align behavior with capability boundaries.<n>Experiments demonstrate a substantial reduction in futile reasoning while preserving performance across task difficulties.
arXiv Detail & Related papers (2026-07-31T09:30:33Z)
The Undecidability of Artificial General Intelligence (AGI) Alignment [0.0]
This article establishes the foundational mathematical limits of Artificial General Intelligence (AGI) safety.<n>We formalize this boundary through two central impossibility results: the Unverifiability Theorem of Alignment and the Theorem of Finite Structural Unverifiability of AGI Alignment.
arXiv Detail & Related papers (2026-06-26T22:51:16Z)
LC-ERD: Mining Latent Logic for Self-Evolving Reasoning via Consistency-Regulated Reward Decomposition [55.572260012037084]
We introduce LC-ERD (Logic-Consistent Endogenous Reward Decomposition), a framework framing self-alignment as latent structure mining.<n>We derive a Variational Logic Potential by aggregating consensus from the model's Latent Logic Expertise.<n>Experiments show LC-ERD delivers a robust self-evolution path, uncovering trade-offs between logic consistency and accuracy.
arXiv Detail & Related papers (2026-05-19T07:27:50Z)
Fantastic Reasoning Behaviors and Where to Find Them: Unsupervised Discovery of the Reasoning Process [66.38541693477181]
We propose an unsupervised framework for discovering reasoning vectors, which we define as directions in the activation space that encode distinct reasoning behaviors.<n>By segmenting chain-of-thought traces into sentence-level'steps', we uncover disentangled features corresponding to interpretable behaviors such as reflection and backtracking.<n>We demonstrate the ability to control response confidence by identifying confidence-related vectors in the SAE decoder space.
arXiv Detail & Related papers (2025-12-30T05:09:11Z)
Are Language Models Efficient Reasoners? A Perspective from Logic Programming [109.47572890883248]
Modern language models (LMs) exhibit strong deductive reasoning capabilities, yet standard evaluations emphasize correctness while overlooking a key aspect of human-like reasoning: efficiency.<n>We propose a framework for assessing LM reasoning efficiency through the lens of logic programming.
arXiv Detail & Related papers (2025-10-29T15:30:31Z)
Foundation Models for Logistics: Toward Certifiable, Conversational Planning Interfaces [59.80143393787701]
Large language models (LLMs) can handle uncertainty and promise to accelerate replanning while lowering the barrier to entry.<n>We introduce a neurosymbolic framework that pairs the accessibility of natural-language dialogue with verifiable guarantees on goal interpretation.<n>A lightweight model, fine-tuned on just 100 uncertainty-filtered examples, surpasses the zero-shot performance of GPT-4.1 while cutting inference latency by nearly 50%.
arXiv Detail & Related papers (2025-07-15T14:24:01Z)
On the Mathematical Impossibility of Safe Universal Approximators [0.0]
We prove that catastrophic failures are an inescapable feature of any useful computational system.<n>We prove this through a three-level argument that leaves no escape routes for any class of universal approximator architecture.
arXiv Detail & Related papers (2025-07-03T01:05:24Z)
A Comment On "The Illusion of Thinking": Reframing the Reasoning Cliff as an Agentic Gap [0.39073867995073247]
We argue that the observed failure is not evidence of a fundamental cognitive boundary, but rather a predictable outcome of system-level constraints.<n>A model, initially declaring a puzzle impossible when confined to text-only generation, now employs agentic tools to not only solve it but also master variations of complexity far beyond the reasoning cliff it previously failed to surmount.
arXiv Detail & Related papers (2025-06-23T17:14:21Z)
Beyond 'Aha!': Toward Systematic Meta-Abilities Alignment in Large Reasoning Models [86.88657425848547]
Large reasoning models (LRMs) already possess a latent capacity for long chain-of-thought reasoning.<n>We explicitly align models with three meta-abilities: deduction, induction, and abduction, using automatically generated, self-verifiable tasks.<n>Our three stage-pipeline individual alignment, parameter-space merging, and domain-specific reinforcement learning, boosts performance by over 10% relative to instruction-tuned baselines.
arXiv Detail & Related papers (2025-05-15T17:58:33Z)
ZebraLogic: On the Scaling Limits of LLMs for Logical Reasoning [92.76959707441954]
We introduce ZebraLogic, a comprehensive evaluation framework for assessing LLM reasoning performance. ZebraLogic enables the generation of puzzles with controllable and quantifiable complexity. Our results reveal a significant decline in accuracy as problem complexity grows.
arXiv Detail & Related papers (2025-02-03T06:44:49Z)
LogicBench: Towards Systematic Evaluation of Logical Reasoning Ability of Large Language Models [52.03659714625452]
Recently developed large language models (LLMs) have been shown to perform remarkably well on a wide range of language understanding tasks. But, can they really "reason" over the natural language? This question has been receiving significant research attention and many reasoning skills such as commonsense, numerical, and qualitative have been studied.
arXiv Detail & Related papers (2024-04-23T21:08:49Z)
Are LLMs Rigorous Logical Reasoner? Empowering Natural Language Proof Generation with Contrastive Stepwise Decoding [10.421832675327712]
We introduce contrastive decoding to stepwise proof generation, making use of negative reasoning paths to strengthen the model's capacity for logical deduction.<n> Experiments on EntailmentBank underscore the success of our method in augmenting the proof planning abilities of language models.
arXiv Detail & Related papers (2023-11-12T05:12:49Z)
LINC: A Neurosymbolic Approach for Logical Reasoning by Combining Language Models with First-Order Logic Provers [60.009969929857704]
Logical reasoning is an important task for artificial intelligence with potential impacts on science, mathematics, and society. In this work, we reformulating such tasks as modular neurosymbolic programming, which we call LINC. We observe significant performance gains on FOLIO and a balanced subset of ProofWriter for three different models in nearly all experimental conditions we evaluate.
arXiv Detail & Related papers (2023-10-23T17:58:40Z)
Logic-induced Diagnostic Reasoning for Semi-supervised Semantic Segmentation [85.12429517510311]
LogicDiag is a neural-logic semi-supervised learning framework for semantic segmentation. Our key insight is that conflicts within pseudo labels, identified through symbolic knowledge, can serve as strong yet commonly ignored learning signals. We showcase the practical application of LogicDiag in the data-hungry segmentation scenario, where we formalize the structured abstraction of semantic concepts as a set of logic rules.
arXiv Detail & Related papers (2023-08-24T06:50:07Z)
Some Preliminary Steps Towards Metaverse Logic [0.8594140167290096]
We look in the present work for a logic that would be powerful enough to handle the situations arising both in the real and in the fictional underlying application domains. The discussion was kept at a rather informal level, always trying to convey the intuition behind the theoretical notions in natural language terms.
arXiv Detail & Related papers (2023-07-10T09:13:22Z)
Counterfactuals Modulo Temporal Logics [1.90365714903665]
Lewis' theory of counterfactuals is the foundation of many contemporary notions of causality. We extend this theory in the temporal direction to enable symbolic counterfactual reasoning on infinite sequences.
arXiv Detail & Related papers (2023-06-15T07:40:36Z)
Learnability with PAC Semantics for Multi-agent Beliefs [38.88111785113001]
The tension between deduction and induction is perhaps the most fundamental issue in areas such as philosophy, cognition and artificial intelligence. Valiant recognised that the challenge of learning should be integrated with deduction. Although weaker than classical entailment, it allows for a powerful model-theoretic framework for answering queries.
arXiv Detail & Related papers (2023-06-08T18:22:46Z)
The Transformation Logics [58.35574640378678]
We introduce a new family of temporal logics designed to balance the trade-off between expressivity and complexity. Key feature is the possibility of defining operators of a new kind that we call transformation operators. We show them to yield logics capable of creating hierarchies of increasing expressivity and complexity.
arXiv Detail & Related papers (2023-04-19T13:24:04Z)
Non-Deterministic Approximation Fixpoint Theory and Its Application in Disjunctive Logic Programming [11.215352918313577]
Approximation fixpoint theory is a framework for studying the semantics of nonmonotonic logics. We extend AFT to dealing with non-deterministic constructs that allow to handle indefinite information. The applicability and usefulness of this generalization is illustrated in the context of disjunctive logic programming.
arXiv Detail & Related papers (2022-11-30T18:58:32Z)
Nonunitary Gate Operations by Dissipation Engineering [0.0]
We propose protocols that harness dissipation to realize the nonunitary evolution required for irreversible gate operations. We exemplify our approach considering several classical logic operations, such as the OR, NOR, and XOR gates. Our study shows that irreversible logic operations can be efficiently performed on realistic quantum systems and that dissipation engineering is an essential tool for obtaining nonunitary evolutions.
arXiv Detail & Related papers (2022-01-28T18:53:10Z)
Neuro-Symbolic Entropy Regularization [78.16196949641079]
In structured prediction, the goal is to jointly predict many output variables that together encode a structured object. One approach -- entropy regularization -- posits that decision boundaries should lie in low-probability regions. We propose a loss, neuro-symbolic entropy regularization, that encourages the model to confidently predict a valid object.
arXiv Detail & Related papers (2022-01-25T06:23:10Z)
Logical blocks for fault-tolerant topological quantum computation [55.41644538483948]
We present a framework for universal fault-tolerant logic motivated by the need for platform-independent logical gate definitions. We explore novel schemes for universal logic that improve resource overheads. Motivated by the favorable logical error rates for boundaryless computation, we introduce a novel computational scheme.
arXiv Detail & Related papers (2021-12-22T19:00:03Z)
Transporting Causal Mechanisms for Unsupervised Domain Adaptation [98.67770293233961]
We propose Transporting Causal Mechanisms (TCM) to identify the confounder stratum and representations. TCM achieves state-of-the-art performance on three challenging Unsupervised Domain Adaptation benchmarks.
arXiv Detail & Related papers (2021-07-23T07:25:15Z)
Universal Fault-Tolerant Quantum Computing with Stabiliser Codes [0.0]
Quantum computers should have both universal and fault-tolerant logic gates. A number of no-go theorems constrain the ways in which a set of fault-tolerant logic gates can be universal. We present a general framework for universal fault-tolerant logic with stabiliser codes. We show how non-unitary implementations of logic gates provide a general approach to circumvent the no-go theorem.
arXiv Detail & Related papers (2020-12-09T19:01:07Z)
Logical Neural Networks [51.46602187496816]
We propose a novel framework seamlessly providing key properties of both neural nets (learning) and symbolic logic (knowledge and reasoning) Every neuron has a meaning as a component of a formula in a weighted real-valued logic, yielding a highly intepretable disentangled representation. Inference is omni rather than focused on predefined target variables, and corresponds to logical reasoning.
arXiv Detail & Related papers (2020-06-23T16:55:45Z)

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