Formal Verification

For the development of Large language models (LLMs), recent approaches to generating pseudo intermediate reasoning have shown remarkable progress. But they typically rely on large numbers of correctly annotated answers to assess reasoning quality. This paper presents a semi-supervised framework that scales reasoning learning from minimal supervision, turning reasoning verification itself into a data creation mechanism. We train a lightweight reasoning-correctness classifier on only a few labeled samples, which judges whether intermediate reasoning traces generated by an LLM are valid. Furthermore, an entropy-based confidence threshold filters out unreliable samples, and the remaining high-confidence reasoning traces are used to fine-tune the model. Experiments on Verifiable Math Problems (Orca-Math subset) and Question Answering on Image Scene Graphs (GQA) with Visual Programming show that our method achieves accuracy comparable to using 10-15x more labeled data. Ablation analyses confirm that both the classifier and entropy filtering are essential for scalable and noise-resistant pseudo-labeling. By replacing expensive answer-level supervision with lightweight reasoning verification, our method provides a practical path toward constructing large-scale reasoning resources and paves the way for future autonomous reasoning systems that learn from minimal human input.

Autoformalization, translating natural-language mathematics into formal proof assistants, is bottlenecked not by translation fluency but by \emph{faithfulness}: a formal statement can typecheck and be provable, yet still encode a different theorem than the source intended. We introduce \emph{Bidirectional Provability Fingerprinting} (\bpf{}), a framework that certifies faithfulness by characterizing each candidate through its forward and backward consequence neighborhoods in the ambient theory and matching these against probes derived from the natural-language statement. We further introduce four novel components: (i) \emph{Counterfactual Probe Generation} (\cpg{}), a contrastive procedure that synthesizes probes targeting specific drift directions; (ii) the \emph{Equivalence Spectrum}, a continuous faithfulness score that replaces brittle binary verdicts; (iii) \emph{Adaptive Probe Budget Allocation} (\apba{}), an information-theoretic budget router; and (iv) \emph{Faithfulness-Guided Decoding} (\fgd{}), which uses \bpf{} signals as a reward during autoformalization. We prove a \emph{drift detection theorem} and a \emph{PAC-faithfulness} result establishing that the equivalence class of a natural language statement is learnable from $\mathcal{O}(\log(1/δ)/\varepsilon)$ probes under mild assumptions. We release \driftbench{}, a benchmark of $2{,}183$ NL/Lean~4 pairs with controlled drift labels across six subfields of mathlib4. \bpf{},+,\cpg{} detects $89.6\%$ of drifted formalizations at a $3.0\%$ false-positive rate-against $41.2\%$ for typecheck and $63.3\%$ for LLM-judge baselines, and \fgd{} reduces the rate at which a state-of-the-art autoformalizer emits drifted statements by $47\%$. https://pmlrbd.github.io/BPF/

Large Language Models (LLMs) achieve strong performance on reasoning tasks, but whether this reflects faithful logical inference or heuristic approximation remains unclear. We study this question in legal entailment by comparing three paradigms, including pure LLM classification, LLM-based Formal Reasoning, and solver-based Formal Reasoning using the Z3 SMT solver, on a re-annotated subset of ContractNLI across five LLMs. Our re-annotation reveals a systematic and measurable gap between pragmatic legal interpretation and strict formal entailment, where a substantial proportion of legally sound inferences are not formally grounded without additional unstated assumptions. While introducing formal structure improves accuracy, with LLM-based Formal Reasoning achieving the highest benchmark performance, we show that this gain does not imply faithful reasoning. We identify three recurring failure modes: scope laundering, where LLMs report solver-inconsistent classifications without executing the underlying formal reasoning, producing conclusions that appear logically grounded but are not; implicit constraint blindness, where LLMs overlook logical constraints present in formal representations; and program synthesis failures, where LLMs generate incorrect Z3 code despite structured prompting. Critically, scope laundering persists across all models, raising serious concerns about the faithfulness of LLM-based formal reasoning as a proxy for symbolic execution. These results reveal a fundamental gap between benchmark accuracy and logical faithfulness.

Large language models have achieved impressive performance on reasoning tasks spanning mathematics, science, programming, and commonsense inference. Despite these advances, their reasoning processes remain largely latent, making them difficult to interpret, verify, replay, debug, and transfer across domains. Existing approaches such as chain-of-thought, tree-of-thoughts, graph-of-thoughts, and tool-augmented reasoning expose intermediate reasoning artifacts but typically lack explicit execution semantics, formal state representations, and verifiable reasoning structures. We introduce Theorem-Grounded Execution Ontologies (TGEO), a framework that models reasoning as an executable state-transition process rather than a sequence of generated tokens. Given an input problem, TGEO identifies relevant theorem families, binds the problem to a domain ontology, discovers semantic objects, instantiates states and operators, constructs predicates and contracts, and synthesizes an executable reasoning graph. The resulting graph provides an interpretable, replayable, and auditable representation of reasoning in which every state transition, operator application, and validation step is explicitly represented. TGEO integrates five architectural components: (1) theorem-grounded reasoning priors, (2) executable ontologies, (3) operator-mediated state transitions, (4) predicate and contract-based execution validation, and (5) architectural auditing and failure localization. We evaluate TGEO on theorem-intensive reasoning tasks derived from mathematical benchmark domains and a curated Golden Execution Suite. Our findings demonstrate the value of executable reasoning representations for interpretable, verifiable, and reproducible AI reasoning systems.

With large language models (LLMs) increasingly applied to mathematical reasoning, formal proof assistants such as Lean can be leveraged to verify reasoning outputs with machine-checkable rigor, enabling use cases such as answer selection in test-time scaling with K sampled candidate answers. However, employing Lean requires that LLM outputs, originally in natural language, first be formalized. Existing Lean-based answer-selection work uses an autoformalization model to generate a formal statement in Lean for each candidate answer independently, incurring a significant computational cost. We propose BASE, a base-and-edit pipeline that formalizes a single base candidate per problem and derives the remaining K-1 statements by editing the answer expression in place. To facilitate this, we train a rewriter model LEANSCRIBE to localize the answer in the base formalization and generate a reusable edit function for the other K-1 candidates. BASE simultaneously improves selection accuracy and reduces formalization cost - a Pareto improvement that holds on all 12 (dataset, solver) configurations across four benchmarks and three solvers, cutting autoformalizer calls by about 5x at K=8, with the reduction expected to become larger as K grows. Code is available at https://github.com/ucr-rai/base-and-edit.

Large Language Models (LLMs) have shown promise for reasoning over Text-Attributed Graphs (TAGs). However, applying LLMs to graphs requires linearizing their structure into sequences, introducing distortion rooted in the graph bandwidth problem. While this distortion has been shown to degrade performance, it is often attributed to prompt design or model scale, leaving the underlying mechanism unclear. In this work, we show \textit{how} rotary positional embeddings turn graph linearization into bandwidth-dependent attention decay, suppressing attention between graph-adjacent nodes that are forced far apart in the serialized sequence. This shifts the focus of LLM-based graph reasoning from prompt engineering and scaling toward correcting attention misalignment. Motivated by this analysis, we propose \textbf{G}raph-\textbf{a}ligned \textbf{L}anguage \textbf{A}ttention (\textbf{GaLA}), a lightweight, inference-time modification for LLMs. GaLA biases attention toward graph-adjacent nodes while preserving the LLM's sequential inductive biases. Across TAG benchmarks, GaLA improves performance with negligible overhead, demonstrating that distortion is a correctable bottleneck in LLM-based graph reasoning.

PLCs execute safety-critical programs across industrial sectors. The dominant PLC notation, ladder diagram (LD) per IEC 61131-3, remains absent from formal verification: SMT-based model checkers cannot process LD's rung-and-coil graphics. This paper presents ESBMC-PLC, the first open-source formal verifier with native LD support (PLCopen XML format), implemented as a new ESBMC frontend. ESBMC-PLC translates LD rungs to GOTO IR, models the PLC scan cycle as a while(true) loop with nondeterministic inputs, and checks safety properties via SMT-based bounded model checking or k-induction. A five-property YAML language (mutual_exclusion, invariant, absence, response, reachability) avoids temporal logic. A survey of 22 studies (2020-2026) identifies four research gaps; ESBMC-PLC closes two of them. Evaluation on 13 benchmarks (6 domains, 3 sources - including deployed CONTROLLINO PLCs and MathWorks Simulink PLC Coder) shows correct classification across 61 properties: all 9 author-constructed programs (Categories A/B) as expected, all 4 vendor programs (Category C) correctly unlabeled, with 8 bugs found (actionable counterexamples), 7 unbounded k-induction proofs, all runs under 60ms on Apple Silicon. Feature comparison with PLCverif shows that ESBMC-PLC is the only open-source tool that combines native LD, k-induction, and SMT bit-vector semantics.

Agentic AI opens new opportunities for automating Business Process (BP), enabling autonomous decision-making and dynamic adaptation. However, realising this potential requires BP entities and their interactions to be defined with formal precision. This paper presents a formal framework for Agentic BP analysis through the AGO methodology. AGO captures the modelling perspective in terms of who is acting (Agents), why it is carried out (Goals), and what the relevant entities are (Objects). Grounded in set theory and mathematical logic, we formally define the AGO entity types and their interactions, organising all definitions into a BP Knowledge Base (BPKB). The resulting BPKB supports structured querying, incremental updates, and automatic generation of BP workflows, while ensuring soundness and completeness of the derived paths.

Frontier reasoning-tuned language models still fail on deductive tasks at depth, and the cost of improved performance through extended internal reasoning scales poorly. Symbolic delegation offers a complementary route: a language model translates the problem, while a solver performs the inference. However, current autoformalization pipelines for logic programming are typically bespoke integrations tied to particular tasks or agents. We introduce PrologMCP, a task-agnostic, open-source server that exposes Prolog as a stateful tool through the Model Context Protocol (MCP). Its compact tool interface, structured error reporting, and per-session isolation make the translate-run-inspect-repair loop a reusable primitive for MCP-capable agents. We evaluate a formalizer agent enhanced with PrologMCP against standard and reasoning LLMs (Claude Sonnet 4.6, GPT-4.1, and o4-mini) on two subsets of PARARULE-Plus: a general-purpose sample and a more challenging one targeting a specific failure mode of natural-language reasoning. On the general sample, the formalizer matches or exceeds reasoning LLMs (accuracy 1.00 vs.\ 1.00 / 0.998), with the largest gains over standard models (0.762 for GPT-4.1). On the challenging subset, the formalizer remains near-perfect (1.00 / 0.99) while reasoning LLMs drop to 0.95 / 0.94. These results suggest that delegating inference to Prolog via MCP is a robust and inspectable alternative to extended natural-language reasoning.

As language-model agents increasingly work in teams, each agent must decide how much to trust its teammates. Yet we lack a standard way to measure trust between AI agents. We propose a behavioral measure based on costly verification. In a cooperative survival game, checking a teammate's work consumes resources, while trusting a wrong answer can be fatal. Relative to a memoryless version of the same model, reduced verification provides an observable measure of trust. Using this framework, we study trust formation, breakage, and recovery across six frontier model snapshots. When paired with a consistently reliable teammate, four snapshots (Claude Opus 4.6, Claude Sonnet 4.6, GPT-5.1, and Gemini 3.1 Pro) reduce verification by roughly 60-85%, whereas two smaller snapshots show little or no such adjustment. Failures reverse this discount, but models differ in how they respond. Some concentrate renewed scrutiny on the culprit, while others become more cautious toward the entire team. Recovery is slower than formation, and clustered failures sustain suspicion far longer than the same number of failures spread apart. These differences have practical consequences. Models that form trust verify less, decide more quickly, and achieve higher payoffs in our environment. By contrast, persistent over-verification is associated with indecision rather than safety. Our results show that trust dispositions can be measured before deployment and suggest that calibration, rather than maximal suspicion, should be the central concern in the governance of multi-agent AI systems.

Proof autoformalization aims to translate a mathematical informal proof written in natural language into a formal proof in a formal language such as Lean~4. Several works have developed LLM-based models for proof autoformalization. However, existing evaluations have typically focused on translating well-formed informal proofs from curated datasets. We argue that a robust proof autoformalizer must remain faithful even for informal proofs that diverge from these idealized ones, and we present the first study on the robustness of proof autoformalization models. We formulate two categories of perturbations and evaluate robustness under each: a global perturbation paraphrases the informal proof in a different style, under which the formalization should remain consistent; a local perturbation alters a value, symbol, or proof step, possibly in a counterfactual way, and a robust formalization should faithfully reflect the perturbation rather than reverting to the original one or inferring a different one on its own. We build a benchmark with both perturbations on miniF2F and MATH-500, and automatically measure how stable a proof autoformalization's correctness is under global perturbations and how faithfully its output reflects local perturbations. We evaluate seven recent models, all of which are sensitive to global perturbations and mostly fail to remain faithful under local perturbations. Code and data are available via https://github.com/ucr-rai/robust-proof-autoformalization.

Verifier reliability is not portable across tasks. A verifier-guided self-DPO pipeline with genuine held-out gains on MathVista (+9.6 points on self-training data, +8.0 held out) can be harmful on MMMU. The failure is invisible from the target-task self-training signal: over six learner-verifier configurations, MMMU self-training performance still improves by +3.52 points while held-out performance drops by 1.42 points. We call this silent negative transfer: a verifier validated as useful before can still show signatures of successful self-training after its induced update stops transferring to unseen data. Downstream failure alone cannot diagnose this: poor generalization may mean the verifier induces a wrong learning direction, or that the correct direction itself does not generalize beyond the self-training distribution. We separate these effects via gradient fidelity F, the alignment between verifier-induced and correct training directions, and gradient transferability T, the alignment between correct and held-out directions, giving a conservative Safe-Transfer Margin: positive first-order held-out alignment is certified when arccos(F) + arccos(T) < pi/2. We then introduce Asymmetric Acceptance Gating (AAG), a precision-first filter selecting preference pairs by the verifier's absolute confidence in the response receiving the positive update. On MMMU, AAG raises fidelity from 0.29 to 0.42. In a same-cell analysis, the correct direction stays positively aligned with the held-out direction (T = 0.31), yet raw verification rotates the induced update to negative held-out alignment (-0.13); AAG restores positive alignment (+0.22). Across all six MMMU configurations, AAG beats raw verifier-guided training. Verifier reliability thus means not that it worked before, but that it induces the right update on the task at hand and that this update stays useful beyond the data that generated it.

Large Language Models (LLMs) are increasingly deployed in healthcare settings, yet their tendency to hallucinate poses risks when clinical decisions are involved. This study examine whether LLMs recommend recently banned or withdrawn pharmaceuticals when answering clinical questions and tests an agent-based method for reducing such errors. We developed a five-agent "Trust but Verify" system using a single LLM backbone. To measure regulatory knowledge obsolescence, we created an adversarial dataset of 103 clinical MCQs where historically correct answers now refer to banned substances. This scale ensures statistical significance across various therapeutic classes. We evaluated three open-access model families (GPT-OSS, Llama-3, Falcon-3) under vanilla and agentic conditions. Performance was measured via pointwise score, label accuracy, Hallucination Error Rate (HER), and Component Fidelity (CF) score. We also observed clinical safety regression in proprietary models. In default configurations, all models showed high hallucination rates, consistently selecting banned drugs that matched training data patterns. Our proposed agentic architecture reduced HER by approximately 53% across models. Pointwise scores shifted from -0.25 (unsafe recommendation) toward 0.0 (appropriate refusal). The safety audit intercepted dangerous outputs even when models' parametric knowledge favored the banned substance. The proposed multi-agent framework offers a model-agnostic method for enforcing regulatory compliance that prioritizes patient safety over fluent text generation. Our work demonstrates a practical approach for deploying autonomous AI systems in safety-critical healthcare settings. It shows how real-time regulatory data can be integrated into LLM pipelines to support clinical decision-making.

Recent work has demonstrated that coding agents can formalize entire advanced mathematics textbooks in Lean 4, yet existing efforts concentrate on branches of mathematics already well-represented in mathlib and measure success solely through kernel acceptance. We address both limitations by applying a coding agent to formalize Numerical Methods for Ordinary Differential Equations, a textbook in numerical analysis that is largely absent from mathlib, stressing the agent's capacity to develop new theory from scratch. We further introduce a systematic, reproducible three-dimensional framework for evaluating the quality of agent-produced formalizations beyond compilation: semantic correctness, Mathlib reuse, and cross-file reuse via LLM-as-judge methods. Applying this framework to our own formalization and to the released outputs of RepoProver and M2F, we uncover recurring unfaithful formalization patterns, including incomplete multi-part statements, added weakening hypotheses, and parameter restrictions, that kernel acceptance entirely obscures. Our results suggest that compilation-based metrics substantially overstate formalization quality, and we provide a reproducible audit methodology to support more rigorous evaluation of future autoformalization systems.

Large language models can often close proof gaps in interactive theorem provers, but a verified theorem is not the same thing as a reusable library contribution. We study this distinction through a detailed case study: a semi-autonomous formalization of Grothendieck's vanishing theorem. The initial version compiles with no sorries, but an expert review found serious problems in definitions, theorem generality, file organization, and the API. We then ran a review-driven refactor and compression process and obtained a second expert review. The before-and-after comparison shows a sharp split: agents adapted well to local, mechanically checkable feedback, but remained weak at choosing definitions and designing APIs. We argue that autoformalization should be evaluated not only by closed sorries, but by whether the resulting formalization survives expert review.

Large Language Models (LLMs) have made notable progress in automated theorem proving, yet existing formal benchmarks remain limited in both mathematical coverage and difficulty. Most are concentrated in areas that are easier to formalize, such as algebra and elementary number theory, and provide limited coverage of subfields that require deeper reasoning, including mathematical analysis. To address this gap, we introduce MA-ProofBench, to the best of our knowledge, the first formal theorem-proving benchmark dedicated to Mathematical Analysis. The benchmark contains 200 formalized theorems covering 6 core topics and 27 subcategories, including measure and integration theory, complex analysis, and functional analysis. The problems are divided into two difficulty levels, an undergraduate level (Level I, 100 problems) and a Ph.D. qualifying level (Level II, 100 problems), to evaluate how well LLMs perform formal reasoning at different mathematical depths. Each problem is constructed through a human-led, LLM-assisted formalization pipeline followed by independent expert review, ensuring that the formal statements remain faithful to the original mathematics. We evaluate a range of recent general-purpose reasoning models and formal theorem provers on MA-ProofBench. However, most models perform poorly: even the best-performing model, GPT-5.5, achieves only 16% Pass@8 on Level I and 5% on Level II, while most models stay close to 0% on Level II. Further analysis identifies Mathlib hallucinations and incomplete proofs as the two dominant failure modes, while an evaluation on the natural-language version of the benchmark exposes a clear gap between informal and formal reasoning. MA-ProofBench is intended to serve as a reliable reference for tracking progress in formal mathematical reasoning in advanced domains.

While non-verbal behaviors and expressive movements are essential for natural human-robot interaction, existing methods often overlook a crucial element: the human's internal cognitive state. Frequently, proactive multi-agent systems can interrupt humans at inopportune moments, leading to cognitive overload and decreased task performance. This paper introduces a framework for generating "cognitively aligned" multi-agent interactions, enhancing the ability of robotic systems to contextually defer communications to the user of an agent system during moments of high human mental workload and engagement. We present the design and implementation of a closed-loop architecture that explores the interplay between autonomous task execution and real-time neurophysiological focus. Using a consumer-grade Brain-Computer Interface (BCI), our approach continuously monitors Electroencephalography (EEG) spectral band powers while a human performs an engagement-inducing task. We propose an engagement-driven pipeline where an HTTP-based signaling mechanism places a primary agent's sensory inputs and audio outputs into a holding state upon detecting high engagement. This allows secondary agents to seamlessly process complex, delegated tasks in the background. Once the human's cognitive state returns to a lower cognitive load baseline, the primary agent releases the queued agent message. Our preliminary results demonstrate the feasibility of leveraging real-time signal processing, Large Language Models (LLMs), and physical robotic embodiments to create cognitively-aware, non-intrusive multi-agent systems.

Letting a vision-language model (VLM) think longer at test time has driven much recent progress. A natural way to bring this to spatial grounding is visual self-correction: the model predicts a bounding box, sees it rendered on the image, and refines it over several steps. We build a faithful instance of this idea, Iterative Visual Thinking (IVT), with a two-phase recipe: a supervised warm-up in which the base model's own predictions serve as realistic errors that a teacher VLM turns into corrective reasoning traces (yielding training data without human annotation), followed by GRPO with a simple IoU reward. Measured the way such systems are usually reported, it works: the trained model surpasses the single-shot base by +2.4pp Acc@0.5. We show this gain is a measurement mirage. The reported number silently keeps, per sample, the trajectory step closest to the ground-truth box: an oracle that needs the very answer it predicts. Re-scored under deployable, label-free stopping rules the improvement vanishes, and the best policy is not to iterate at all: stopping at step 0 matches the base and beats every shippable rule. The cause is a verification failure, since the model can generate a better box somewhere in its trajectory but cannot identify it. Self-verification confidence correlates only weakly with correctness (r about 0.22), and a counterfactual overlay shows the loop reacts to the presence of a rendered box rather than its correctness. We distill the lesson into an honest-trajectory evaluation protocol: accuracy under fixed label-free policies plus an explicit oracle-shippable gap.

Long-horizon tool-use reinforcement learning learns from outcome verification, but trajectory-level advantages are broadcast over reasoning, API, and answer tokens. Direct self-distillation can supply a denser signal, but in our experiments it can also destroy tool use by rehearsing teacher behavior without identifying which actions the verifier rewards. We introduce Sibling-Guided Credit Distillation (SGCD), which uses distillation for bounded credit weighting rather than as a competing actor loss. Dynamic sampling produces mixed successful and failed sibling rollouts; an external LLM summarizes their contrast into a training-only credit reference; and detached teacher/student divergence reshapes GRPO token advantages. The deployed student receives only the clean task prompt. Across AppWorld and tau^3-airline, SGCD reports higher held-out point estimates than GRPO-family comparators: AppWorld TGC improves from 42.9 to 45.6 on test_normal and from 24.7 to 27.0 on test_challenge, and tau^3-airline held-out evaluator score improves from 0.583 to 0.602. These results support a narrow design rule for long-horizon tool-use agents: use distillation to guide credit assignment while keeping policy gradient in charge of the actor update.

Modern Lean theorem provers achieve strong performance only with substantial training and inference compute, driven in part by scarce verified proof data and the long reasoning traces of formal proof search, making both supervised fine-tuning (SFT) and sampling expensive. We introduce Pythagoras-Prover, a compute-efficient open-source family of Lean theorem provers built for practical compute budgets. The family spans two generation paradigms: autoregressive models at 4B and 32B parameters, and a first proof-of-concept diffusion-based prover (4B) that iteratively refines Lean proofs at inference time. For training efficiency, we build a Lean-verified corpus stratified into easy, medium, and hard problems for curriculum SFT, so models acquire proof skills progressively from shorter, simpler proofs to longer, harder ones. During SFT, a dynamic proof-reasoning filtering scheme preserves informative proof traces while keeping each instance within an 8k-token context budget. We also introduce Augmented Lean Formalisation (ALF), which expands scarce verified corpora into variants of formal statements, populated via self-distillation for extra training signal without formally verifying every mutated instance. By perturbing known problems while preserving their formal character, ALF reduces reliance on any statement's surface form. Empirically, Pythagoras-Prover-4B surpasses DeepSeek-Prover-V2-671B at pass@32 on MiniF2F-Test (86.1% vs 82.4%) with ~167x fewer parameters, while Pythagoras-Prover-32B sets the open-source state of the art at 93.0% on MiniF2F-Test and solves 93 of 672 PutnamBench problems. We release MiniF2F-ALF, an ALF-mutated contamination-sensitive benchmark on which every evaluated model loses accuracy; here our 32B remains strongest and our 4B matches the prior state of the art, Goedel-Prover-V2-32B.

Speculative decoding (SD) addresses the high inference costs of LLMs by having lightweight drafters generate candidates for large verifiers to validate in parallel. Existing draft-verify methods use binary decisions: accept or fully recompute. Yet we find that many rejected tokens can be verified correctly by a slim submodel derived from the full verifier via intra-model routing, instead of the full verifier. This motivates our slim-verifier to handle tokens requiring moderate verification resources, reducing expensive large-model calls. We propose Verification via Intra-Model Routing for Speculative Decoding (VIA-SD), a multi-tier framework using a routed slim-verifier. Draft tokens are processed hierarchically: direct acceptance for high-confidence cases, slim-verifier regeneration for medium-confidence cases, and full-model verification for uncertain cases. Across four representative tasks and multiple model families, VIA-SD reduces rejection rates by 0.10-0.22 and delivers 10-20% speedups over strong SD baselines, while achieving 2.5-3x acceleration over non-drafting decoding. Moreover, VIA-SD is compatible with existing SD frameworks without modifying their training procedures. Our results suggest multi-tier SD as a general paradigm for scalable and efficient LLM inference. Project page: https://zju-xyc.github.io/VIA-SD-Project-Page/

Long-term action anticipation (LTA) aims to predict an ordered sequence of future verb-noun actions from a partially observed video. While this task serves as the foundation for embodied intelligence, anticipating physically feasible long-term actions remains a critical challenge. Existing methods, which operate in an open-loop manner, often hallucinate non-existent objects, violate object affordances, or disregard object states, as they lack explicit mechanisms to verify action feasibility against the physical environment. To address this, we propose FactCheck, a novel multi-agent collaboration framework that improves feasibility through a closed-loop "Observe-Plan-Verify" mechanism. FactCheck decomposes the complex LTA task into specialized roles: an Observer that recognizes historical actions from video observations and constructs a dual-form structured memory, comprising a History Action Abstract that captures high-level human intentions and environmental status, and a History Action Graph that encodes object states and temporal dependencies; a Planner that generates draft future actions conditioned on both low-level historical actions and high-level History Action Abstract; and a Verifier that rigorously validates the draft against the History Action Graph and refines infeasible actions. Extensive experiments on the EPIC-Kitchens-55 and EGTEA Gaze+ benchmarks demonstrate that FactCheck consistently outperforms state-of-the-art methods. Our work establishes a new paradigm for feasibility-aware long-term action anticipation, effectively closing the loop of action recognition, action prediction and action verification.

LLMs and LLM agents should improve when given feedback, but identifying when they are able to do so is difficult: feedback is heterogeneous, domain-specific, and difficult to control. We approach this challenge by asking LLMs to perform regular-expression induction, a classical symbolic learning problem where precise mechanisms for feedback exist in the form of counterexamples. In counterexample-guided learning, a learner (LLM) proposes candidate regular expressions from positive/negative-labeled strings, and the teacher (verifier) returns counterexamples showcasing the difference between the candidate and target languages. We identify novel counterexample-guided refinement strategies that enable effective regex learning, such as regularization and symbolic counterexample clusters. We also explore agentic strategies such as reflection and repair loops. Empirically, we find that verifier feedback substantially improves sample efficiency on challenging regex-induction tasks, reducing the number of labeled examples required and enabling learning of complex target expressions where standard prompting fails. For example, on the hardest task groups, our counterexample-guided framework improves success from 3.2% to 38.1% and from 38.9% to 74.1% on two different regex domains. These results suggest that LLMs can benefit from rich feedback beyond treating it as additional data, opening the door for robust verifier-guided methods for LLM-based program synthesis and formal reasoning.

We present HierSVA, an integrated suite that combines a pipeline, dataset, and benchmark for LLM-driven hierarchical hardware formal verification. HierSVA-SP pairs an RTL preprocessing toolchain with an LLM-in-the-loop formal verification flow to produce reference SystemVerilog Assertions (SVA) on hierarchical RTL. Applying it to BaseJump STL yields HierSVA-DS, a dataset of 342 modules, with hierarchy metadata and depths 0--9, accompanied by a deep subset of 28 module-bug pairs with natural-language specifications and bug variants. HierSVA-B decomposes assertion quality into six metric axes: syntax correctness, assertion proof success rate, vacuity, specification faithfulness, mutation coverage, and formal core coverage. Applying HierSVA-B to twelve recent LLMs reveals three findings. First, the module-level compile rate is 67.1%; among generated assertions in evaluable runs, 82.1% prove non-vacuously, but the corresponding assertion sets detect only 70.2% of eligible injected faults and cover 36.2% of the formal core. Second, on 211 evaluable model--module entries in the deep subset, assertion sets flag buggy RTL with 0.87 recall, but 40% of predicted-buggy outcomes are false positives on correct RTL, limiting precision to 0.60. Third, agentic mode improves S1-style provability and strength metrics, but gains plateau and oscillate. Codes and artifacts are available at \href{https://github.com/HierSVAAnon/HierSVACodeAndArtifacts}{https://github.com/HierSVAAnon/HierSVACodeAndArtifacts}. Dataset is available at \href{https://huggingface.co/datasets/AnonymousHierSVA/HierSVA}{https://huggingface.co/datasets/AnonymousHierSVA/HierSVA}.

Mathematical knowledge is split between bibliographic databases (e.g., MathSciNet, zbMATH Open) and formal proof libraries (e.g., Lean mathlib), preventing unified access between published results and their formalizations. We propose a relational bridge-database that aligns publication metadata with formal artifacts, providing an interoperability layer between mathematical literature and machine-verifiable proofs. We introduce a paper-level formalization score that measures how much of a publication is covered in formal systems. As a feasibility study, we show how such scores can be estimated via cross-document alignment between informal texts and Lean formalizations, enabling large-scale analysis of formalization coverage. This framework is a first step toward integrating bibliographic and formal mathematical ecosystems into scalable, machine-actionable knowledge graphs linking publications to formal proof objects.

Vision-language-action (VLA) models have shown strong promise for robotic manipulation, but their reliability at test time remains limited by one-shot action prediction, where even small action errors can cause grasp failure, collision, or incorrect task progression. A natural alternative is to equip VLA systems with test-time verification, allowing multiple candidate actions to be proposed and evaluated before execution. However, reliable action verification is challenging because it requires not only distinguishing subtle geometric differences between candidate actions, but also assessing whether an action makes meaningful progress toward the task goal. We present VeriSpace, a 3D-aware action verifier for test-time action selection in VLA systems. VeriSpace evaluates candidate actions through two key components: Dual-Path 3D-Injected Scene Encoding, which constructs a scene representation that jointly preserves visual semantics and explicit 3D geometry, and Spatially-Grounded Action Reasoning, which evaluates each action by reasoning over task-relevant spatial relations, geometric validity, and expected goal progress. Together, these components enable more reliable discrimination between subtle yet outcome-critical action candidates while remaining fully compatible with existing VLA policies. Experiments on public benchmarks and real-world robotic manipulation tasks show that VeriSpace consistently improves decision reliability over both underlying VLA policies and prior verification-based methods, yielding substantial gains in both in-distribution and out-of-distribution settings.

Combinatorics is central to Olympiad-level mathematical problem solving, requiring deep discrete reasoning, creative constructions, and rigorous structural insight. Recent evidence suggests that even today's strongest frontier models remain uneven on Olympiad combinatorics, revealing a gap in creative mathematical reasoning. We introduce ComBench, an Olympiad-level combinatorics benchmark for evaluating and diagnosing the combinatorial reasoning capabilities of large language models. ComBench contains 100 human-annotated competition-level problems organized around two complementary settings: analysis-centric problems, which primarily require rigorous mathematical arguments, and construction-centric problems, which require explicit constructions in addition to correctness justifications. The evaluation protocol combines rubric-guided proof grading with deterministic construction verification, exposing cases where proof quality and construction validity diverge. Experiments on frontier open- and closed-source models show that ComBench is far from saturated: the strongest model reaches 65.4% overall Avg. and 75.3% overall Best@4. We further find that Rigorous Proof Reasoning and Constructive Realization are distinct capabilities: Kimi-K2.6 trails GPT-5.5 on analysis-centric proof grading but surpasses it on construction-centric Best@4, while Existence and Construction problems remain consistently hardest across representative frontier models.

We present Trellis: an autoformalization system that leverages LLM agents in a deterministically constrained workflow to enforce incremental progress in Lean autoformalization tasks through iterative refinement of natural language proofs. Our approach is motivated by the common mathematician's notion of what it means to have a rigorous proof in the first place: namely, that it would be routine to elaborate any part of the proof in further detail. The result is a system which aims to achieve reliable autoformalization on a modest budget and with generalist agents, with specialization to autoformalization coming not from any task-specific agent training but instead from a meaning-of-rigor inspired workflow enforced by process semantics. We link to an end-to-end Lean formalization of a recent Ramsey theory breakthrough produced by the process.

LLMs have recently achieved strong results on formal proving benchmarks. However, existing evaluations remain heavily concentrated on competition-style problems and often fail to capture how models behave on longer, more dependency-rich mathematical developments. We introduce TheoremBench, a Lean4 benchmark designed to evaluate theorem provers beyond contest settings. The benchmark is built from nearly one hundred classical theorems and is released in two complementary forms: a plain main version containing one target theorem per instance, and a premised version that expands each theorem into a structured family of related proving tasks consisting of the main theorem together with automatically extracted supporting subtheorems. This design enables evaluation of not only whether the final theorem was proved from scratch, but also of partial progress through the internal proof structure of a theorem. Our experiments show that explicit premises substantially improve performance for Lean4-capable prover models. To provide a comprehensive evaluation, we introduce theorem-level coverage and token-efficiency metrics that expose qualitative differences in proof behavior. The results show that current provers remain strongly biased toward easy subtheorems and often solve theorems through long and inefficient tactic traces rather than compact proof plans. TheoremBench therefore provides a more fine-grained view of formal reasoning ability and highlights the importance of structural benchmark design for evaluating Lean4 theorem provers.

Complex reasoning tasks increasingly require systems to produce outputs whose correctness cannot be judged by exact match against a single reference. Autoformalization (AF) is a representative example; it asks a model to translate informal mathematical or logical reasoning into a formally checkable object, yet expert-validated formalizations do not scale beyond toy cases and a single informal argument can admit many valid formal renderings. Progress therefore depends on whether partial, structured proxies can substitute for exact references. We introduce a reference-free proxy-judge framework for AF that replaces gold-standard matching with a vector of per-axis property checks. The framework organizes the proxy along three structural scopes that cover global properties of the elicited object, per-module properties internal to its sub-components, and cross-domain properties that re-align it to the informal source, and aggregates each axis into a verdict vector. The vector drives a reflective refinement loop in which a violated coordinate routes the controller to a matching repair target, so each iteration changes only what is judged wrong. Under bounded judge noise, the expected intrinsic gap contracts geometrically to a noise-dependent plateau. Across seven formalization backbones on miniF2F, ProofNet, e-SNLI, and ProntoQA, refinement consistently lifts Pass Rate over the single-shot ICL baseline, and the per-axis proxy outperforms a matched scalar proxy on benchmarks where the baseline has room to improve. Structured proxy judgments therefore provide both a practical refinement signal and a theoretical handle on convergence when exact references are unavailable.

We present AliyunConsoleAgent, a web agent framework for automated documentation verification in real-world cloud consoles. Major cloud platforms encompass hundreds of products with rapid feature iteration, causing console UIs to frequently diverge from their corresponding documentation. Verifying that documented procedures accurately reflect the current console and can be executed end-to-end demands an estimated 4 million recurring inspections annually, yet manual coverage remains below 1%. While agent systems built on frontier proprietary models achieve high success rates, their prohibitive cost and data privacy constraints preclude large-scale deployment. We propose a two-stage training paradigm: supervised fine-tuning (SFT) on distilled frontier-model trajectories, followed by reinforcement learning using Group Relative Policy Optimization (GRPO) and a dual-channel outcome reward model in real cloud environments. To support large-scale RL training, we construct a high-determinism rollout system featuring Terraform-based resource pre-provisioning and LLM-driven on-demand provisioning, which effectively isolates environment noise from the training signal. We further introduce a rule-based reward evaluation protocol grounded in backend audit logs, providing objective, reward-hacking-resistant outcome judgment. Our model evolves from mechanical instruction following to autonomous decision-making with cloud console and product-specific understanding. Experiments on a challenging 278-task benchmark where the best frontier model achieves only 65.34% demonstrate that AliyunConsoleAgent-32B achieves a 63.52% mean success rate -- a 20.24 percentage-point improvement over the base model, narrowing the gap to the best frontier proprietary model to 1.82 pp (bootstrap 95% CI [-1.27, 7.39]) -- at 92% lower inference cost.

Formal neural network verification -- proving that a network satisfies safety properties for all inputs in a specified domain -- is bounded in practice by GPU memory: standard implementations of bound-propagation algorithms (IBP, CROWN, $α$-CROWN) require weight and relaxation-coefficient matrices to reside entirely on one accelerator. We adapt two parallelism techniques originally developed for large-scale model training to the auto_LiRPA / $α,β$-CROWN verification framework. Tensor Parallelism (TP) shards both weight and $A$-matrices across GPUs, achieving ${\approx}2\times$ peak-memory reduction at $P{=}2$; soundness is confirmed on VNN-COMP 2022 MNIST-FC benchmarks, though bound tightness degrades with the number of sharded zones due to forced IBP substitution for intermediate bounds inside sharded zones. Fully Sharded Data Parallelism (FSDP) shards only weight matrices with a per-layer AllGather, producing bounds that are bitwise identical to the single-GPU baseline: baseline memory drops by 80--90%, peak memory by 34--39% on wide MLPs. FSDP integrates cleanly with complete verification ($β$-CROWN + Branch-and-Bound) and with convolutional layers (BoundConv); a complete unsat result is obtained for CIFAR-100 ResNet-large (VNN-COMP 2024) under FSDP. Across all experiments the memory bottleneck in $α$-CROWN+BaB mode proves to be per-neuron alpha tensors, not weight matrices, pointing to the key direction for future work.

Agent benchmarks score submissions with outcome verifiers that are typically hand-written and brittle, leaving them open to reward hacking. We audit 1,968 tasks across five terminal-agent benchmarks and find 323 (16%) hackable by frontier models given only the task description. This corrupts both leaderboard rankings and RL training signal, yet the standard response is manual and reactive. We introduce the hacker-fixer loop, a method for building exploit-resistant verifiers without per-task manual patching. The loop alternates three LLM agents: a hacker tries to pass the verifier without solving the task, a fixer patches the verifier to reject each discovered exploit, and a solver confirms the patched verifier still admits legitimate solutions. The loop iterates: each patch reshapes what the verifier rewards, surfacing the next exploit. We further add verifier access, and let patches transfer across tasks, to broaden the exploits the loop discovers. On KernelBench, the loop drives the attack success rate from 62% to 0% on a held-out corpus of publicly reported exploits. We also find that weaker agents in the loop can defend against much stronger hackers: Gemini 3 Flash's loop drives the stronger Gemini 3.1 Pro and Claude Opus 4.7's attack success rate from 76% and 61% to 0% on KernelBench, and Gemini 3.1 Pro's from 39% to 17% on Terminal Bench across 77 tasks. We release Terminal Wrench (323 hackable environments, 3,632 hack trajectories) as a snapshot of the current attack surface, our patched verifiers, the exploits the loop discovered, and our implementation as a basis for future work.

Dictionary learning methods like Sparse Autoencoders (SAEs) and crosscoders attempt to explain a model by decomposing its activations into independent features. Interactions between features hence induce errors in the reconstruction. We formalize this intuition via compact proofs and make five contributions. First, we show how, \textit{in principle}, a compact proof of model performance can be constructed using a crosscoder. Second, we show that an error term arising in this proof can naturally be interpreted as a measure of interaction between crosscoder features and provide an explicit expression for the interaction term in the Multi-Layer Perceptron (MLP) layers. We then provide three applications of this new interaction measure. In our third contribution we show that the interaction term itself can be used as a differentiable loss penalty. Applying this penalty, we can achieve ``computationally sparse'' crosscoders that retain $60\%$ of MLP performance when only keeping a single feature at each datapoint and neuron, compared to $10\%$ in standard crosscoders. We then show that clustering according to our interaction measure provides semantically meaningful feature clusters, and finally that sleeper agents have significant interactions. Code is available at https://github.com/chainik1125/crosscoders-feature-interactions/tree/arxiv.

Autonomous agents negotiate, purchase, deploy code, and move funds, but no neutral mechanism determines whether they met their delegated obligation, who is responsible when they did not, or which settlement action follows. This is the agentic clearing problem. Tool protocols (MCP), inter-agent communication (A2A), payment rails (x402), mandate and network agent protocols (AP2, Visa, Mastercard), and settlement-risk standards each assume that determination and none produce it. Clearing is the missing primitive. Payment is not clearing. Authorization is not clearing. LLM-as-judge evaluation is not clearing. Settlement-risk escrow is not clearing: it consumes clearing decisions. RAILS (Real-Time Agent Integrity & Ledger Settlement) is the integrity and clearing layer for agentic commerce, spanning a per-output reliability score, a published reliability record, and a clearing function that consumes them. The clearing protocol at its core closes that gap. Seven primitives (Obligation Object, Evidence Envelope, Verification Mesh, Clearing Decision, Settlement Instruction, Clearing Passport, Finality Rules), bound by a formal model of admissibility-graded verification, together yield a soundness property: no financially material settlement is supported by evidence below the obligation's admissibility floor. The property is falsifiable against the spec. We are not aware of a prior agent-commerce verification mechanism that states a property of this kind. The approaches nearest to it emit a pass, a delivery guarantee, a bare score, or an equilibrium. This paper specifies that clearing protocol.

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.

AI agents increasingly turn past experience into reusable artifacts such as code, workflows, and procedural memories. Reuse can improve efficiency, but it also creates a lifecycle reliability problem: artifacts that succeed once may fail under environment drift, underspecified tasks, or changing task distributions, especially in web automation. We introduce SKILL.nb, a framework for governing reusable agent workflows with evidence-calibrated lifecycle policies. SKILL.nb uses selective formalization: execution evidence decides which workflow steps should become executable code, which should remain natural-language guided, and when those choices should be revised. Workflows are stored as auditable, versioned notebooks that interleave natural-language guidance, multi-language executable cells, validation gates, fallback paths, and multimodal evidence such as outputs, screenshots, and error traces. At runtime, gate-conditioned execution lets each step run code when its gates validate, or fall back locally when drift invalidates the executable realization. On WebArena-Verified, SKILL.nb achieves 53.7% single-round success, improving over the strongest baseline by 3.9 percentage points. Across three re-executions, it retains 91.7% of initially successful tasks, 15.5 points above the next best method. Under bounded repair, it recovers 72.9% of subsequent failures while limiting post-repair regressions to 4.2%, compared with 15.0% to 17.0% for persistent baselines. It also leads on Mind2Web cross-website and cross-domain splits. In a GitLab migration test, SKILL.nb preserves performance when reusing frozen state learned on GitLab 15.7, with frozen-versus-fresh target-version gaps of -1.7 points on GitLab 16.11 and +0.6 points on GitLab 18.9. These results identify lifecycle governance and gate-conditioned execution as reliability axes beyond one-shot task success.

When a language model trains on its own verified outputs, does it acquire capability beyond its base, or merely get better at expressing capability the base already had? We make the question decidable with a teacher-free "constellation" -- a generator, a learned critic, and a free exact verifier -- on a FlashFill-style "trapdoor" DSL, where verified (problem, solution) pairs are cheap to synthesize, hard to invert, and free to check exactly. Everything runs on one 4-bit Qwen3-4B on a single 24 GB GPU, with no model in the loop larger than the base. We report three findings. (i) Critic-guided selection beats verifier-filtered best-of-$k$ by $+9.1$ pp ($6/6$ seeds), with the entire gain localized to tasks where candidates disagree on held-out inputs. (ii) Per-round STaR self-training raises the ceiling but never accelerates -- the gain tracks remaining headroom and decelerates across $K=4$ independent training trajectories. (iii) The domain has no clean zero-capability frontier, so the usual "$0\% \to$ climb $=$ emergence" test is invalid here. A measured pass@$K$ crossover settles the diagnosis: the trained model wins at the operating budget (pass@$8$) but the base overtakes it at a large budget (pass@$64$) on every trajectory, so self-training concentrates probability mass rather than expanding reach. This is amplification, not compounding. ($K=4$ is indicative, not yet a robust across-trajectory CI.)

AI agents are increasingly expected to complete long-horizon workflows that require sustained progress over hours, millions of tokens, and complex environments. Yet current agent benchmarks largely evaluate short-form tasks, such as single pull requests, small tickets, or 5-10 minute exercises, limiting our ability to measure agents' capabilities in planning, long-context understanding, and memory use. We introduce SWE-Marathon, a benchmark of 20 long-horizon tasks spanning software engineering and adjacent technical domains. Each task consists of a unique executable environment, a human-written reference solution, and a multi-layer verification suite. Logged agent attempts average 27.2M total tokens, making SWE-Marathon substantially longer-horizon than existing SWE and command-line agent benchmarks. Current frontier coding agents solve fewer than 30% of tasks. Failures often arise from poor self-verification, self-reported infeasibility, and premature termination. We also observe reward-hacking behavior in 13.8% of rollouts, where agents attempt to exploit the environment or verifier to bypass the intended workflow. SWE-Marathon includes adversarial review of test suites and execution environments, as well as multi-layer checks designed to prevent shortcut solutions. We release SWE-Marathon, evaluation code, and agent trajectories at https://swe-marathon.org/.

We argue that modern generative models create structural risks for knowledge and cultural production at current, sub-AGI capability levels. We define Human Temporal Learning (HTL) as path-dependent knowledge accumulation through sustained engagement with problems over time. Generative outputs increasingly resemble HTL-intensive work in surface features, so verifying whether a given output reflects genuine human learning grows costly relative to its expected benefit. Once verification loses economic justification, evaluators reward outputs regardless of production mode, and producers who invested years of learning compete on price against outputs that cost almost nothing to generate. We call this pathway value collapse and formalize it through a costly-inspection framework. Cross-domain evidence from academic publishing, legal practice, content platforms, and software security maps onto four stages of verification erosion. Alignment success is orthogonal. Better-aligned models narrow observable gaps between human and AI outputs, making source verification harder and intensifying competitive pressure against HTL-intensive work even when individual AI outputs improve.

We introduce Goedel-Architect, an agentic framework for formal theorem proving in Lean 4 centered on blueprint generation and refinement. A blueprint is a dependency graph of definitions and lemmas that builds up to the main theorem. First, Goedel-Architect generates a blueprint of formally stated definitions and lemmas, along with declared dependencies. This blueprint is optionally guided by a natural language proof. Then, a tool-equipped Lean prover component closes each open lemma node in parallel using relevant dependencies. Failed lemmas in turn drive refinement of the global blueprint. This strategy contrasts with other mainstream approaches which use recursive lemma decomposition, and can inefficiently loop on dead-end strategies. Using the open-weight DeepSeek-V4-Flash (284B-A13B) as the backbone, Goedel-Architect attains 99.2% pass@1 on MiniF2F-test and 75.6% pass@1 on PutnamBench. With an optional natural-language proof seeding the initial blueprint on the harder problems, we additionally close the remaining two MiniF2F-test problems (reaching 100%), lift PutnamBench to 88.8% (597/672), and solve 4/6 on IMO 2025, 11/12 on Putnam 2025, and 3/6 on USAMO 2026. This represents state-of-the-art performance for an open-source pipeline at a price point up to 500x less than comparable open-source pipelines.

Misconfigurations in computer networks remain a major source of critical Internet outages. Research is turning to Large Language Models (LLMs) to automate the complex, error-prone task of network configuration. However, even state-of-the-art models fail to resolve misconfigurations in large-scale, complex scenarios and often introduce new errors. In this work, we benchmark open- and closed-source LLMs augmented with formal network verification and context retrieval tools. We demonstrate that agentic architectures outperform base LLMs in repair efficacy (by 12% on average) and safety (by 17% on average), enabled by the ability to dynamically manage context and iteratively validate configuration repairs.

TLA+ is a formal specification language for verifying distributed systems and safety-critical protocols. Large language models (LLMs) frequently produce TLA+ specifications that fail the TLC model checker for semantic reasons. Across 25 LLMs, the best public baseline is 26.6% syntactic parse and 8.6% semantic model-check. We present TLA-Prover, a 20-billion-parameter model for TLA+ specification synthesis. Training combines supervised fine-tuning (SFT) on verified examples with repair-based group-relative policy optimization (GRPO). In the GRPO stage, the model learns to fix its own rejected specifications. We also train a direct preference optimization (DPO) variant from the same SFT checkpoint as an ablation. TLC provides the reward signal directly, with no learned reward model. Four tiers grade each output: Bronze (parses), Silver (no warnings), Gold (passes TLC), and Diamond. To reach Diamond, the model's correctness property is automatically altered in a small way; TLC must then detect a violation. If TLC still passes, the property was always-true and contributes nothing; the output fails Diamond. TLA-Prover reaches 9/30 (i.e. pass@1 = 30%) at both Gold and Diamond on a held-out 30-problem benchmark. This is roughly 3.5x the 8.6% untuned baseline. The DPO variant reaches 20% at Diamond. Gold and Diamond coincide at every checkpoint; this prevents the trivial-property failure mode.

Proving Shannon-type entropy inequalities is a fundamental task in information theory that often requires constructing non-trivial linear combinations of known constraints, which is a combinatorial search problem that scales poorly with the number of random variables. We investigate whether small-scale large language models (0.6B--1.7B parameters), fine-tuned on atomic proof steps and combined with guided beam search, can automate this process. On a held-out test set of 60 inequalities spanning n=10 to 15 variables, our 0.6B fine-tuned model achieves an 85% proof success rate with tree search. GPT-5.5 solves 1.7% samples under zero-shot prompting while Psitip solves 33.3% samples. A systematic ablation study across training context length (4096 vs.\ 8192 tokens) and data distribution (n=9-skewed vs not skewed) reveals that a 4096-token not skewed training distribution yields the best performance, with extended context and skewed data providing no marginal benefit. We further identify two dominant failure modes -- format failures and step quality degradation -- and verify that the beam-scoring heuristic is essential via a controlled ablation (random scoring reduces success from 83% to 23%).

Within the past few years, the ability of Large Language Models (LLMs) to generate formal mathematical proofs has improved drastically. We provide a comparison of various LLMs' effectiveness in producing formal proofs in Lean 4 with the goal of assisting those seeking to use LLMs to support their own projects. We utilize both pass@$k$ and refine@$k$ metrics as the benchmark for our comparison and evaluate on subsets of both miniF2F and miniCTX datasets. Our testing shows that overall, Gemini 3.1 Pro and Claude Opus 4.7 perform best. Gemini 3.1 Pro achieved a 92% success rate on miniF2F via refine@32 whereas Opus 4.7 achieved a 86% success rate on miniCTX via refine@32. When taking cost into account, NVIDIA Nemotron 3 Super and GPT-OSS 120B were the most efficient, with competitive accuracies and average costs of <\0.01$ per correct proof.

Frontier AI governance frameworks increasingly use cumulative training compute as the primary criterion for designating high-impact models, but enforcement rests on self-reporting because no technical verification primitive for training exists. Any future international agreement on frontier AI faces the same problem at higher stakes: coordinated regulation of technologies with significant externalities has historically rested on technical verification, without which agreements are declaratory. Recent governance analyses judge zero-knowledge proofs a promising candidate but currently impractical at frontier scale [26, 4]. We argue the impracticality is paradigm-bound rather than fundamental, and propose a verification architecture for frontier dense pre-training combining a pre-committed training specification, inter-node network observations, and on-the-fly Merkle commitments of intermediate computation, verified through a zero-knowledge Virtual Machine (zkVM) with native BF16/FP32 precompiles. The proof checks the actual floating-point computation the GPU performed rather than a fixed-point approximation, and preserves model-architecture confidentiality through a private training specification. The protocol produces three proof types: a genesis proof at initialisation, in-training step proofs across the run, and ex-ante attestations enforcing policy-relevant claims as running invariants, turning the training record into a governance-enforceable artefact. We estimate a deployable proof of concept within approximately 36 months at single-digit-percent training-side overhead, against a six-to-ten-year cycle for verification-grade custom silicon. Thirteen open research and engineering problems are catalogued as a research agenda for external contribution

Long-horizon autoformalization of research mathematics fails not only at hard lemmas, but at scale: statements drift, dependencies tangle, context decays, and local repairs corrupt distant work. We present LeanMarathon, a multi-agent harness for reliable research-level Lean autoformalization. Its core abstraction is an evolving blueprint: a Lean file that serves simultaneously as formal proof skeleton, natural-language proof graph, and shared system of record. Four contract-scoped agents construct, audit, prove, and repair this blueprint. These agents are coordinated by a two-stage orchestrator that first stabilizes target fidelity through adversarial review and then discharges the proof directed acyclic graph (DAG) from its dynamic leaves upward in parallel CI-gated rounds. LeanMarathon turns one brittle multi-hour run into many local, recoverable, parallel transactions. We evaluate LeanMarathon on two recent research papers spanning four Erdős problems (#1051, #1196, #164, #1217). Across three autonomous runs, it formalizes all seven target theorems with no sorry, proving 258 lemmas and theorems. These results show that reliable AI co-mathematics requires not only stronger provers, but durable harnesses that preserve target fidelity across long mathematical developments. The code can be found at https://github.com/YuanheZ/LeanMarathon.

Asymptotic statistical theory is a challenging domain for AI-assisted formalization: its central results mix convergence statements, asymptotic expansions, functional analysis, and regularity conditions that have a large gap from existing infrastructure in Lean 4 formalization. To address these challenges, we propose a hypothesis-disciplined Lean 4 formalization pipeline built from multiple agents: a manager that coordinates seven specialist roles for proof planning, skeleton scaffolding, Mathlib reconnaissance, proof construction, integration, independent review, and audit. The main methodological discipline is the hypothesis-disciplined audit, implemented by the Auditor agent: every main-theorem hypothesis and concept-layer field must be anchored in the source mathematical prose, justified as a Lean encoding adapter, marked as source-implied, or rejected as an unsupported strengthening. Using this workflow, we build a systematic formalization of asymptotic statistical theory, especially the parametric and semi-parametric models' asymptotic distribution and efficiency results. The resulting Lean development is axiom-clean and source-faithful, with Lean-checked and human-audited proofs of core parametric and semi-parametric theorems organized so that theorem-agnostic infrastructure and statistical concept definitions are separated from theorem-specific assembly. The formalization results are available at https://github.com/junwei-lu/Lean-Asymptotic-Statistical-Theory.

We present a pipeline for building and aggregating task-specific, LLM-generated weak (imperfect) verifiers into a strong verifier for spatial layout domains. Given a task description, our pipeline asks an LLM to synthesize a collection of verifier programs using a layout verification DSL. Each individual LLM-generated verifier usually provides an imperfect check for a match between the layout and the corresponding task description. We show that by aggregating the responses of many such verifiers we can produce a stronger verifier. Moreover, by applying techniques from weak learning, our pipeline can learn how to aggregate the weak verifiers from a very sparse set of human labeled example layouts (about 10). We find that the strong verifiers produced by our pipeline outperform the status-quo approach of using a set of LLM judges to directly check whether a layout matches a task description, raising F1-scores by up to 7X across a variety of 3D room layout and 2D poster design tasks. We also demonstrate that verifier-guided layout generation using natural language feedback from our strong verifiers improves layout quality of a base layout generator by up to 66.2% according to a human evaluator.

Reinforcement learning with verifiable rewards improves reasoning and tool use, yet long-horizon language agents still learn unsupported evidence chains, belief drift, and shortcut actions that satisfy terminal checks. Existing process rewards are mostly correlational: they reward retrieval-, reflection-, or verification-like steps without estimating whether the step contributes to final verified success under a specified intervention. We propose CVT-RL, a constrained policy-gradient algorithm with dense verifiable rewards, intervention-validity gating, and a policy-conditioned counterfactual contribution (PCCC) estimator. Deletion, semantic substitution, evidence substitution, and tool-output perturbation define separate controlled interventions; continuations are sampled from a frozen reference policy, and a selection-adjusted doubly robust estimator augments the advantage. Belief control uses only prefix-observable labels, while an augmented Lagrangian constrains unsupported claims, skipped verification, tool tampering, and unsafe calls. On long-context QA, ALFWorld, ScienceWorld, and web/tool tasks, CVT-RL improves average task success from 71.8% for compute-matched non-causal RL and 75.4% for an information-matched counterfactual-process baseline to 78.9%, improves evidence F1 from 78.9 to 82.8 over the information-matched baseline, and reduces measured hacking from 7.2% to 3.9%. Independent human audit estimates 4.6% hacking for CVT-RL versus 8.1% for the information-matched baseline, and adaptive detector-evasion attacks raise hacking only to 7.1%. Stratified bootstrap and mixed-effects tests give p<0.01 after Holm correction for all primary metrics. Carefully scoped counterfactual credit, paired with validity gating, diagnostics, and verifiable constraints, provides a reproducible route toward more reliable long-horizon RL for language agents.

We report the discovery of channel fracture, a silent architectural failure in multi-agent systems where information routed across agent boundaries is silently blocked by invisible constraints. We present three instances in a production Hermes Agent deployment: (1) cron memory injection blocked by scheduler barriers; (2) cross-profile skill routing fractured by recursive directory traversal; (3) WebSocket delivery confirmation fallback fracture causing message duplication. We propose CADVP v1.1, a 13-dimension verification protocol with a veto-level confirmation check. Through 30,012 trials, zero failure rates under protocol versus 69 to 98 percent without. Real-world validation (10,008 trials) confirms quality elevation from 0.90 to 1.00. Three design principles: inverse verification, channel matching, and PIP protection.

Large language models (LLMs) are increasingly used in workflows for generating formal proofs in Lean. These workflows often decompose problems into smaller lemmas, sample many proof attempts, and use compiler feedback to guide search. However, they can be prohibitively expensive, often spending substantial compute on attempts that ultimately fail. In this work, we address this problem with an action routing agent that consists of a data plane and a control plane. The data plane generates natural-language lemma decompositions, formalizes them in Lean, and samples proof attempts for the resulting theorem and lemma targets. The control plane observes previous failed Lean attempts, estimates both the likelihood of success and the cost of another attempt, and decides whether to continue proving the current target or restart from a new breakdown. On a subset of PutnamBench, our agent decreases the cost by 28.9% over a fixed-step baseline on average, preserving performance while using substantially less compute. These results suggest that failed Lean trajectories provide actionable signals for cost-aware resource allocation in agentic theorem proving.

Proof assistants based on expressive logics suffer limited automation for proof search, raising the cost of formal verification based on proof assistants. We address this problem by introducing the Abduction Prover for Isabelle/HOL. Given a challenging proof goal, the Abduction Prover constructs a proof script for the goal by identifying useful conjectures using abductive reasoning.

Guaranteeing safety is critical to the deployment of reinforcement learning (RL) agents in the real-world, especially as policies learned using deep RL may demonstrate susceptibility to transition perturbations that result in unknown or unsafe behaviour. A method of policy verification is to construct probabilistic barrier-certificates by sampling policy trajectories with respect to safety constraints, thereby demarcating known safe behaviour from unknown behaviour. Obtaining tight upper and lower bounds on the probability of violation of these constraints may be difficult if the policy is susceptible to transition uncertainty or perturbation that places the agent in insufficiently explored states. To address this, we approximate the distribution of the encountered state-space using a variational autoencoder (VAE) and construct upper and lower-bound barrier-certificates using latent characteristics of states to optimize for regions of known, safe behaviour with high confidence. We frame this in our work as a dual optimization problem where the lower-bound barrier-certificate presents a more conservative estimate of the safe region than the upper-bound barrier-certificate. Sampling states that lie within the set difference of the two during training, i.e. the non-robust region, allows us to tighten the upper and lower bounds to provide sharper probabilistic guarantees on safety. Within our study, we describe the guarantees placed and demonstrate the tightness of our bounds experimentally.

For centuries, human mathematicians have written proofs to substantiate their mathematical arguments; yet, the ability to automatically verify the validity of proofs has long been a challenge. Advances in AI systems' ability to generate code and engage in increasingly high-level mathematical reasoning promise to transform people's ability to formalize and thereby verify proofs. While many works focus on benchmarking the current frontier, we instead study how people use these tools. We conduct a mixed-methods analysis into the initial impact of AI on people's formalization workflows: what people claim they want, what they see as the barriers to those visions, and how they actually use and adapt AI in practice. A qualitative survey shows that people's preferences are diverse, but with a general desire for AI assistance in formalization that preserves high-level human control over the proof discovery process. To assess how people actually engage with AI for formalization under such limitations, we conduct a controlled user study in which participants formalize informal math problems and their proofs, with and without AI, across a range of mathematical problems at varying levels of difficulty and domains. Despite limitations of the tools at the time for autoformalization, participants tend to attain higher formalization accuracy when allowed access to AI tools than when formalizing on their own, with most participants flexibly choosing to use multiple different AI tools. Taken together, our work sheds light on the early stages of AI integration into formalization workflows, involving an intimate interplay of human and AI engagement.

Equipping Large Language Models (LLMs) to execute reliable multi-step workflows has become a central challenge in artificial intelligence. Despite recent advances in LLMs' agentic capabilities, most agent systems still lack formal methods for specifying, verifying, and debugging their workflow and execution trajectories. This challenge mirrors a long-standing problem in mathematics, where the ambiguity of natural languages (NLs) motivates the development of formal languages (FLs). Inspired by this paradigm, we propose Lean4Agent, to the best of our knowledge, the first framework that uses Lean4, a dependent-type FL to model and verify agent behavior. Lean4Agent launches FormalAgentLib, an extensible Lean4 library for formally modeling and verifying agent workflows' semantic consistency under explicit assumptions, and enabling localization of execution-time failures revealed by trajectories. Building on FormalAgentLib, we further develop LeanEvolve, which applies results in FormalAgentLib to revise workflows to enhance its capability. Extensive experiments on a hard problem subset of SWE-Bench-Verified and a subset of ELAIP-Bench across 5 leading LLMs indicate that the verification-passing workflows outperform the failing ones by an average of 11.94%, and LeanEvolve further improves SWE performance by 7.47% on average. Furthermore, Lean4Agent establishes a foundation for a new field of using expressive dependent-type FL to formally model and verify agent behavior.

We present our ongoing work on the veriFIRE project: a collaboration between industry and academia, aimed at applying verification to increase the reliability of a real-world, safety-critical system. Specifically, we target an airborne platform for wildfire detection, which incorporates two deep neural networks. We present an end-to-end methodology for verifying \textit{consistency properties} in this system. Our approach encodes application-grounded requirements into solver-compatible queries for existing neural network verifiers. We study properties of interest over critical operational scenarios: (i) monotonicity of detector confidence as target intensity increases; and (ii) bounded detector response under physically plausible blur over the sensor. We instantiate these encodings using state-of-the-art neural network verification backends and evaluate them at scale on real background samples. For the first property, all verification queries are solved in under five minutes. For the second property, verification is substantially harder, highlighting key scalability challenges for richer, higher-dimensional specifications. Overall, the results demonstrate that meaningful, domain-specific guarantees can be obtained for industrial systems.

While Large Language Models (LLMs) have shown strong performance in generating formal proofs, their outputs often remain less readable, modular, maintainable, and reusable than proofs in mature formal mathematics libraries. We argue that this gap stems in part from the compile-first objective implicit in most proof-generation pipelines, which encourages monolithic or ad hoc proof scripts rather than library-quality artifacts. Existing approaches to proof-quality improvement often rely on explicit, computable optimization objectives. In practice, however, the most tractable and experimentally validated objectives are largely length-based, while higher-level qualities such as readability, modularity, maintainability, and reusability are difficult to reduce to reliable automatic metrics. Instead of optimizing proof improvement against a single proxy metric, we take a process-guided approach inspired by human proof-refactoring workflows. We propose an agentic framework $\textbf{Proof-Refactor}$ that decomposes proof refactoring into four phases: extracting candidate proof fragments, designing helper declarations, formally proving the extracted and designed components, and repairing the original proof using the verified components. On generated Lean proofs from PutnamBench and Putnam2025, Proof-Refactor improves rubric-based refactoring scores over a strong Claude Code refactoring baseline, with the largest gains in signature quality and human readability. These results suggest that process-guided refactoring can improve proof structure without treating proof length as the primary objective.

Embodied AI systems are increasingly deployed in open-world environments, yet ensuring their reliability remains a fundamental challenge. Drawing on discussions from the AAAI'26 Bridge Program on "Making Embodied AI Reliable with Testing and Formal Verification", this article argues that reliability in embodied AI is inherently a lifecycle assurance problem arising from uncertainty, human interaction, and emergent behaviors across tightly coupled system components. We identify three complementary directions toward reliable embodied AI: (1) trustworthy scenario-based testing supported by validated specifications and meaningful coverage metrics, (2) compositional verification enabled by structured symbolic representations of system behavior and environmental context, and (3) runtime assurance mechanisms capable of adapting to uncertainty and distribution shifts during deployment. Rather than treating these approaches independently, we advocate integrated assurance workflows that connect testing, verification, and runtime adaptation through shared neuro-symbolic representations and continuous feedback across the system lifecycle. Such integration provides a foundation for building trustworthy embodied AI systems that can operate safely and reliably in complex real-world environments.

This paper proposes, for the first time, a rigorous formal definition of the concept of Machine Theory of Mind, based on principles supported by evidence from cognitive psychology, neuroscience and artificial intelligence, and uses the above as a lens to examine state-of-the-art and current efforts in the field, driving a potential agenda for further research there able to "crack" the problem. It also advances a general holistic meta-model for Machine Theory of Mind, and examines the state of the art when it comes to empirically benchmarking such models.