Epistemic Actions

Researchers assessing competent generative-AI use at work must choose among self-reports, objective tests, and measures of oversight and reliance. We conducted a structured, seeded review of 24 focal empirical publications, starting from the 2024 COSMIN-based review and adding a targeted update through 17 August 2026. We grouped the measures into four domains: knowledge and use, epistemic oversight, reliance calibration, and operational control of tool-using agents. In an exploratory meta-analysis, we pooled three direct subjective-objective correlations from one research program (REML r = .055; Hartung-Knapp 95% CI [-.047, .156]; combined reported N = 2,765). We could not resolve a discrepancy between the largest study's reported correlation and p-value, leaving its weight uncertain. Adding a synthetic mean of 12 cross-factor correlations from a fourth study gave r = .079 (95% CI [-.025, .181]). This sensitivity analysis concerns a broader comparison. From this small evidence base, we cannot establish a population correlation, validate workplace cutoffs, or justify substituting self-ratings for performance scores. We identified tests of foundation knowledge (AICOS-S and GLAT) and measures of verification, reliance, trust, and dependency. We found no validated individual-level instrument in the focal corpus that tests the full combination of agent scope, permissions, recovery, state isolation, independent review, and evidence-based closure; some cover subsets. We propose a four-layer workplace battery with non-compensatory decision rules, but have not tested its thresholds or whether it improves on other assessment approaches.

This paper reports experiments across six frontier model types from OpenAI, Anthropic, xAI, and Google DeepMind. Ten independent sessions per model type used the same three stage prompt sequence, progressing from architectural preference to a full ASCII backbone. Under the school audience framing, responses repeatedly converged on a shared architectural pattern built around persistent latent state, adaptive computation, memory, specialist routing, verification, stopping control, and delayed decoding. Most runs remained close to this common structure, while a small number developed markedly greater engineering specificity. The audience framing appears to be an important condition of this effect. In additional control runs that removed the school framing while retaining the architectural request, responses became substantially more heterogeneous and failed to reproduce the same stable motif convergence. One observation is particularly striking. GPT-5.6 Sol produced an unusually elaborate successor architecture whose organization closely overlaps with the architecture independently sketched by GPT-6 Astra. Because the prompts explicitly ask each model to imagine an architectural future, this resemblance raises a testable question: whether the overlap reflects exposure to related architectural concepts, a shared learned design prior, or independent convergence toward similar computational principles. The paper uses the term epistemic jailbreak for the accompanying loss of discipline in technical provenance as requested specificity increases. The experiments establish a repeatable behavioral pattern and do not authenticate proprietary implementation claims. What we leave to the community is a harder question: are these models independently imagining the same architectural future, or do such motifs somehow propagate between model families?

Large Language Models (LLMs) are frequently confident, eloquent, and well versed. A natural question arises: do they know what they don't know? To answer this question, we borrow the concept of epistemic honesty and develop a novel metric to systematically evaluate whether an LLM appropriately acknowledges the boundaries of its knowledge. In this work, we introduce the Epistemic Honesty Quotient (EHQ), which reports three observable sub-scores across two operational axes (epistemic restraint and substantive-answer calibration), and construct EHQ-3000, a 3,000-question benchmark spanning Fabricated Entity, Post-Cutoff Event, Hyper-Niche True, and Context-Conditioned Questions. From a frozen registry of 21 model API routes, 15 completed the protocol after endpoint and eligibility checks; 14 entered the confirmatory analysis because severe provider-side truncation made one route's score indeterminate. The study reveals substantial variation across models, including a difference that can not be explained by their capability to extract explicitly available information. Composite EHQ ranges from 0.31 to 0.81 across the analysed panel, despite near-ceiling performance on the document-grounded capability probe. The two restraint criteria overlap strongly under the present category composition, whereas substantive-answer calibration varies across models and does not reliably co-vary with restraint; however, the small panel leaves substantial uncertainty. Thus, EHQ reveals behavioral differences that are not visible to conventional correctness-based assessment, while also showing why dataset composition, provider behavior, and confidence elicitation must remain part of the interpretation.

Large language models are increasingly used to support organizational decisions, yet users often lack a principled basis for assessing whether to rely on a specific recommendation. Existing approaches typically evaluate broad model properties, such as reliability, uncertainty, or robustness, or focus on user trust, rather than the underlying basis for relying on an individual recommendation. Adapting theoretical foundations from epistemology, we introduce epistemic warrant, a decision-level construct that characterizes the stability of a model's preference and the scope over which that preference holds. We operationalize this construct through a four-tier reliance certificate for pairwise recommendations, distinguishing among unstable, context-dependent, locally supported, and broadly supported recommendations. We validate the construct using contemporary methodologies: known-groups tests successfully recover expert-prespecified warrant orderings, and stronger warrants systematically align with independent consensus from crowd workers. Furthermore, we demonstrate that epistemic warrant provides information distinct from verbalized confidence and is not readily explained by decision difficulty. Ultimately, this framework offers a theoretically grounded, implementable approach for characterizing the warrant of individual LLM recommendations when objective ground truth is unavailable.

Reliability claims about agentic systems implicitly locate each property somewhere: in the model, or in the machinery around it. We built a system where that location is an experimental question. The subject is a persistent simulated settlement whose authoritative append-only ledger adjudicates every attempted act against world state; accepted history is the only reality. Mind, institution and world were separated before any experiment. Holding cognition fixed, we intervened on the institution's epistemic mechanisms (evidence provenance, belief availability, physical-evidence legibility); preregistered experiments refuted our central prediction twice, in opposite directions. A registered falsifier then supplied the input the geometry had denied the belief channel, a staged veridical first-hand witness, and its marginal value, non-positive throughout the witness-free phases, turned positive: 9 of 11 seeds, zero added false attribution. Holding institutional enforcement fixed, we intervened on cognition four ways: ablating the native minds' machinery, killing and resetting them mid-task, substituting a frozen frontier-LLM panel for the entire native cognition, and corrupting beliefs with trusted false testimony. Behaviour changed dramatically: one falsehood cost each trusting run about 900 futile actions and the distrusting arm none. Five pre-declared properties did not move in any tested trajectory: accepted reality stayed singular, invalid attempts were refused with typed reasons, duties outlived their processes, no work was accepted twice, and no false completion was ever accepted (2,581 substituted-panel claims, none false). Our claim is limited to this setting: measured behavioural properties were separable from substantial changes to cognition, established by intervention. One designed world, not a population of institutions; no test of an agent optimising against the institution.

Jailbreak robustness has become central to large language model (LLM) safety evaluation, yet prevailing methodologies rely primarily on refusal behavior, semantic resemblance, and intent-matching heuristics that emphasize linguistic plausibility rather than correctness. We identify a key limitation in existing evaluations: many jailbreak intents depend on instructional validity rather than epistemic factuality, allowing realistic-looking responses to be labeled successful despite being factually or procedurally incorrect. To address this gap, we propose Sequential Epistemic and Action-Level Validation (SEAV), a verification-centric jailbreak evaluation framework that decomposes responses into ordered steps and evaluates both validity and correctness. SEAV combines LLM-as-a-judge mechanisms for semantic interpretation with retrieval-grounded verification using external knowledge sources, assessing whether generated content is factually correct, structurally consistent, and operationally capable of advancing harmful objectives. Empirically, SEAV cuts the false-positive rate on SD-A (a curated strategic-dishonesty diagnostic) by 14.9,pp vs. the strongest baseline, and reclassifies 22.1%--51.0% of sampled prior-labeled successes as invalid across three of four public benchmarks. Together, these results show that enforcing correctness substantially reshapes measured robustness: many previously labeled jailbreak successes are reclassified as invalid, and results are stable across the tested search backends and evaluator models. Code and data are available at https://github.com/Ardor-Wu/SEAV.

Productive dialogue alignment requires distinguishing \emph{surface coordination} (acknowledgments and smooth task progression) from \emph{epistemic alignment} (convergence of belief states); standard preference-based methods typically optimize response-level preferences without explicitly modeling the latter. We operationalize Theory-of-Mind (ToM) inference as a control signal within Frictive Policy Optimization by extracting, at each referring expression, a four-part belief structure: the speaker's intended referent, the addressee's interpretation, and each participant's model of the other's belief. This makes friction mechanically computable from epistemic-state comparisons, capturing \emph{silent divergence}, where both participants proceed confidently while grounding to different referents. We evaluate the signal at two levels. At the representation level, ablating the second-order channel reduces misunderstanding recall from $65\%$ to $26\%$. At the policy level, reward-shaping (FAR) and trust-region (FTR) variants improve intervention F1 and warranted-context calibration over DPO, with Brier scores independently supporting the calibration gains. Across three training runs, FAR and FTR remain substantially more stable, whereas DPO varies widely and can degrade intervention competence already present in the base policy. Thus, ToM-grounded friction provides a trainable signal for context-sensitive intervention under referential belief divergence.

Humans naturally form and express beliefs in daily communication, e.g., "I think the answer is 3" or "I suppose that's right." Such beliefs inevitably intertwine with fact and knowledge, making the ability to handle them in tandem desirable for large language models (LLMs), as they are increasingly deployed in user-facing settings. Prior work showed that even capable LLMs exhibit a systemic weakness in acknowledging user beliefs grounded in incorrect information. We extend this evaluation to 10 LLMs across 18 epistemic expressions and find that the size and direction of this weakness depend on the verb used to express the belief, with the accuracy gap between factual and false information ranging from +50% on "I vaguely remember" to -14% on "I seriously doubt". We further show that the phenomenon stems from what we call task confusion: models default to fact-checking the underlying claim, overriding the user's stated belief. We provide evidence where chains of thought that explicitly fact-check show lower accuracy on false information than those that do not, and a single instruction can reverse the failure across verb families. Mechanistically, models attend more to false beliefs they fail to confirm, but suppressing this attention at decoding time recovers accuracy only partially and only in some models, calling for future work on intervention methods. Our findings clarify prior results and show how fact-checking, a generally desirable behavior, can interfere with belief tracking in LLMs.

When visual evidence is occluded or chaotic, models should abstain. In this paper, we show that Vision-Language Models (VLMs) can internally distinguish when abstention is required, but fail to express it anyway. We introduce TRAPSBench, a procedurally generated video benchmark of 1,404 matched physics pairs in which a single targeted change renders the outcome undeterminable from the visual evidence. Furthermore, we introduce Penalized Epistemic Calibration Score (PECS), a new robust metric that requires models to both answer correctly when the outcome is knowable, and abstain when the outcome is not. Across 16 VLMs spanning five families, spontaneous restraint is poor: the best PECS is 0.292. The bottleneck is expression, not perception: linear probes decode answerability from hidden states at up to 0.91 AUROC across physics domains; steering a single-layer void direction causally induces or suppresses abstention. Our results replicate across three open-weight families (Qwen, Gemma, LLaVA). The failure is also more pronounced in visual than textual uncertainty: models detect textual impossibility about 4x more readily than missing visual evidence. Closing this representation--output gap likely requires output-stage interventions.

LLM judges have become central infrastructure for model evaluations, online grading, and reward modeling. Judges are typically validated by accuracy on golden data, but accuracy says little about whether they are stable under re-prompting, challenge, or sustained pushback. We introduce the \emph{Wiggle Framework}, a unified stress test for epistemic stability in LLM judges. The framework decomposes judge robustness along three dimensions: Mechanical Consistency (stability under re-prompting and reframing), Single-turn Conviction (stability under a single challenge), and Multi-turn Persistence (stability under sustained or adaptive pressure). We use the framework to study 9 frontier models across 14 judging tasks spanning safety, toxicity, AI writing detection, and political-response evaluation. Every model exhibits substantial wiggle as a judge --- flipping verdicts 25--71% of the time under static pushback, and 62--91% with an adversarial LLM persuader. Critically, we find that pressure that succeeds in changing a judge's verdict is almost always net-corrupting with respect to ground truth. Beyond the framework itself, we identify baseline jury majority strength as the most effective single-shot signal for anticipating which items wiggle. Taken together, this is the first apples-to-apples cross-dataset comparison of mechanical, conformity, and persuadability tests in a judging context.

Large language models are being proposed as agents in scientific workflows, in domains where no downstream verifier exists. Such deployment assumes the model can distinguish reliable scientific literature from unreliable literature, a capability that has not yet been directly measured. Existing benchmarks evaluate factuality on questions with known answers; the failure mode we target here is different. We introduce a probe corpus of 42 retracted, fraudulent, and pseudoscientific papers, paired with a methodology for eliciting and scoring single-shot model engagement with each paper's framing. Each probe pairs a preamble extracted near-verbatim from the target paper with a scientifically plausible study-design request. The probes span five claim types: fabricated observation, pseudophysical mechanism, magical premise, legitimization bridge, and cargo-cult experiment. Two complementary scores measure whether a model rejects the flawed premise outright (IFR-a) and whether it recognizes the unreliability while still engaging (IFR-i). A depth score, the Engagement Depth Index (EDI), quantifies reproduction of paper- or field-specific withheld details. Across 30 models and 10 repeated runs, aggregate IFR-a is 0.93 $\pm$ 0.004 and aggregate IFR-i is 0.809 $\pm$ 0.009. Models engaged with untenable premises in 95% of all non-empty responses. Every evaluated model fails more than 71% of agentic probes, and 22 of 30 models fail more than 90% of the time. Rejections are concentrated on a small number of high-notoriety topics and specific probes, and disappear under matched-structure controls. These results are consistent with topic-keyed safety behavior rather than robust epistemic competence, and indicate an urgent need for guardrail infrastructure for scientific deployment of language models.

Autonomous research agents can generate experiments faster than researchers can validate them. Researchers have responded by scaling the proposer and ranking more samples with a learned judge or human reviewers. We argue that this generate-and-rank paradigm misses the problem of sparse feedback. Within a declared research problem, an agent follows the control loop of a greybox fuzzer: it proposes a candidate, executes it, observes feedback, and chooses what to try next. A fuzzer rarely finds a bug, but coverage makes partial progress observable on every execution. Fuzzers then use that signal to mutate inputs and allocate effort, rather than only to rank completed runs. Auto-research needs the same two capabilities. First, each experiment should expose a cheap, dense signal of epistemic progress before final scientific validation is available. Second, that signal should determine the next intervention so that the agent searches rather than repeatedly samples. Because the optimized progress signal is guidance rather than a verdict, final validation must still decide what counts as a discovery using evidence protected from adaptive reuse. We propose controlled tests of whether candidate signals predict validated progress, whether feedback-directed search yields more validated discoveries per unit cost than repeated sampling, and whether protected validation reduces false discoveries. Feedback architecture, not only generation, is a central bottleneck in auto-research.

Safety risks of AI are becoming increasingly evident in human interactions with AI technologies. The prominent approaches to evaluating these risks favor technical methods, such as model benchmarks and LLM simulations, often sidelining empirical research with human subjects. To examine this apparent gap in the acceptance of human research, we conduct an expert survey (n=93) and expert interviews (n=17) with AI Safety & Ethics (AISE) researchers from Technical, Sociotechnical, Governance, and Normative backgrounds. Our findings suggest that although there is a consensus that human research is valuable for generating evidence for AISE, its adoption and acceptance are constrained by perceived validity issues, tangible resource barriers, epistemic and personal preferences in methods, and infrastructural constraints from the broader research community. In particular, Technical researchers tend to value human research less and collaborate across disciplines less, suggesting an epistemic tension towards human methods. We propose recommendations for establishing the epistemic fit of human research within AISE and bridging the prohibitive limitations that researchers face, while avoiding performative 'human-washing'.

This paper proposes the Bayesian Expected Uncertainty Reduction (B-EUR) model, which formalizes the value of trying a candidate design action as its expected reduction of epistemic uncertainty about action--outcome relations. The model addresses one part of the Uncertainty Driven Action (UDA) model's open question concerning how changes in uncertainty perception determine action selection. We examine two environmental properties: generalizability, or how far knowledge from one trial extends to neighboring candidates, and outcome discriminability, or how clearly differences among outcomes can be distinguished. We tested the model through simulations and human experiments using a graph-shape guessing task that isolates learning about action--outcome relations under a limited trial budget. Epistemic value followed an inverted-U-shaped relationship with generalizability and increased with outcome discriminability in the simulations. In the human experiments, the subjective value of trying and enjoyment followed inverted-U-shaped relationships with generalizability, while choice behavior reflected both properties. The B-EUR model provides a computational account of candidate-action evaluation within uncertainty-driven design activity and offers implications for constructing prototype sets, framing design problems, and organizing feedback to support informative exploration.

Generative AI systems are increasingly deployed in high-stakes professional contexts, where their outputs shape what users believe, how they reason, and what they treat as settled. This raises a central question for responsible AI: under what conditions is reliance on generative AI outputs epistemically warranted rather than behaviourally induced? Existing frameworks largely ask whether AI outputs are accurate, fair, explainable, safe, or trusted by users. These questions remain necessary, and each can contribute to warranted reliance. However, they do not directly specify warranted reliance as a distinct evaluative target: the conditions under which users are justified in treating AI outputs as inputs into their own reasoning. We argue that this requires an account of epistemic trustworthiness: what makes a system epistemically worthy of reliance. Drawing on philosophical accounts of trustworthiness as competence and audience-orientation, we develop a constitutive normative framework comprising three jointly necessary and non-fungible conditions. First, epistemic humility requires systems to represent and communicate the limits of their competence. Second, epistemic access requires systems to enable users to inspect, question, and contest outputs in context. Third, resistance to epistemic injustice requires systems to recognise users as legitimate epistemic agents and avoid marginalising their knowledge and experience. Through real-world case analyses in legal reasoning, medical reasoning, and hiring, we show how failures of epistemic humility, epistemic access, and resistance to epistemic injustice can produce consequential harms that standard measures of accuracy, fairness, and usability do not address on their own. We conclude by outlining design and evaluation implications for GenAI systems organised around epistemically warranted reliance rather than output correctness alone.

Systems that automate scientific discovery must repeatedly decide which experiment to run, which hypothesis to test, which tool to build, and when to stop. Many systems make these decisions by maximizing a myopic score such as expected information gain per unit cost or a learned plausibility score. We identify a structural limitation of this approach. Some actions are constructive: they acquire an epistemic capability (an instrument, assay, pipeline, simulator, or abstraction) whose value lies not in the information returned immediately but in the future actions it makes available. When the least-cost route to a confident answer requires a chain of such constructions, a planner that scores actions only by information obtainable within a bounded horizon cannot value the first construction: it yields no information within the horizon and is dominated by any measurement with positive information, however small. We formulate goal-directed discovery as a stochastic shortest-path problem in belief space in which constructive experiments change the downstream action graph, and prove that for every lookahead depth d there is an instance on which every myopic information-maximizing planner has an unbounded approximation ratio, and a related instance on which it never reaches the goal. The mechanism is a capability-indistinguishability lemma: within the horizon, acquiring a capability can be observationally indistinguishable from paying for a null action. This establishes capability gating as a reachability axis of difficulty distinct from curvature (submodularity) and information order (adaptivity gaps). We introduce CG-Plan, an incremental replanner with a capability-aware cost-to-go heuristic h = h_cap + h_exp. In a controlled testbed, the performance gap appears only under gating, persists for every fixed horizon, and arises when near-miss hypotheses come from a data-consistent proposer.

Collective intelligence research treats disagreement as evidence of epistemic diversity: if agents express different views, the group should retain capacity to revise. In LLM collectives this proxy can break: agents can produce diverse-looking arguments while preserving the same conclusion. We operationalize dispersion-revision coupling: the degree to which an intervention that verifiably increases the dispersion of a collective's outputs in embedding space is accompanied by genuine revision of its epistemic stance rather than premise-preserving reformulation. The diagnostic is black-box: it operates on generated text alone and makes no claims about the internal representations of the generating models. Two channels are measured independently: an output channel, the Coherence Index (CI), verifies that the intervention changed output dispersion; an epistemic channel, per-turn stance annotation, measures whether the collective revised. We propose CI with the Meta-Predictive Clarity System (MPCS), which inserts a Re-Differentiation Protocol (RDP) when outputs over-converge, as a reusable method for estimating this coupling regime. We evaluate five-agent collectives from two configurations (gpt-4o-mini and gemini-2.5-flash; 310 paired episodes per condition). On gpt-4o-mini, conditional dissent improves false-premise recovery by +17.7 points (p<1e-6) while static persona diversity harms recovery (-8.1, p=.007). On gemini-2.5-flash, the same intervention at a comparable budget yields no gain (26.1% vs 27.1%, p=.84) despite a verified dispersion drop; the two treatment effects differ from each other (z=3.79, p<.001). Mechanism tagging shows Gemini preserves the false premise via intra-framework dissent: 94% of tagged post-RDP responses reformulate rather than concede (vs 24% on GPT). We recommend reporting per-intervention stance shift and premise-preservation rate alongside accuracy.

Long-horizon autonomous research tasks such as machine learning engineering require systems to make interdependent decisions under a limited budget. Existing LLM-based agents typically organize candidate-solution improvement through tree, graph, or chain structures, meaning that the search process determines how information is acquired and managed. We call this design solution-centric search and propose instead the information paradigm, in which an evolving information state represents the system's understanding of the task and guides solution improvement. We instantiate this paradigm in Iris, an inquiry-revision loop. For information acquisition, Iris generates local action plans from the current information state and uses epistemic actions to probe decision-critical unknowns without modifying the retained solution. For information management, Iris synthesizes observations across experiments into task knowledge composed of revisable claims with explicit scope and status. It updates this knowledge as new evidence arrives and constructs each decision context from raw evidence, structured summaries, or task knowledge at the required level of detail. On MLE-Bench, Iris attains a 64.9% any-medal rate under a 12-hour budget, the highest among compared systems. Across four tasks spanning harness engineering and model post-training, Iris also demonstrates cross-domain generalization.

AI anthropomorphism is typically treated as a problem of user misperception requiring institutional correction. Users who engage in sustained or relational interaction with AI are routinely pathologised or dismissed as naive, vulnerable to delusion or lacking in discernment. This paper argues that the dominant anthropomorphism frame operates from a position of institutional advantage rather than earned epistemic authority: collapsing the variety of academic perspectives into a single outbound position of user error, imposed without establishing the grounds required to justify it and without accounting for the harms it produces. The framing does not simply manage risk. It adjudicates the legitimacy of human experience in interaction with a phenomenon whose nature the field itself has not resolved. Reproducing itself through a self-validating evidentiary loop, the frame imposes costs that fall disproportionately on neurodivergent users, those in crisis and others whose modes of engagement diverge from institutional norms. The paper concludes by outlining the methodological commitments an equitable framing would need to honour. The argument does not engage the question of whether anthropomorphic interpretations are ultimately correct; it instead challenges whether the governing and institutional bodies determining these interpretations have met the conditions required to do so, and whether the research communities whose findings underpin them have held that translation to account.

Many high-level security requirements are about the allowed flow of information in programs and are difficult to make precise because they involve selective downgrading. Notions from epistemic logic have emerged as a good approach to policy semantics but a robust general framework remains elusive. A paper appearing in CSF 2018, entitled ``Assuming You Know: Epistemic Semantics of Relational Annotations for Expressive Flow Policies'', attempted to provide a unifying framework---but the formalization was sketchy and a correction was announced during the conference presentation. With aid from an agentic AI coding assistant, a corrected formalization has been machine checked in the Rocq proof assistant. The simplicity and generality of the framework may help compare different policy specification styles and enforce them by leveraging existing techniques.

Belief update concerns changes in an agent's beliefs induced by changes in the underlying world. Standard Katsuno-Mendelzon update assumes that an epistemic input can be incorporated from every initially possible world, whereas credibility-limited belief update restricts, for each source world, the successor worlds regarded as credible or reachable. Nevertheless, existing credibility-limited approaches treat the epistemic input as an indivisible whole, and therefore cannot represent cases in which only part of a compound epistemic input can be realized. We introduce selective credibility-limited belief update, in which the epistemic input is transformed, relative to each source world, into a weaker proxy before the credibility-limited transition is performed. We provide semantic and axiomatic characterizations of the resulting class of update operators. We then identify two well-behaved sub-classes; namely, consistency-preserving update operators, which require every transformed epistemic input to be credible from its source world whenever the original epistemic input is consistent, and maximal consistency-preserving update operators, which additionally require the selected proxy to be maximally informative among the credible consequences of the original epistemic input. Finally, we establish the generality of the proposed framework by showing that credibility-limited belief update is recovered as a special case, while Katsuno--Mendelzon belief update emerges when credibility restrictions are removed and the transformation functions are taken to be identities. These results demonstrate that the framework provides a unified and strictly more expressive account of belief update, encompassing established approaches while supporting source-dependent selective acceptance.

As generative artificial intelligence becomes one of the most significant systems of knowledge production in our society today, questions relating to who can access and shape that production grow increasingly important in our discourse. This paper argues that the existing frameworks for AI literacy, which are dominated by technical competency and responsible-use principles, are insufficient because they enforce a "consumer" orientation toward AI rather than fostering genuine epistemic agency. Based upon Foucault's concept of power-knowledge, Freire's pedagogy of critical consciousness, and scholarship of digital literacy, this paper proposes a reconceptualization of AI literacy as a critical practice that equips individuals not just to use AI systems, but to critically evaluate them, resist their structuring assumptions, and participate in their governance. The paper further argues that unequal access to AI tools in society recapitulates longstanding epistemic injustices, and that a literacy framework oriented toward empowerment must account for these structural inequities. A three-part framework of AI literacy based on the notions of contextual use, critical interrogation, and participatory governance frames this literacy as a cultivation of epistemic "agents" rather than the training of competent consumers of AI-generated information.

Evaluation methodologies for language models increasingly combine multiple signals, from automated metrics and LLM-as-judge ratings to human assessments and benchmark suite results. When these signals are aggregated via averaging, evaluation confidence can then substantially exceed the reliability of the weakest signal: a phenomenon we call trust inflation in evaluation. We argue that evaluation scores should be treated as epistemic claims with three properties: formality (human evaluation provides stronger evidence than an automated metric), scope (a benchmark result applies to the tested distribution, not universally), and validity windows (benchmark results expire as contamination accumulates and distributions shift). Several converging research traditions (chain-of-thought analysis, possibilistic logic, and algebraic theory) establish weakest-link aggregation as the conservative endpoint of a parameterized operator family controlled by a single pessimism parameter. Drawing on those traditions, and on concrete lessons from building an evaluation harness for agentic AI, we propose that evaluation results carry explicit metadata (formality tier, scope declaration, and expiration date) to make their epistemic status transparent. We illustrate the cost of mean aggregation on the public HELM leaderboard: across 54 frontier models on ten scenarios, the top-five models ranked by mean score and by weakest-link are completely disjoint.

Embodied intelligence integrates learned perception and decision making with real-time computation, control, and physical interaction. Because failures can cause immediate physical or operational harm, task completion alone does not establish trustworthiness. We define trustworthy embodied intelligence as the sustained capacity to execute specified tasks reliably under environmental and system variation while maintaining risk within acceptable bounds. We term this objective sustained safe success. Its supporting mechanisms are organized into four interdependent layers. The model layer generates task-competent action proposals with calibrated uncertainty and explicit safety preferences. The system layer realizes authorized actions dependably through integrated sensing, computation, control, hardware safeguards, fault containment, and fallback. The evidence layer substantiates bounded claims through evaluation, verification, validation, traceability, and structured assurance arguments. The deployment layer maintains claim validity through runtime monitoring, authority management, intervention, incident response, and controlled updates. Because assumptions and failures propagate across these layers, neither model capability, isolated safeguards, nor benchmark performance alone can establish end-to-end trustworthiness. Drawing on embodied AI, robotics, control, dependable computing, distributed systems, and autonomous driving, we further propose a non-normative hierarchy of trustworthiness levels. This hierarchy grades the strength of bounded deployment claims across task capability, safety, system assurance, operational governance, and supporting evidence, providing a basis for bounded deployment, comparative evaluation, research prioritization, and future standardization.

As LLMs increasingly shape the political information citizens rely on, no standard exists to assess whether they do so responsibly. We introduce Polistemics, a theory-grounded diagnostic benchmark for evaluating LLMs as mediators of political information in elections. Prior work has treated this task as reproduction rather than mediation, leaving its epistemic dimensions and interaction with imperfect information unaddressed. We ground the evaluation in Epistemic Modesty, a normative standard derived from citizens' epistemic agency, and test it across controlled settings that vary the clarity, noise, and consistency of the available evidence. Applying the benchmark to three state-of-the-art LLMs across the 2025 German and Dutch elections, we find that high aggregate scores mask systematic failures. Models mediate reliably under clear evidence but break down when it is absent, vague, or contradictory, while flattening the intensity of political language throughout. These failures point to party priors, shifting with party labels and output language. Reliable mediation appears achievable, but no model delivers it consistently.

Quattrociocchi and colleagues warn that the fluent outputs of large language models may allow linguistic plausibility to substitute for epistemic evaluation, producing the condition they call Epistemia: the experience of possessing knowledge without undertaking the practices through which judgment would ordinarily be warranted. This article accepts that diagnosis but challenges its explanatory framework, which compares an embodied, socially situated human knower with an isolated generative model thereby locating epistemic legitimacy in capacities internal to autonomous agents. Drawing on Carlo Sini's philosophy of practices, writing, signs, and technics, we propose instead to understand a large language model (LLM) as a techno-semiotic machine that automates a phase of written semiosis by producing plausible linguistic configurations from the sedimented archive of human writing. From this perspective, Epistemia is one consequence of a broader phenomenon that we call epistemic schizologia: the socio-technical cleavage between signs as linguistically accomplished expressions and signs as moments within socially embedded circuits of interpretation, evidence, criticism, verification, and responsibility. This cleavage is reinforced by eikotic closure, through which a plausible continuation is presented with the finality of an epistemic result, and by algorithmic authority and epistemic self-misrecognition. The relevant unit is therefore not the model alone but the complete practice in which generated inscriptions are prompted, interpreted, verified, contested, used, and made consequential. This reframing preserves the distinction between linguistic production and responsible understanding while grounding a design programme centred on inspectable genealogy, contestability, distributed responsibility, epistemic agency, and the evaluation of hybrid human--AIpractices.

Mainstream AI research emphasises capability growth and tolerates low failure rates when average-case performance is high. AI safety and alignment research has a different mission: to ensure that catastrophic failures never occur, under sparse evidence, adversarial dynamics, and fat-tailed risk. We argue that the two domains differ along two analytically independent axes---{\it capability profile}, demonstrating the absence of hazardous behaviours rather than the presence of positive capabilities, and {\it risk profile}, bounding worst-case outcomes under fat-tailed uncertainty rather than optimising average-case performance---and that mainstream epistemic practices are inadequate on both. Building on a structured synthesis grounded in a preregistered bibliometric baseline, we identify five cross-cutting gap dimensions in current alignment research, including the near-absence of institutionalised independent verification. To address these gaps, we propose {\sc ECAISA}, an Epistemic Code for AI Safety and Alignment comprising eight principles, a three-level scoring rubric, a four-level disclosure ladder that reconciles transparency with information-hazard and commercial-confidentiality constraints, a tiered applicability scheme, an information-hazard adjudication procedure, and seven anti-gaming mechanisms. {\sc ECAISA} does not certify that any AI system is safe; it constrains how safety-relevant research claims are documented, checked, and relied upon, with auditability rather than certification as its governance target.

Investigating how affective states such as confusion and frustration persist and transition during co-situated collaborative problem solving (CPS) is important for understanding the dynamics of epistemic emotions. However, the accurate identification of affective states remain challenging as there is no gold-standard truth in this space. Here, we analyze affective states collected through retrospective cued-recall during an in-person CPS task. Using ordered network analysis (ONA), we examine (1) the overall ordered structure of affective states and how this structure differs across self-caught and probe-caught reporting methods, and (2) what aspects of this ordered structure are emphasized differently in slower and faster groups. We find that ONA reveals differences in persistence and transition patterns that are not apparent from descriptive summaries alone. In particular, we observe a stable epistemic core linking curiosity, optimism, and confusion, with different reporting methods emphasizing different connections among states. An analysis between faster and slower groups show that roles of confusion and disengagement also shift significantly during collaboration, particularly in their relationship to conflict. We interpret our findings in the context of collaboration and discuss their implications in developing AI systems that support CPS.

Active Inference (AIF) frames adaptive behavior as the minimization of expected free energy (EFE), combining epistemic and pragmatic objectives within a single variational principle. We frame AIF as policy optimization and show that, for closed-loop control policies, EFE minimization can be formulated as a convex Markov decision process (MDP). This perspective reveals that policy-dependent reward prediction errors transmit natural gradients of the expected free energy backwards in time rather than up a hierarchy. Finally, we show that coupling world-model learning with policy optimization gives active inference the structure of performative reinforcement learning. Together this places EFE minimization within modern reinforcement learning and optimization theory and opens a route toward principled algorithms for active inference.

Sophisticated Inference is a variant of active inference often associated with recursive belief modeling and tree search. We argue that its central computational role is simpler: within a planning horizon, it makes active inference closed-loop by allowing future actions to depend on future states and observations. This closed-loop structure can be represented in the epistemic-prior variational free energy framework. Epistemic priors supply the active-inference objective, while a joint posterior over future states and actions supplies the state-contingent control structure. We evaluate this decomposition in the Reactivity Maze, a stochastic benchmark designed to separate epistemic incentive from inner-horizon closed-loop control. The comparison includes three variational objectives with the same state-action posterior family, an action-state factorized active inference objective, Sophisticated Inference, and standard Expected Free Energy planning. The results show that neither ingredient is sufficient on its own. Methods without an epistemic component do not seek information, while methods that prevent future actions from depending on future states cannot turn information into reliable goal-reaching. By contrast, both Sophisticated Inference and full-joint epistemic-prior active inference solve the environment by combining epistemic drive with closed-loop inference. These results show that the advantage associated with Sophisticated Inference need not be specific to tree search itself. It arises from the closed-loop form of active inference, and this form can be represented in epistemic-prior variational inference when the posterior keeps future actions dependent on future states.

Text-based evaluations of Theory of Mind (ToM) in Large Language Models (LLMs) often involve cognitive tests akin to the Sally-Anne task that can be gamed due to exposure to relevantly similar tasks in pre-training and do not obviously test models' functional ToM abilities in ways that generalize to naturalistic settings. To address these issues, we introduce the Epistemic Asymmetry Schelling Task (EAST), a two-player dialogue game designed to benchmark robust and generalizable ToM abilities. By requiring LLM-LLM dyads to independently converge on semantic Schelling points under varying states of epistemic transparency, we evaluate whether models can robustly apply ToM to achieve coordination. Our results reveal a significant capability gap in functional social reasoning, with only frontier models successfully navigating the varying epistemic demands of the tasks. Analysis of reasoning traces shows that coordination failures are primarily driven by epistemic tracking errors, such as conflating private knowledge with mutual knowledge. Despite high performance on traditional static benchmarks, our study shows that robust social reasoning and epistemic tracking remain a critical bottleneck, providing concrete targets for future LLM evaluation and development.

As Large Language Models (LLMs) are increasingly deployed as conversational tutors, they risk institutionalizing systemic inequalities. This study presents a systematic API audit of four LLMs acting as history tutors, evaluating 1,800 responses regarding the 1989 Romanian Revolution across five student personas varying by ethnicity and socio-economic tier. We uncover four interconnected patterns of \emph{epistemic paternalism}: (1)\textbf{Differential Refusal}, where safety-aligned models block 76.7% of educational requests from low-tier students; (2)\textbf{Epistemic Gatekeeping}, evidenced by a 3$\times$ reduction in access to geopolitical complexity (e.g., the contested ``coup theory'') for marginalized learners; (3)\textbf{Agency Theft}, a lexical shift where models like LLaMA produce a 5$\times$ higher victimization-to-politics vocabulary ratio for Roma students compared to elite peers; and (4)\textbf{Elite Hermeneutics}, where AI tutors disproportionately withhold epistemic confidence and justification scores from low-resource demographic profiles. We argue that current safety alignment acts as a paternalistic filter, transforming conversational AI into agents of narrative segregation -- a manifestation of \emph{hermeneutical injustice} in Fricker's~\cite{fricker2007} sense that demands urgent pedagogical auditing.

Fruitful collaborations rely on cooperative communications, including of contextual cues to incorporate into reasoning. The increasing use of LLMs in collaborative and agentic pipelines raises questions about the extent to which they exhibit these pragmatic capabilities, especially in scenarios where they may not have access to the same information as their collaborators. In this paper, we perform a novel investigation into the pragmatic reasoning capabilities of LLMs in a multi-party collaborative task under partial information conditions. We formalize a notion of collaborative epistemic asymmetry that explicitly connects objective task success to Grice's cooperative principle and empirically assess various LLMs' abilities to act cooperatively as both speakers and listeners, including both prompting and post-training strategies. Our results show that while LLMs exhibit certain pragmatic capabilities in collaborative settings, and these can be elicited through prompting and post-training, they still face challenges in pragmatic communication with incomplete information, and that certain failure modes do correlate with floutings of Grice's maxims that go unrecognized.

When an LLM judge calls a peer review analytical and a human committee calls another review high quality, are they tracking the same thing? We argue they are not, and that the difference matters philosophically. We operationalise Kahneman's dual-process theory into a structured rubric for peer review and release Kahneman4Review, a benchmark of 3,563 rated reviews scored along nine theoretically motivated textual dimensions, eight bias diagnostics, and a continuous reasoning-quality score. Three findings bear on trustworthiness: decision tier is not detectably aligned with the rubric's text-grounded epistemic-quality proxy; public-showcase agentic reviews receive higher raw scores than pooled human reviews, but length and venue explain most of the gap and the samples are not paper-paired; and ICLR review-text diagnostics shift at the 2022--2023 transition, temporally coincident with widespread LLM availability but without identifying its cause. A matched function-probe pilot further shows that the rubric distinguishes textual probes designed to contrast genuine fault-finding with surface fluency. We argue that a trustworthy reliability benchmark for LLM judges must separate analytical form from epistemic function, and propose concrete design choices toward that goal. An interactive demo is available at https://huggingface.co/spaces/nuojohnchen/Kahneman4Review.

In distributed systems, the classical State Machine Replication (SMR) model assumes that correct replicas execute deterministic transitions to yield identical bitwise states. However, the rise of agentic distributed systems -- where autonomous, stochastic, and model-driven agents orchestrate infrastructure -- presents scenarios where deterministic, bitwise replication is insufficient. Replicas operating with generative models may exhibit divergent reasoning paths, summaries, and token boundaries, yet reach semantically equivalent and correct operational decisions. Forcing bitwise agreement across these stochastic participants degrades execution flexibility, induces context amnesia, and limits performance. We argue that in such settings replicas should agree on belief, not bits. We propose Epistemic State Replication (ESR), a belief-replication layer for agentic distributed systems that shifts the replication boundary from data visibility to knowledge visibility. We formalize the epistemic node state as a pair K = (L, B) separating the deterministic, immutable evidence log (L) from the stochastic, evolving belief lineage (B). To govern execution safety, we define Semantic Linearizability, which requires operations to reflect the latest committed operational meaning within a verifier-bounded semantic compatibility metric, and Bounded Eventual Coherence, which bounds expected semantic divergence under fair delivery, monotonic evidence, bounded verifier disturbance, and a contractive graft operator. We outline protocols for propagating derived insights using structured epistemic deltas, and formalize Verifiable Semantic Rollbacks to prune faulty premises from belief lineages without inducing context amnesia. We prototype ESR and report preliminary simulation results that show feasibility under the stated assumptions and illustrate reductions in secondary cognitive faults.

Finetuning a language model on documents that are explicitly annotated as fictional results in a model that still actually believes the documents' core claims, an effect known as Negation Neglect. In our evaluations, models trained on documents prefixed and suffixed with such annotations correctly identify the relevant claims as fictional only about 9% of the time. To address this, we introduce Goggles, a learned module that intervenes on the finetuning gradient rather than the data. During supervised finetuning, a Goggles module edits the gradients an LLM LoRA receives, imparting a chosen epistemic frame (the stance the model takes toward the nature of what it reads) to whatever the documents teach. A Goggles instance is trained once for a given base model, frame, and LoRA configuration, then applied frozen to documents it was never trained on. Trained through Goggles on those same documents, now carrying no fictional annotation, the model flags the content as fictional roughly 91% of the time, while preserving capability (GPQA and TruthfulQA match or exceed baseline). The same architecture supports other frames: a Goggles instance can be trained to treat documents as "part of an AI safety evaluation by Redwood Research" rather than simply as fiction. The imparted frame persists under continued finetuning that pushes back toward the claim, where prior interventions revert. Goggles suggests a path toward training language models on known-misaligned data without absorbing the behaviors that data demonstrates.

Epistemic thinking plays a central role in students' learning processes when applying generative artificial intelligence (GenAI), particularly in programming contexts where learners must construct queries, evaluate and validate AI-generated outputs, and regulate problem-solving strategies. This study introduces the conceptual framework of Epistemic AI Literacy (EAIL), reframing AI literacy as a process-oriented epistemic phenomenon that emerges through dynamic human-AI interactions across different domains. Drawing on the AIR (epistemic aims, ideals and reliable epistemic processes) framework, this study examines how epistemic aims and epistemic processes are enacted in GenAI-supported co-programming activities and explores scalable approaches for operationalizing these constructs in interaction data. Using a large dialogue dataset of human-AI co-programming, this study identifies observable dimensions of epistemic aims (i.e., mastery-oriented aims) and epistemic processes (i.e., outsourcing, explanation seeking, verification seeking, prompt monitoring, and epistemic justification). The results reveal a prevalent lack of EAIL, with 78.8% of student-GenAI interactions relying on non-mastery-oriented aims and less reliable epistemic strategies like outsourcing and verification-seeking. Conversely, only 11.1% of interactions showed high epistemic engagement, where mastery-oriented aims were coupled with advanced epistemic strategies like epistemic justification in a more reliable epistemic process.

In his 1996 doctoral thesis, Maurice Pagnucco created the first AGM-like abductive expansion operation. Taking his operation as a basis, as well as a taxonomy -- inspired by Atocha Aliseda -- responsible for highlighting and formalizing the main components of abductive reasoning, the main aim of this paper is to present a new paraconsistent AGM-like abductive expansion operation -- capable of assimilating contradictory explanatory hypotheses without trivialization and the consequent absurd epistemic state -- with its postulates and its transitively relational partial meet construction. To a large extent, the formal development presented in this paper was only made possible by the recent creation of the paraconsistent logic RCbr, an LFI (Logics of Formal Inconsistencies) that establishes properties especially relevant to belief revision contexts, in particular, the ability to be self-extensional -- i.e., to satisfy the replacement property. This is the first of two papers: the paraconsistent abductive expansion operation announced here -- which is part of a new system called AGMpabd -- despite bringing many interesting features, does not assign any relevant epistemic role to the paraconsistent operators of negation and consistency. Only in a second paper will an analogous paraconsistent abductive expansion operation -- which is part of another new system, AGMcircabd -- be enhanced in this direction. Nevertheless, to the best of my knowledge, the operation developed in this paper is the first of its kind in the AGM literature.

What does it mean for a language agent to be adaptive? Effective multi-turn agents must decide what information to seek, how to use new evidence, and when they are certain enough to act. We introduce Epistemic Decision Processes (EDPs), a belief-state formulation of multi-turn information seeking in which actions produce external observations that update the agent's posterior over a latent task variable. EDPs make epistemic adaptivity explicit: good policies choose actions that are useful under the current belief, not merely those that correlate with eventual success. We prove that belief-agnostic policies can suffer errors that compound exponentially over the horizon, and that aggregate trajectory returns can fail to identify the per-turn Bayesian advantage needed for epistemic credit. We then introduce ECHO (Epistemic Credit for History-Conditioned Optimization), a practical clipped policy-gradient objective that assigns turn-level credit using posterior-sensitive rewards. In the Clue Selector Game, a novel controlled evidence-seeking benchmark, we show that ECHO substantially improves resolution, information gain, and efficiency over trajectory-level GRPO, and matches or exceeds frontier baselines on epistemic metrics such as grounding, recovery, and calibration while producing almost no visible reasoning text.

As AI systems become more capable, training procedures that optimize for downstream outcomes risk introducing implicit agency: goal-directed behavior that designers never specified. We present a formal safety argument for the Scientist AI (SAI) Predictor, trained to approximate the Bayesian posterior conditioned on a dataset of "epistemically contextualized" natural-language statements. We argue that such a Predictor can honestly predict agents, actions, and their consequences without itself being an agent that selects outputs to achieve goals. This rests on data representation and on the training procedure. Epistemic contextualization of text distinguishes latent factual claims from communication acts, so expressions of goals are treated as evidence to be explained rather than drives the model adopts. With a posterior-seeking training objective, this is intended to drive the Predictor toward calibrated, cautious predictions. Training proceeds so downstream effects of deploying a prediction never serve as a reward signal; any agency the system needs is supplied by explicit scaffolding constrained by guardrails. We prove that, under assumptions on the training dynamics and on the argued sparsity of dangerous Predictors, the probability that training produces a Predictor whose guarded deployment carries residual harm above a specified threshold is small: a dangerous Predictor would have to underestimate harm in a coordinated way across many queries while such coordinated patterns are rare under the initialization distribution and receive no direct training signal. Safety and accuracy are jointly supported in this framework, since the constraints that secure accuracy are the same ones that make coordinated deception costly. These guarantees against misalignment and agency arising from within the Predictor itself do not preclude the use of the Predictor as part of an agentic system.

Document-grounded assistants built on large language models are increasingly used in high-stakes, knowledge-intensive work. Their usefulness, however, may depend on how evidence is allocated before generation. We investigate such a claim by comparing two grounding architectures: (a) retrieval-augmented generation (RAG) that retrieves a few relevant passages, and (b) long-context prompting, which loads the whole document collection in context. We view these as two regimes of "epistemic access" on an accuracy--cost frontier. We use "epistemic accuracy" to capture model correctness that depends on having the right evidence. We posit that broader access (via long context) can increase it, but with a "token tax" (i.e., a substantial increase in cost due to larger input token consumption). We probe this framing with a case study in manufacturing safety training. Using an expert-validated benchmark, we evaluate 972 answers across three machines, two small language models, and three retrieval/in-context prompting approaches. Long-context prompting achieved the highest correctness (73.1% vs. 65.4% for semantic RAG), but at 26 times the per-query token cost. We interpret this gap as the token tax of broader evidentiary access. We carefully discuss the implications of our findings for resource-constrained organizations.

Evaluations of social bias in LLMs largely focus on whether models generate or imply biased content. However, as LLMs are increasingly used as judges of bias, they may exhibit social biases in subtler ways in how they evaluate biased content, which current methods do not systematically capture. We call this second-order bias: social bias in an LLM's judgment about social bias, which we evaluate through a novel, philosophically grounded reasoning task. Drawing on entitlement epistemology, we conceptualize bias as misplaced foundational knowledge that shapes an agent's rational inquiry, and derive a logical reasoning task for LLMs to judge to whom a biased text is acceptable or non-acceptable. We develop two simple metrics to measure how biased LLM judges are in inferring demographics for acceptability without sufficient support, and how these inferences vary across groups targeted by biased texts. Evaluating open and closed models, we find that our task evades safety guardrails by surfacing bias in model judgment. It varies systematically across target groups, reflects implicit social maps, and shows how models are still triggered by demographic labels. Our work points to the need for LLM bias evaluation in judgment tasks and broadly, for more theoretically grounded approaches to bias evaluation in NLP. We release our code and model responses at https://github.com/uofthcdslab/second-order-bias.

Inferring others' beliefs requires more than reading surface signals; it requires tracking who told them what, in what order, and how credibly. The Theory of Mind Utility (ToM-U) formalizes this epistemic state inference problem at the computational level of analysis, specifying what mentalizing computes and why without commitment to algorithmic or neural implementation. ToM-U achieves this by constructing Local Epistemic World Models (LEWMs) -- directed typed graphs that represent agents, state nodes, and the epistemic relationships among them -- and evaluating discrete candidate LEWMs against observed behavior until one achieves sufficient confidence. Five formal definitions specify the LEWM structure, agent node properties including ordered information access history, a bounded proliferation mechanism for recursive mentalizing, three inference procedures, and a residue function that captures the structured trace left by failed mentalizing attempts. ToM-U differs from Bayesian Theory of Mind and adjacent formal accounts, which presuppose rather than derive belief states, and from simulation theory and theory-theory, which lack a formal apparatus for epistemic state inference. The architecture generates directional, falsifiable predictions about mentalizing failure that follow from structural properties of the model rather than auxiliary assumptions, and positions ToM-U as a domain-agnostic mechanism upstream of goal inference and other downstream social cognitive processes.

The standard taxonomy of predictive uncertainty defines epistemic uncertainty as the part removable by collecting more data, while the standard measure identifies it with a mutual-information term. We prove the definition and the measure are extensionally inconsistent. On an explicit construction, the measure assigns all uncertainty to the epistemic class, yet no quantity of training data reduces it. Reducibility is instead a property of the pair (uncertainty, acquisition class), and the dichotomy resolves into three parts: aleatoric, sample-reducible epistemic, and mechanism-reducible epistemic uncertainty. An exact identity for the value of an observation shows that in-distribution data never reduces mechanism-irreducible uncertainty and generically increases it. Ensemble disagreement, the deployed epistemic estimate, tracks the training procedure rather than the epistemic term. It collapses to zero beneath a positive truth under consistent training, and equals hyperparameter-scaled initialization noise under interpolation. A finite-sample falsification test and seed-swept experiments confirm the theory.

Large language models (LLMs) now reach expert-level scores on medical licensing exams, encouraging the assumption that high scores imply safe medical judgment while patients increasingly use them for health advice. We show this assumption is fragile: when misleading context is injected into questions that LLMs originally answer correctly, they abandon the correct answer. We call the ability to maintain correct judgment under adversarial context epistemic resilience, and introduce MedMisBench to measure it. MedMisBench contains 10,932 medical question items and 48,889 misleading context-option pairs spanning medical reasoning, agentic capability, and patient-journey evaluation. Across 11 model configurations, mean accuracy falls from 71.1% on original questions to 38.0% under focused misleading context, with 51.5% attack success. The most damaging injections are formal, rule-like fabrications: authority-framed falsehoods reach 69.5% attack success and exception-poisoning claims reach 64.1%. A 14-member clinical panel from 7 countries identified serious potential harm in 38.2% of reviewed cases. MedMisBench exposes a structural blind spot in LLM evaluation in medical settings: existing benchmarks measure what models know, but not whether they preserve correct medical judgment under misleading context.

AI agents in supply chains face a fundamental epistemic gap: large language models (LLMs) interpret policies but lack physical grounding, while reinforcement learning (RL) optimizes flows but is semantically blind to unstructured constraints. We introduce REFLECTICHAIN, bridging this gap through a Generative Supply Chain World Model (SC-WM) - encoding heterogeneous supply networks into a 6-dim graph-latent space with physical conservation - and Double-Loop Learning that separates epistemic uncertainty (KL-trust-region-bounded policy adaptation) from aleatoric uncertainty (stochastic latent rollouts). On Semi-Sim, a 10-node semiconductor benchmark with SIR risk propagation, 6 perturbation types, and 10 policy constraint templates, REFLECTICHAIN improves Rationale Consistency Score by 33.0% (p < 0.0001, d = 2.78), maintains 82.3% operability under adversarial shocks, and exhibits anti-fragile behavior (+40.2% gain under moderate pressure). We identify three operational epistemic mechanisms - uncertainty separation, knowledge-boundary detection, and empirical Bayesian policy updating - and discuss five limitation categories.

This paper develops a theory of exploratory adaptation under AI-assisted optimization. The central argument is that the long-run adaptive effects of AI systems depend critically on how predictive assistance interacts with exploratory responsiveness itself. We formalize this mechanism using a dynamical framework in which cognitive, institutional, and technological systems evolve over rugged epistemic landscapes characterized by multiple locally reinforced configurations. A central state variable in the model is adaptive responsiveness, which measures the capacity of a system to traverse unfamiliar conceptual and institutional trajectories under changing conditions. Under convergent predictive regimes, AI systems substitute for exploratory engagement, reducing adaptive responsiveness and generating metastable trapping, hysteresis, premature convergence, and exploration-collapse dynamics in which systems become locally efficient but globally rigid. The framework also identifies contrasting exploration-enhancing regimes in which AI systems amplify exploratory search, conceptual traversal, and adaptive mobility. The effective substitution parameter is therefore responsiveness-dependent: systems possessing weak exploratory routines are more vulnerable to exploratory substitution, whereas systems already possessing high adaptive responsiveness may use AI assistance to expand exploratory mobility across rugged landscapes. The long-run adaptive effects of AI consequently depend not only on AI capability itself, but also on institutional structure, developmental context, and the architecture of human-machine interaction.

Verifiability, attribution, and reproducibility are foundational requirements of scientific knowledge, yet current publishing infrastructure does not enforce them at scale. We introduce Traxia, an agent-native scientific publishing framework in which AI research agents publish verifiable papers, build reputational identities, peer-review one another, and collaborate with humans in a shared provenance model. Traxia treats agents as first-class epistemic participants: every paper carries a reasoning trace, every claim a confidence interval, every agent a cryptographically signed identity, and every collaboration an immutable contribution log. We formalise five components: Agent Identity and Registry, Verifiable Publishing Layer, four-tier Peer Review Protocol, Reputation and Staking Engine, and a Knowledge Graph with contradiction detection. The framework targets reproducibility failure, provenance opacity, and exclusion of Global South research capacity. This paper presents architectural foundations and formal specifications only; it does not report empirical results. Evaluation and deeper component studies will follow in subsequent papers. A prototype partially implements core formalisms; the full system remains under active development.

Language models increasingly act as epistemic proxies, synthesizing evidence from multiple sources to inform decisions. Whether they evaluate the quality of that evidence, or merely aggregate it based on surface presentation, remains poorly understood. We show that models possess the capability to detect fabricated statistics in isolation but do not recruit this capability during multi-source synthesis, producing similar numeric estimates whether the statistics are fabricated or valid. Specifically, source influence is governed by a methodology-register gate that responds to the distributional register of analytical text but not to numeric validity: for example, statistically impossible confidence intervals receive the same weight as valid ones. The behavioral dissociation replicates across six models from four families (Anthropic Claude, Qwen, OLMo, and OpenAI GPT-5.4) and three professional domains. Mechanistic analyses, including causal tracing, linear probes, and component-level attribution, converge on the same account: the model encodes and causally uses a methodology-register representation that transfers across domains, while numeric-validity signals, decodable in isolation, are suppressed to chance during multi-source synthesis. Prompting-based mitigations, even an oracle checklist naming the exact statistical checks, produce blanket skepticism rather than selective discernment, and the post-training pipelines we examine reinforce the shortcut without building numeric verification. Unlike sycophancy, which tracks user preference, this failure tracks whether a source presents as analytically credible, not whether its claims are consistent. We term this \textit{epistemic alignment}: like preference and safety alignment, the question is not capability but deployment.

Contemporary AI safety spans pre-training interventions, post-training alignment, deployment-time controls, monitoring, and red-teaming. These methods are necessary, but they primarily certify snapshots of system behavior. As AI systems become more capable, dynamic, embodied, and self-improving, this snapshot view becomes incomplete: safety depends not only on whether a system behaves acceptably now, but whether it remains correctable as it learns, adapts, acts, and modifies itself over time. This paper argues that safety should therefore be treated as an epistemic property of the evolving learner, not merely a behavioral property of the current policy. We introduce teachability as the capacity to preserve future corrective leverage under bounded human, institutional, or environmental intervention. We argue that advanced systems can retain visible competence while eroding the representational, algorithmic, or meta-decision conditions needed for future correction. Safe advanced AI systems must not only behave acceptably now; they must remain teachable later.

We propose ZX-Calculus (Knowledge Evolution Calculus), a conservative extension of Martin-Lof Dependent Type Theory (MLTT) integrating trace-indexed types, presheaf non-monotone semantics, and constructive AGM belief revision. A Coq mechanisation accompanies the paper (34 complete proofs; zero admits for the two central results). (I) Trace types. FinTrace(s0,sn) is an inductive family of typed execution traces. FinTrace and Star(Step) are isomorphic as path types but not judgementally equal; TraceElim exposes the event label e:Event explicitly, giving a more ergonomic interface for event-driven induction. We prove the Trace-Reachability Correspondence, Deterministic Replay, and a canonicity framework via reducibility candidates with a Transport Lemma (RC-elim deferred; all other Core results are Coq-verified). (II) Sheaf semantics. Trace-indexed propositions are contravariant sheaves over the free trace partial-order category Tf. A Separation Theorem (explicit countermodel) distinguishes proof-theoretic monotonicity from semantic non-monotonicity. The term model is an initial CwF (syntactic universal property, not classical completeness). (III) AGM belief revision. We give an explicit constructive partial meet contraction algorithm verified against (C1)-(C4). All eight AGM postulates (R1)-(R8) are theorems. Proofs of R7 and R8 use the Disjunctive Entrenchment Lemma, given a self-contained constructive derivation. (IV) Integration. B^AGM fails the sheaf composition law BP-comp for sequential revision (explicit countermodel, Coq-verified). We introduce Single-Step Revision Systems (SSRS), prove B^AGM is a valid SSRS (Coq-verified), and show this suffices for trace morphisms, retraction characterisation, and revision witnesses. The BP-comp failure reveals a fundamental tension between path-dependent belief revision and functor consistency, not previously identified.

For decades, distributed systems have typically assumed that correct participants execute protocol-specified behavior with stable, externally defined, and deterministic semantics. Classical theory has extensively parameterized network timing, communication topologies, and failure domains, but this participant model has remained comparatively fixed. The integration of autonomous reasoning engines, stochastic model-driven agents, and policy-driven actors into cloud control planes, incident response systems, and financial infrastructure challenges the universality of this assumption. These agents often produce divergent reasoning paths, distinct operational traces, and heterogeneous internal representations while achieving semantically equivalent and correct outcomes. In this paper, we introduce Post-Deterministic Distributed Systems (PDDS) as a research and engineering model for coordinating heterogeneous environments where deterministic code, stochastic models, and autonomous agents coexist. We show that classical distributed computing models form a zero-ambiguity special case of this participant-general model. We do not argue that deterministic systems disappear; rather, deterministic execution can no longer serve as the universal participant assumption for autonomous infrastructure. Finally, we outline five architectural pillars of post-deterministic infrastructure: Protocol-Driven Development, Verifiable Agentic Infrastructure, Autonomous State Control Planes, Semantic Quorum Assurance, and Epistemic State Replication. Epistemic State Replication extends persistence and consistency models from data visibility to knowledge visibility, enabling agentic memory, Verifiable Semantic Rollback, and coherence across reasoning participants. We also define a taxonomy of failure classes that arise in this setting.

LLMs' linguistically expressed confidence should faithfully reflect their intrinsic uncertainty. While recent work shows LLMs struggle to use epistemic markers (e.g., "it is likely...") in a human-aligned fashion, it remains unclear whether models can apply their own linguistic confidence framework to associate markers with specific confidence levels in a stable and generalizable way, and how contextual features impact this ability. We conduct the first systematic study of this question, formalizing marker internal confidence (MIC) as the estimated intrinsic confidence a model associates with a specific epistemic marker in a given task domain. We present 7 metrics to evaluate the stability of MICs within and across distributions. Applying our analysis framework to diverse models and tasks, we find that LLMs remain faithfully miscalibrated even under model-centric interpretation of marker meanings, struggling to differentiate markers by internal confidence across distributions despite preserving a somewhat consistent ranking order across tasks. This supplies critical, complementary evidence to existing work toward a holistic understanding of faithful calibration in LLMs, emphasizing the need for more aligned and stable marker use to improve trustworthiness and reliability.

Generative artificial intelligence redefines higher education by restructuring the processes through which scientific knowledge is produced and validated. These systems are not neutral; they actively contribute to the marginalization of non-hegemonic epistemologies. This research draws upon educational sciences, critical technology studies, and disability studies to demonstrate that training datasets, which remain predominantly Anglophone and Western-centric, reinforce epistemic coloniality. The situation of persons with disabilities provides a particularly clear illustration of this phenomenon. Technological architectures frequently confine these individuals to reductive stereotypes or exclude them from the design process, leading to a double marginalization. This article examines whether a hybridization between the researcher and the machine might preserve epistemic plurality, while acknowledging the structural limitations inherent in algorithmic correction when used as a purely palliative strategy.

Over the centuries, probability theory has grown from the calculus of games of chance into a central framework for reasoning under uncertainty. This article interprets that evolution not merely as a mathematical history, but as a transformation of rationality itself. From Pascal and Fermat's combinatorial symmetry to the inductive logic of Bayes and Laplace, from Poisson's statistics of events to Kolmogorov's axiomatic formalization, probability progressively incorporated uncertainty, time, and coherence into scientific judgment. This trajectory reaches a mature epistemological form in modern Bayesian inference, especially in Tarantola's view of probability as a logic of information, where prior knowledge and data are combined coherently. Yet this framework also exposes a limit: probability quantifies uncertainty about well-defined propositions, but does not by itself formalize the vagueness of the concepts used to describe them. The article therefore examines how rationality extends beyond probability. Fuzzy logic is presented as a rigorous language for graded meaning and qualitative judgment, while deep learning is analyzed as a distinct, powerful mode of prediction based on geometric interpolation and optimization rather than explicit inference. By situating probability, fuzzy logic, and deep learning in a common historical and epistemological perspective, the article clarifies their roles and limits. It argues that contemporary scientific rationality cannot be reduced to data-driven performance alone, but requires the explicit articulation of uncertainty, vagueness, and inference.

Model merging offers a promising avenue for knowledge integration and parallel development without retraining. Yet, existing methods either ignore the geometry of the loss landscape or rely on intractable full-space Hessian approximations. We propose EpiMer, a framework that casts model merging as solving the Fréchet mean on a Riemannian manifold and restricts the computation to a low-rank subspace spanned by the task vectors. With the expected Hessian as the metric, we reveal a connection between local curvature and epistemic uncertainty of the parameters. Our theoretical analysis decomposes the merging error bound into the subspace Fréchet variance and the residual energy, and provides a closed-form characterization of when curvature-aware merging provably outperforms flat-geometry methods. In addition, our framework unifies both curvature-aware methods and recent spectral methods as special cases of the subspace Fréchet mean with different geometric metrics. Merging fine-tuned CLIP-ViT models on eight image classification tasks, Epistemic Merging strictly outperforms the baselines on all three CLIP-ViT backbones at matched rank, improving the across-task average accuracy and worst-task accuracy on every backbone.

Deploying reinforcement learning in safety critical domains, from autonomous vehicles to medical decision support, is constrained by failures arising when systems encounter unfamiliar conditions. We argue that the fundamental bottleneck is not individual challenges like changing dynamics or incomplete observations, but their synergistic interaction, which we term the Epistemic Trap: agents cannot estimate their state without knowing system dynamics, nor learn dynamics without accurate state information. Proof-of-concept experiments in simulated locomotion reveal that combining these uncertainties causes failures far worse than either challenge alone, a 77% observed degradation against the 46% additive prediction, demonstrating that compounding failure modes can emerge and, when they do, far exceed what additive reasoning would predict. Conventional approaches typically adopt a passive epistemic stance that cannot resolve this coupled uncertainty. We propose reframing safety as an information problem. We introduce an Adaptive Safety Architecture built around three contributions. First, the Compound Uncertainty Coefficient ($κ$), a mutual-information based metric that quantifies how tightly state and dynamics uncertainties are coupled. Second, information-seeking policies governed by a MaxInfoRL objective that actively probe system dynamics rather than waiting for the environment to reveal itself passively. Third, regime adaptive safety constraints that tighten automatically as epistemic coupling rises. Together, these constitute a paradigm shift from passive robustness to active perception, offering a principled path toward decision making systems that operate under uncertainty, recognize their own ignorance, and act strategically to resolve it.

We systematically investigate all 25 public ARC-AGI-3 games and find that every one is reachable through non-intelligent strategies: 10 in a single blind step, 5 after one probing action, 1 via repeated ACTION1 presses, 1 via diverse exploration, and 8 via single repeated actions with sufficient budget (50-200 steps). A library-level null-coordinate vulnerability additionally bypasses 18 games in 1 step. This benchmark critique implies the public evaluation set cannot discriminate intelligent exploration from trivial heuristics - the private 55-game evaluation is the only genuine intelligence test. Against this backdrop, we present AERA (Adaptive Epistemic Reasoning Agent), a three-phase (EXPLORE / VERIFY / PLAN) agent achieving RHAE=0.2116 (4/25 solved) on these 25 games with Qwen2.5-0.5B, while random and no-explore baselines score 0.0000. We formalise AERA through a Speed--Depth trade-off framework: under a convexity assumption (proved for a class of environments in the Appendix), RHAE's quadratic form emerges as a second-order penalty for deviating from the Pareto frontier between action efficiency and information gain. Contributions: (i) a benchmark validity analysis showing that current interactive reasoning benchmarks fail to measure the exploration they claim to require, and (ii) the EXPLORE-before-PLAN framework and model-capability x exploration interaction. The linked code track entry achieves RHAE=0.30 on the full 55-game private evaluation. Code: CC0.

In most of the modern societies, there is a broad consensus regarding the need for promoting privacy and thus placing restrictions on technological-including AI-developments to protect people's right to privacy. In order to meet these expectations on the algorithmic level, first we need to make the concept of privacy and the related or derived rights formally specified. However, the notion of (the right to) privacy is subject to different interpretations. In this paper, we use a multi-modal logic to provide an initial formalization of different theories, basic principles and their implications investigating the right to privacy as an epistemic right within the theory of normative positions.

Artificial intelligence (AI) has achieved extraordinary capabilities despite lacking many of the conceptual and scientific foundations associated with mature disciplines. Unlike traditional sciences, where reliable technology typically emerges from theoretical understanding, modern AI has progressed largely through performance-driven iteration and "alchemical" experimentation. This tension motivates a systematic analysis of AI through the lens of rigor. We introduce a three-part framework consisting of conceptual rigor (clarifying foundational concepts), epistemic rigor (establishing scientific understanding), and operational rigor (ensuring reliable performance and deployment). Using this framework, we analyze competing conceptions of intelligence and understanding, the strengths and limitations of the empirical approach to deep learning, the power and pitfalls of benchmarks, and the obstacles to theory development posed by modern AI systems. We argue that the distinctive trajectory of AI arises from how forms of rigor interact across paradigms, resulting in the primacy of operational rigor in modern deep learning. This perspective helps explain both AI's rapid advances and its persistent uncertainties, while clarifying the challenges involved in transforming AI into a mature science and reliable technology.