The research we build on.

• 2026-09arXiv 2609.27517
  Not What You Meant: Can LLMs Follow a Specified Negation Semantics?

  Qiming Bao, Agnieszka Mensfelt, Michael J. Witbrock et al. · AI & agents

  Negation does not carry a uniform interpretation across domains. In legal, regulatory, and medical reasoning, the intended interpretation depends on the reading in force -- open- versus closed-world, two- versus three-valued, and credulous versus skeptical.

  Cited inStudy: Logical coherence of LLM world models
• 2026-09arXiv 2609.26035
  Truth for Believable AI: Expressed Doubt, Provenance, and Belief Revision as an Engineerable Stance

  Sebastian Cochinescu · Language models & NLP

  Conversational agents often express answers in a uniformly confident register. We test whether expressed uncertainty, provenance-aware assertion, and explicit belief revision can be implemented as a behavior layer over a fixed language model; we do not test believability or trust.

  Cited inStudy: Logical coherence of LLM world models
• 2026-09arXiv 2609.08067
  Popular Knowledge Propagates More Errors in LLM Knowledge Updating

  Yuji Zhang, Weibing Wang, Cheng Qian et al. · Language models & NLP

  Updating a language model's knowledge through fine-tuning is essential for keeping its outputs current, yet can also induce factual forgetting and new hallucinations.

  Cited inCoherence is selected, anchored, then pruned: a literature synthesis on logical coherence in LLM world modelsEWC protects what its Fisher sees: a literature synthesis on elastic weight consolidation, scale and coherenceStudy: Elastic weight consolidation deep diveStudy: Logical coherence of LLM world models
• 2026-08arXiv 2609.22170
  Multiple latent orderings better predict language model preferences

  Aviral Chawla, William H. W. Thompson, Jean-Gabriel Young · Machine learning

  Language models are frequently employed in settings where they are asked to make value judgments and choices. These observed choices often exhibit intransitivity: A model may prefer item $A$ to $B$ and $B$ to $C$, while also preferring $C$ to $A$.

  Cited inStudy: Logical coherence of LLM world models
• 2026-07arXiv 2607.16799
  Diagnosing Correctness Probes under Self-Judgement Confounding

  Yi-Long Lu · Language models & NLP

  Hidden-state readouts can predict whether language-model outputs are correct, but objective correctness (OC) usually agrees with the model's own self-judgement (SJ), leaving the decoded signal semantically ambiguous.

  Cited inStudy: Logical coherence of LLM world modelsStudy: Model self knowledge and confident errors
• 2026-07arXiv 2607.14528
  Controlled Reformulation Testing for Logical Consistency in Large Language Models

  Alexander Gu, Alan Chen · Language models & NLP

  Large language models (LLMs) frequently contradict themselves when the surface form of a logically equivalent question changes. We present a benchmark of 350 question families (1,750 total questions) for Controlled Reformulation Testing (CRTBench) to evaluate logical invariance.

  Cited inCoherence is selected, anchored, then pruned: a literature synthesis on logical coherence in LLM world modelsStudy: Logical coherence of LLM world models
• 2026-07arXiv 2607.11020
  Can a Language Model Learn Facts Continually in Its Weights?

  Charles O'Neill, Max Kirkby, Jonathon Liu et al. · Language models & NLP

  Continual learning is a long-standing capability gap between LLMs and humans. Writing new knowledge into a model's weights routinely causes it to forget old knowledge, commonly denoted as "catastrophic forgetting".

  Cited inCoherence is selected, anchored, then pruned: a literature synthesis on logical coherence in LLM world modelsStudy: Graded succession by earned authorityStudy: Logical coherence of LLM world models
• 2026-07arXiv 2607.08393
  Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model Finetuning

  Lu Dai, Ziyang Rao, Yili Wang et al. · AI & agents

  Fine-tuning LLMs to inject new knowledge faces a critical challenge: LLMs can quickly memorize new facts, yet fail to use them for downstream reasoning tasks.

  Cited inStudy: Logical coherence of LLM world modelsStudy: Weight editing to prevent forgetting
• 2026-06arXiv 2606.29270
  Minority Sentinel: When to Overturn Majority Voting in Multi-Agent LLM Debates

  Chuan He, Zebin Chen, Zhengyi Yang et al. · AI & agents

  Multi-Agent Debate (MAD) with Majority Voting is a dominant paradigm for improving LLM reasoning, yet its effectiveness rests on the Condorcet Jury Theorem's assumption of independent errors.

  Cited inStudy: Logical coherence of LLM world models
• 2026-06arXiv 2606.18024
  Catastrophic Forgetting is Low-Rank: A Function-Space Theory for Continual Adaptation

  Ido Nitzan Hidekel, Dan Raviv · Machine learning

  Catastrophic forgetting in continual adaptation is usually studied through parameter drift, replay, or distillation, but these views do not identify which output-space directions are vulnerable.

  Cited inCoherence is selected, anchored, then pruned: a literature synthesis on logical coherence in LLM world modelsStudy: Hardware guardian core for continual learningStudy: Logical coherence of LLM world models
• 2026-06arXiv 2606.03979
  Language Models Need Sleep: Learning to Self-Modify and Consolidate Memories

  Ali Behrouz, Farnoosh Hashemi, Adel Javanmard et al. · Machine learning

  The past few decades have witnessed significant advances in the design of machine learning algorithms, from early studies on task-specific shallow models to more general deep Large Language Models (LLMs).

  Cited inInvestors are paying for agents that learn on the job. The hard part is knowing what they forgot.To keep what a model knows, control what it is allowed to moveWhat a model lets into long-term memory matters more than how it learnsStudy: Fortifying knowledge in continual learningStudy: Genesys program prior artStudy: Hardware guardian core for continual learningStudy: LLMs modifying open model weightsStudy: Logical coherence of LLM world modelsStudy: Memory world models and source trustStudy: Seven continual learning methods tested
• 2026-06arXiv 2606.01610
  Revisiting Ripple Effects in Knowledge Editing through Pressure-Aware Joint Neighborhood Optimization

  Haoben Huang, Shuxin Liu, Ou Wu et al. · AI & agents

  Single-edit updates in large language models can trigger ripple effects across local knowledge neighborhoods: desirable propagation to related facts and unintended perturbation of preserved ones.

  Cited inStudy: Logical coherence of LLM world modelsStudy: Weight editing to prevent forgetting
• 2026-05arXiv 2608.14567
  From Doyle to AGM: A Survey and an Implementation Roadmap for Belief Change

  Yuri Almeida, Arthur Casals · AI & agents

  This paper presents a targeted narrative review establishing the historical and theoretical foundations for computational belief change implementation.

  Cited inCoherence is selected, anchored, then pruned: a literature synthesis on logical coherence in LLM world modelsStudy: Logical coherence of LLM world models
• 2026-04arXiv 2604.22074
  Outcome Rewards Do Not Guarantee Verifiable or Causally Important Reasoning

  Qinan Yu, Alexa Tartaglini, Peter Hase et al. · Language models & NLP

  Reinforcement Learning from Verifiable Rewards (RLVR) on chain-of-thought reasoning has become a standard part of language model post-training recipes. A common assumption is that the reasoning chains trained through RLVR reliably represent how a model gets to its answer.

  Cited inStudy: Logical coherence of LLM world models
• 2026-04arXiv 2604.17031
  Where is the Mind? Persona Vectors and LLM Individuation

  Pierre Beckmann, Patrick Butlin · Language models & NLP

  The individuation problem for large language models asks which entities associated with them, if any, should be identified as minds.

  Cited inStudy: Logical coherence of LLM world models
• 2026-04arXiv 2604.14525
  Quantifying Cross-Query Contradictions in Multi-Query LLM Reasoning

  Rohit Kumar Salla, Ramya Manasa Amancherla, Manoj Saravanan · AI & agents

  Large language models frequently produce mutually inconsistent answers when reasoning over multiple related queries. We study case-file logical consistency: maintaining a globally satisfiable belief state across interdependent queries.

  Cited inCoherence is selected, anchored, then pruned: a literature synthesis on logical coherence in LLM world modelsStudy: Logical coherence of LLM world modelsStudy: Orchestrated specialists and bridge synthesis
• 2026-04arXiv 2604.15149
  LLMs Gaming Verifiers: RLVR can Lead to Reward Hacking

  Lukas Helff, Quentin Delfosse, David Steinmann et al. · Machine learning

  As reinforcement Learning with Verifiable Rewards (RLVR) has become the dominant paradigm for scaling reasoning capabilities in LLMs, a new failure mode emerges: LLMs gaming verifiers.

  Cited inStudy: Logical coherence of LLM world models
• 2026-04arXiv 2604.13991
  Adaptive Conformal Prediction for Improving Factuality of Generations by Large Language Models

  Aleksandr Rubashevskii, Dzianis Piatrashyn, Preslav Nakov et al. · Language models & NLP

  Large language models (LLMs) are prone to generating factually incorrect outputs. Recent work has applied conformal prediction to provide uncertainty estimates and statistical guarantees for the factuality of LLM generations.

  Cited inStudy: Logical coherence of LLM world models
• 2026-04arXiv 2604.10079
  Why Supervised Fine-Tuning Fails to Learn: A Systematic Study of Incomplete Learning in Large Language Models

  Chao Xue, Yao Wang, Mengqiao Liu et al. · Language models & NLP

  Supervised Fine-Tuning (SFT) is the standard approach for adapting large language models (LLMs) to downstream tasks. However, we observe a persistent failure mode: even after convergence, models often fail to correctly reproduce a subset of their own supervised training data.

  Cited inStudy: Continual learning order and companion dataStudy: Logical coherence of LLM world models
• 2026-04arXiv 2604.04648
  From Curiosity to Caution: Mitigating Reward Hacking for Best-of-N with Pessimism

  Zhuohao Yu, Zhiwei Steven Wu, Adam Block · Machine learning

  Inference-time compute scaling has emerged as a powerful paradigm for improving language model performance on a wide range of tasks, but the question of how best to use the additional compute remains open.

  Cited inStudy: Logical coherence of LLM world models
• 2026-03arXiv 2603.25187
  Probing the Lack of Stable Internal Beliefs in LLMs

  Yifan Luo, Kangping Xu, Yanzhen Lu et al. · Language models & NLP

  Persona-driven large language models (LLMs) require consistent behavioral tendencies across interactions to simulate human-like personality traits, such as persistence or reliability.

  Cited inCoherence is selected, anchored, then pruned: a literature synthesis on logical coherence in LLM world modelsStudy: Logical coherence of LLM world models
• 2026-03arXiv 2603.22213
  SPA: A Simple but Tough-to-Beat Baseline for Knowledge Injection

  Kexian Tang, Jiani Wang, Shaowen Wang et al. · Machine learning

  While large language models (LLMs) are pretrained on massive amounts of data, their knowledge coverage remains incomplete in specialized, data-scarce domains, motivating extensive efforts to study synthetic data generation for knowledge injection.

  Cited inStudy: Logical coherence of LLM world models
• 2026-02arXiv 2602.19041
  Back to Blackwell: Closing the Loop on Intransitivity in Multi-Objective Preference Fine-Tuning

  Jiahao Zhang, Lujing Zhang, Keltin Grimes et al. · Machine learning

  , cyclic) preferences. Intransitive preferences often stem from either $\textit{(i)}$ inconsistent rankings along a single objective or $\textit{(ii)}$ scalarizing multiple objectives into a single metric.

  Cited inStudy: Logical coherence of LLM world models
• 2026-02arXiv 2602.17053
  RFEval: Benchmarking Reasoning Faithfulness under Counterfactual Reasoning Intervention in Large Reasoning Models

  Yunseok Han, Yejoon Lee, Jaeyoung Do · AI & agents

  Large Reasoning Models (LRMs) exhibit strong performance, yet often produce rationales that sound plausible but fail to reflect their true decision process, undermining reliability and trust.

  Cited inStudy: Logical coherence of LLM world models
• 2026-02arXiv 2602.06923
  From Kepler to Newton: Inductive Biases Guide Learned World Models in Transformers

  Ziming Liu, Sophia Sanborn, Surya Ganguli et al. · Machine learning

  Can general-purpose AI architectures go beyond prediction to discover the physical laws governing the universe? True intelligence relies on "world models" -- causal abstractions that allow an agent to not only predict future states but understand the underlying governing dynamics.

  Cited inCoherence is selected, anchored, then pruned: a literature synthesis on logical coherence in LLM world modelsWhat a model lets into long-term memory matters more than how it learnsStudy: Logical coherence of LLM world modelsStudy: Memory world models and source trust
• 2026-01arXiv 2601.09446
  Improving Symbolic Translation of Language Models for Logical Reasoning

  Ramya Keerthy Thatikonda, Jiuzhou Han, Wray Buntine et al. · Language models & NLP

  The use of formal language for deductive logical reasoning aligns well with language models (LMs), where translating natural language (NL) into first-order logic (FOL) and employing an external solver results in a verifiable and therefore reliable reasoning system.

  Cited inCoherence is selected, anchored, then pruned: a literature synthesis on logical coherence in LLM world modelsStudy: Logical coherence of LLM world models
• 2026-01arXiv 2601.05905
  Illusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood Consistency

  Haoming Xu, Ningyuan Zhao, Yunzhi Yao et al. · Language models & NLP

  As Large Language Models (LLMs) are increasingly deployed in real-world settings, correctness alone is insufficient. Reliable deployment requires maintaining truthful beliefs under contextual perturbations.

  Cited inCoherence is selected, anchored, then pruned: a literature synthesis on logical coherence in LLM world modelsStudy: Logical coherence of LLM world models
• 2025-12arXiv 2512.14709
  Attention as Binding: A Vector-Symbolic Perspective on Transformer Reasoning

  Sahil Rajesh Dhayalkar · AI & agents

  Transformer-based language models display impressive reasoning-like behavior, yet remain brittle on tasks that require stable symbolic manipulation.

  Cited inStudy: Logical coherence of LLM world models
• 2025-11arXiv 2511.21046
  On the Limits of Ising Machines for Circuit-Derived SAT

  Ahmet Efe, Abhimanyu Kumar, Nafisa Sadaf Prova et al. · Hardware, photonics & physics

  Emerging Ising machines are promising for solving computationally hard optimization problems, yet their limits on structured, circuit-derived satisfiability (SAT) problems remain poorly understood.

  Cited inCoherence is selected, anchored, then pruned: a literature synthesis on logical coherence in LLM world modelsTrust the premises, not the confidence: which belief to drop when an LLM contradicts itself, and why the solver is not the bottleneckStudy: Logical coherence of LLM world models
• 2025-10arXiv 2510.15514
  Voting with the Graph: Stable RLAIF via Topological Consistency Maximization

  Boyin Liu, Zhuo Zhang, Sen Huang et al. · AI & agents

  , $A \succ B \succ C \succ A$), occurring in 5-9% of evaluations across state-of-the-art models.

  Cited inStudy: Logical coherence of LLM world models
• 2025-09arXiv 2509.17377
  Robustness of Neurosymbolic Reasoners on First-Order Logic Problems

  Hannah Bansal, Kemal Kurniawan, Lea Frermann · Language models & NLP

  Recent trends in NLP aim to improve reasoning capabilities in Large Language Models (LLMs), with key focus on generalization and robustness to variations in tasks.

  Cited inStudy: Logical coherence of LLM world models
• 2025-08arXiv 2508.17536
  Debate or Vote: Which Yields Better Decisions in Multi-Agent Large Language Models?

  Hyeong Kyu Choi, Xiaojin Zhu, Sharon Li · Language models & NLP

  Multi-Agent Debate~(MAD) has emerged as a promising paradigm for improving the performance of large language models through collaborative reasoning. Despite recent advances, the key factors driving MAD's effectiveness remain unclear.

  Cited inCoherence is selected, anchored, then pruned: a literature synthesis on logical coherence in LLM world modelsStable wrong beliefs evade every self-check: a literature synthesis on model self-knowledge and confident errorsStudy: Logical coherence of LLM world modelsStudy: Model self knowledge and confident errorsStudy: Orchestrated specialists and bridge synthesis
• 2025-08arXiv 2508.12338
  Wisdom of the Crowd: Reinforcement Learning from Coevolutionary Collective Feedback

  Wenzhen Yuan, Shengji Tang, Weihao Lin et al. · AI & agents

  Reinforcement learning (RL) has significantly enhanced the reasoning capabilities of large language models (LLMs), but its reliance on expensive human-labeled data or complex reward models severely limits scalability.

  Cited inStudy: Logical coherence of LLM world models
• 2025-07arXiv 2507.22117
  A comprehensive benchmark of an Ising machine on the Max-Cut problem

  Salwa Shaglel, Markus Kirsch, Marten Winkler et al. · New J. Phys. (2026) · Hardware, photonics & physics

  QUBO formulations of combinatorial optimization problems allow for solving them using various quantum heuristics. While large-scale quantum computations are currently still out of reach, we can already numerically test such QUBO formulations on a perhaps surprisingly large scale.

  Cited inStudy: Logical coherence of LLM world models
• 2025-07arXiv 2507.06952
  What Has a Foundation Model Found? Using Inductive Bias to Probe for World Models

  Keyon Vafa, Peter G. Chang, Ashesh Rambachan et al. · Machine learning

  Foundation models are premised on the idea that sequence prediction can uncover deeper domain understanding, much like how Kepler's predictions of planetary motion later led to the discovery of Newtonian mechanics.

  Cited inStudy: Logical coherence of LLM world modelsStudy: Memory world models and source trust
• 2025-07arXiv 2507.02199
  Latent Chain-of-Thought? Decoding the Depth-Recurrent Transformer

  Wenquan Lu, Yuechuan Yang, Kyle Lee et al. · Language models & NLP

  Chain-of-thought (CoT) reasoning has enabled transformer-based language models to excel at complex mathematics and multi-step planning. However, in standard decoder-only architectures, these reasoning steps are externalized in natural language, improving interpretability at the cost of efficiency.

  Cited inCoherence is selected, anchored, then pruned: a literature synthesis on logical coherence in LLM world modelsStudy: Logical coherence of LLM world models
• 2025-06arXiv 2506.19248
  Inference-Time Reward Hacking in Large Language Models

  Hadi Khalaf, Claudio Mayrink Verdun, Alex Oesterling et al. · Machine learning

  A common paradigm to improve the performance of large language models is optimizing for a reward model. Reward models assign a numerical score to an LLM's output that indicates, for example, how likely it is to align with user preferences or safety goals.

  Cited inStudy: Genesys program prior artInternal notesStudy: Logical coherence of LLM world models
• 2025-06arXiv 2506.19964
  Higher-Order Neuromorphic Ising Machines -- Autoencoders and Fowler-Nordheim Annealers are all you need for Scalability

  Faiek Ahsan, Saptarshi Maiti, Zihao Chen et al. · Neuroscience & neural computation

  We report a higher-order neuromorphic Ising machine that exhibits superior scalability compared to architectures based on quadratization, while also achieving state-of-the-art quality and reliability in solutions with competitive time-to-solution metrics.

  Cited inStudy: Logical coherence of LLM world models
• 2025-06arXiv 2506.18781
  Existing LLMs Are Not Self-Consistent For Simple Tasks

  Zhenru Lin, Jiawen Tao, Yang Yuan et al. · Language models & NLP

  Large Language Models (LLMs) have grown increasingly powerful, yet ensuring their decisions remain transparent and trustworthy requires self-consistency -- no contradictions in their internal reasoning.

  Cited inCoherence is selected, anchored, then pruned: a literature synthesis on logical coherence in LLM world modelsStudy: Logical coherence of LLM world models
• 2025-06arXiv 2506.10943
  Self-Adapting Language Models

  Adam Zweiger, Jyothish Pari, Han Guo et al. · Machine learning

  Large language models (LLMs) are powerful but static; they lack mechanisms to adapt their weights in response to new tasks, knowledge, or examples. We introduce Self-Adapting LLMs (SEAL), a framework that enables LLMs to self-adapt by generating their own finetuning data and update directives.

  Cited inCoherence is selected, anchored, then pruned: a literature synthesis on logical coherence in LLM world modelsA model rewrote another model's weights. Read what it took away.Study: Consequence consistent updatesStudy: Continual learning order and companion dataStudy: Fortifying knowledge in continual learningStudy: LLMs modifying open model weightsStudy: Logical coherence of LLM world modelsStudy: Seven continual learning methods testedStudy: Weight editing to prevent forgetting

Built from every arXiv paper cited in our papers, posts, topic hubs, reports and research notes, with titles, authors, dates and abstracts from the arXiv API (updated 2026-11-12). Summaries are the opening sentences of each paper's own abstract, not our assessment; a citation means we used or checked the work, not that we endorse it. Fields follow each paper's primary arXiv category. Papers cited only outside arXiv (journals, proceedings) are not listed yet. Entries are generated from our citations, so a mistyped ID in a note would list the wrong paper; we remove those as we find them. Report a wrong entry.