NeurIPS 2026 Papers

Reactive synthesis, the problem of automatically constructing a hardware circuit from a logical specification, is a long-standing challenge in formal verification. It is elusive for two reasons: It is algorithmically hard, and writing formal specifications by hand is notoriously difficult. In this paper, we tackle both sides of the problem. For the algorithmic side, we present a neuro-symbolic approach to reactive synthesis that couples large reasoning models with model checkers to iteratively repair a synthesized Verilog implementation via sound symbolic feedback. Our approach solves more benchmarks than the best dedicated tools in the annual synthesis competition and extends to constructing parameterized systems, a problem known to be undecidable. On the specification side, we introduce an autoformalization step that shifts the specification task from temporal logic to natural language by introducing a hand-authored dataset of natural-language specifications for evaluation. We demonstrate performance comparable to that of starting from formal specifications, establishing natural synthesis as a viable end-to-end workflow.

Current medical LLM benchmarks typically decompose clinical competence into isolated factual questions, single-image interpretation, or brief case scenarios. This fragmented paradigm primarily measures local correctness but provides limited insight into whether models can progressively integrate subspecialty knowledge, multimodal evidence, and evolving patient states into safe, guideline-constrained longitudinal reasoning. To address this gap, we introduce NPCBench, a multimodal clinical apprenticeship benchmark for nasopharyngeal carcinoma (NPC). NPCBench operationalizes specialist training as a staged evaluation of (M)LLMs across guideline recall, atomic rule application, multimodal evidence grounding, longitudinal care planning, state revision, and expert-style consultation. It comprises 4,077 staged evaluation problems and 25 multimodal full-care path episodes, covering pathology diagnosis, MRI staging, and 146 downstream clinical decisions. The benchmark explicitly links stepwise tasks to complete patient-level care trajectories, enabling systematic evaluation of all clinical pathways. Beyond isolated precision, NPCBench evaluates whether the models ground decisions in multimodal evidence, maintain temporally consistent patient states, and provide safe expert-level consultation across complete care trajectories. Across 30 evaluated models, we observe a persistent composition gap: strong performance in local case-level tasks does not translate into episode-level clinical competence required for end-to-end patient management. Overall, NPCBench advances medical AI evaluation from static question answering toward apprenticeship-style workflow evaluation, providing a rigorous testbed for evidence-grounded and temporally coherent reasoning in complex oncology care.

Monitoring chain-of-thought (CoT) reasoning is a foundational safety technique for large language model (LLM) agents; however, this oversight is compromised if models learn to conceal their reasoning. We explore steganographic CoT---where models hide secret reasoning within innocuous text---to inform risk assessment and deployment policies. Steganographic reasoning requires two skills in a single forward pass: computing an intermediate result, and embedding it into a coherent cover that answers an unrelated question. Drawing on our taxonomy of steganographic and non-steganographic CoT types, we systematically evaluate the limits of prompt-elicited steganographic CoT capability across 34 models, ranging from past generations to the current frontier. We measure monitor evasion, refusal rates, encoding fidelity, and hidden task accuracy across five datasets, comparing against plain reasoning, direct answer, and filler-token baselines. The two experiments isolate the two sub-skills: a reasoning tasks sweep tests joint reason-and-embed, while a counting task hands the model a known numerical sequence and tests embedding alone---a necessary precondition for stego reasoning. Current frontier models cannot sustain joint reason-and-embed: a paired McNemar comparison shows the steganographic channel is dominated by an filler-token baseline on every (model, family) cell. The encoding-only floor, by contrast, is cleared---Claude Opus~4.5 reaches 92\% per-number partial accuracy (54\% exact-match) on 4-digit sequences and saturates at 100\% exact-match on length-8 single-digit sequences---establishing that the binding constraint on stego CoT is the joint reasoning-plus-encoding load, not raw channel capacity. Separately, GPT-5.2 issues an explicit refusal to the steganographic instruction yet still produces partial valid encoding in 6 of 644 trials. Our findings underscore the need for continuous evaluation of steganographic risk and provide a methodology to preemptively detect and evaluate hidden reasoning that might empower misaligned scheming and deceptive behavior.

Motion instruction generation in cross-video comparison aims to produce corrective feedback that describes the differences between a query and a reference motion. However, existing models often generate instructions that exhibit motion hallucinations, failing to reflect actual kinematic differences between paired videos. To systematically investigate these hallucinations, we introduce MotionHalluc, a dedicated benchmark for evaluating motion hallucinations in paired-video comparison. MotionHalluc comprises 1540 fine-grained questions over 553 video pairs, evaluating hallucinations along three core dimensions: (1) directional hallucination, (2) attributional hallucination, and (3) temporal hallucination. Extensive evaluations of state-of-the-art large multimodal models demonstrate high susceptibility to these hallucinations. Furthermore, we provide Perceive-Parse-Verify (PPV) as a training-free measurements extraction and verification baseline that converts candidate instructions into executable measurement queries and supplies kinematic measurements at inference time. Our results show that this simple measurements injection yields an average 10.6% performance gain across models, suggesting that motion reasoning with explicit quantitative measurements is a key factor in reducing hallucinations in cross-video comparison.

Vision-Language Model (VLM) driving agents promise explainable end-to-end autonomy by first producing natural-language reasoning and then predicting trajectory planning. However, whether planning is **causally** driven by this reasoning remains a critical but unverified assumption. To investigate this, we build DriveMind, a large-scale driving Visual Question Answering corpus with plan-aligned Chain-of-Thought (CoT), automatically generated from nuPlan. Our data generation process converts sensors and annotations into structured inputs and, crucially, separates priors from to-be-reasoned signals, enabling clean information ablations. Using DriveMind, we train representative VLM agents with Supervised Fine-Tuning and Group Relative Policy Optimization and evaluate them with nuPlan’s metrics. Our results, unfortunately, indicate a consistent **causal disconnect** in reasoning-planning: removing ego/navigation priors causes large drops in planning scores, whereas removing CoT produces only minor changes. Attention analysis further shows that planning primarily focuses on priors rather than the CoT. Based on this evidence, we propose the Reasoning-Planning Decoupling Hypothesis, positing that the training-yielded reasoning is an ancillary byproduct rather than a causal mediator. To enable efficient diagnosis, we introduce a novel, training-free probe that measures an agent's reliance on priors by evaluating its planning robustness against minor input perturbations. In summary, we provide the community with a new dataset and a diagnostic tool to evaluate the **causal fidelity** of future models.

We revisit the problem of computing mean-field equilibria (MFEs) in discrete-time, monotone, finite-horizon mean-field games (MFGs). We show that, when the transition kernel is independent of the state-measure term and the reward function satisfies the usual weak monotonicity condition and is Lipschitz continuous, anchored proximal gradient descent methods can be used to compute a monotone MFE. We also establish last-iterate convergence results for these methods. Our approach relies on formulating the computation problem as an optimization problem over the space of occupation measures. Using this formulation, we show that the problem is equivalent to a class of constrained Lipschitz monotone inclusion problems. We then apply iterative methods for this monotone inclusion formulation to derive a tractable algorithm. The resulting algorithm achieves a convergence rate of $O(1/\sqrt{T})$ after $T$ iterations, without requiring any regularization. This rate holds even in the absence of a uniqueness assumption for the corresponding MFE.

Large Reasoning Models (LRMs) introduce new opportunities for safety monitoring through their Chain of Thought (CoT) reasoning. However, CoT is not always faithful to the model's final output, undermining its reliability as a monitoring tool. To address this, we investigate the hidden representations of LRMs to determine whether future behavior can be predicted from prompt and CoT representations. By evaluating a probe at each generated token, we construct a probe trajectory, the continuous evolution of a concept's probability across the reasoning process. We find that future model behavior is more distinguishable when examined over the full trajectory than from a single static prediction. To characterize these temporal dynamics, we extract signal-processing features that capture volatility, trend, and steady-state behavior, significantly improving the separation of future model states. We also present two methodological insights. First, template-based training data achieves near-parity with dynamically generated model responses, eliminating the need for a costly initial inference and labeling. Second, the choice of pooling operation is critical: average-pooling and last-token methods collapse to near-random performance, while max-pooling achieves up to $95\%$ AUROC and yields stable probe trajectories. Using four datasets and four reasoning models across the domains of safety and mathematics, we demonstrate that trajectory features encode task-specific dynamics that improve outcome separability. These findings establish probe trajectories as a complementary framework for monitoring LRM behavior. Warning: This article contains potentially harmful content.

Pre-trained vision encoders contain layer-wise visual representations that differ in spatial granularity, semantic abstraction, and sensitivity to local details. However, most Multimodal Large Language Models (MLLMs) rely only on the final or penultimate vision encoder representations or fixed aggregation rules, making visual abstraction largely query-agnostic and limiting access to fine-grained cues such as small objects, spatial details, text, and subtle visual attributes. In this work, we propose **Mixture of Layers (MoL)**, an instruction-conditioned layer routing approach that dynamically aggregates query-relevant latent representations from intermediate vision encoder layers. Given a text query, **MoL** predicts routing probabilities over vision encoder layers and aggregates selected hidden states at either the image level, patch level, or through a hybrid routing mechanism. Our proposed **MoL** is a vision encoder-agnostic framework for layer-wise routing that selectively samples visual features useful for fine-grained visual reasoning tasks. Experiments across seven fine-grained visual reasoning benchmarks demonstrate substantial performance improvements, including +18.9% on V* overall accuracy, +4.5% on HRBench4K, and +16.3% on CharXiv compared to baseline MLLMs, *without* requiring multi-resolution inputs, simple interleaving of multiple vision encoders, or additional patch tokens. We further analyze receptive field scales and routing behaviors across vision encoder layers to explain why adaptive layer selection improves perception and reasoning. Our results suggest that conditional intermediate-layer representations are a key step toward stronger visual perception and reasoning in MLLMs. Code will be open-sourced.

Large Reasoning Language Models (LRLMs) leverage long Chain-of-Thought (CoT) reasoning to solve complex tasks, yet often engage in overthinking. Specifically, they continue to generate reasoning steps that provide meaningless contribution to or even degrade the final answer, even after sufficient reasoning has been produced. Early-exit strategies are proposed to dynamically terminate meaningless or even harmful reasoning, aiming to improve both efficiency and accuracy. However, existing methods either suffer from over-truncation that degrades accuracy below vanilla CoT, or yield only spurious efficiency gains, which reduce token counts but increase wall-clock inference time. We observe that when an LRLM's reasoning path deviates into meaningless or even harmful wandering, this deviation is accompanied by an anomalous surge of high-entropy transition tokens. Building on this insight, we propose RPDI-EE, a training-free early-exit method that monitors the Reasoning Path Deviation Index (RPDI), defined as the ratio of local to global average entropy, which serves as a proxy for reasoning path deviation. By tracking this index, RPDI-EE detects and terminates likely meaningless or even harmful reasoning while preserving productive inference. Experiments across multiple benchmarks and four LRLMs of varying types and scales show that RPDI-EE achieves the largest average accuracy improvement over vanilla CoT among all tested early-exit methods, while mitigating the spurious efficiency gains of existing alternatives.

Large reasoning models (LRMs) improve language model capabilities by generating explicit thinking traces before final answers. In factuality-oriented question answering (QA), such thinking often improves overall performance by helping the model recover relevant knowledge and refine its answers. However, we find that this benefit is not uniform at the instance level: explicit thinking can also overturn correct non-thinking answers and lead to factual drift. We refer to this failure mode as \emph{thinking-induced hallucination}. To explain this phenomenon, we formulate explicit thinking in factuality QA as a thinking residual over the model's direct-answer tendency, which can either recover missing knowledge or introduce unsupported associations. Based on this formulation, we propose MARGO, \underline{\textit{M}}ixed-Mode \underline{\textit{A}}dvantage \underline{\textit{R}}egularization for \underline{\textit{G}}rounded \underline{\textit{O}}ptimization, a reinforcement learning framework that uses non-thinking rollouts as same-model references in advantage estimation. By constructing mixed-mode rollout groups with both thinking and non-thinking trajectories, MARGO evaluates whether explicit thinking adds factual value beyond direct answering, thereby suppressing hallucination-prone thinking while preserving beneficial thinking behaviors. Experiments across multiple factuality-oriented QA benchmarks demonstrate that MARGO improves factual reliability over strong baselines, while evaluations on mathematical benchmarks show that it preserves general reasoning ability.

Chain-of-Thought reasoning improves the explainability of large language models, yet verifying such reasoning remains difficult when intermediate steps express epistemic uncertainty rather than deterministic entailment. Neuro-symbolic verifiers typically translate reasoning steps into rigid first-order or SMT-style constraints. This forces each proposition into a binary truth regime and creates a Rigidity--Ambiguity Mismatch: uncertainty-marked claims such as may, likely, or suggests are either over-hardened into deterministic assertions or rejected as unverifiable. We propose ProbVeri, a probabilistic soft-logic framework for formal verification under uncertainty. The key idea is to represent uncertainty-marked reasoning steps as weighted soft logical constraints over continuous truth assignments, so that partial evidential support remains expressible. Building on this soft-logic representation, we formulate verification as a contrastive energy minimization problem: a step is considered supported when its natural interpretation has lower verification energy than its negated counterpart under the same evidence, soft rules, and assumption regularization. Probabilistic Soft Logic defines the logical energy through weighted hinge-loss constraints. We introduce a support-grounded assumption penalty that discourages unsupported latent bridge assumptions between context and claim. The resulting energy gap provides a confidence-scored verification signal that separates unsupported steps from weakly but consistently supported inferences. Experiments on ProofWriter, BioASQ, and LegalBench-SARA show that ProbVeri recovers more verified-correct reasoning traces than rigid verifiers while reducing over-acceptance compared with soft-only PSL. These results suggest that uncertainty-aware verification benefits from soft logical formalization and contrastive comparison between natural and negated interpretations.

Although LLMs have made substantial progress in reasoning, systematically producing frontier-level reasoning data remains difficult. Existing synthesis methods often have limited visibility into the structural factors that govern problem difficulty, which can result in narrow diversity and unstable difficulty control. In this work, we view the difficulty of a reasoning problem as arising from the accumulation of atomic knowledge-reasoning transformations, which we term *thought modes*. Building on this perspective, we propose MindLoom, a framework for synthesizing frontier-level reasoning data through compositional thought mode engineering. Given a collection of hard problems with verified solutions, MindLoom first decomposes those solutions into thought mode chains that reveal each problem's construction logic. It then trains a retrieval model that matches problem states to compatible thought modes, providing guidance on which reasoning challenges to introduce during synthesis. New problems are composed by iteratively applying retrieved thought modes to seed questions, with distribution-aligned sampling to encourage diverse reasoning coverage. Finally, a rollout-based judging stage labels generated questions by difficulty and supplies judged-correct responses for supervised fine-tuning. We evaluate MindLoom on nine benchmarks covering five STEM disciplines and four mathematical reasoning tasks across multiple model families and sizes. Models fine-tuned on MindLoom generated data consistently improve over base models, distillation, and external-data baselines across the reported benchmarks. Ablation studies indicate the contribution of each component, and further analysis suggests that MindLoom covers a broad range of reasoning patterns while maintaining useful difficulty control. We have open-sourced our implementation at https://anonymous.4open.science/r/MindLoom-5B8E.

Large language models increasingly rely on long Chain-of-Thought (CoT) to solve complex reasoning tasks, but the resulting CoT often contains repeated checks, abandoned branches, and unused planning that increase inference cost without supporting the final answer. Existing efficient reasoning methods address this through length budgets, token-level importance, confidence signals, or a stronger teacher model, treating CoT compression mainly as a text-shortening problem rather than as a question of which steps the answer actually depends on. We propose MinPath, a training framework that treats CoT compression as a graph problem. The raw CoT is represented as a Typed Reasoning Graph, where the Minimal Dependency Path supporting the target conclusion is extracted, and the resulting MinPath is used for fine-tuning. Across four reasoning models on GSM8K, MATH-500, and AIME24, MinPath reduces generated tokens by 33.9\% on average with nearly unchanged precision (accuracy even improved in 41.7\% of all experiments) and outperforms five compression baselines in every evaluated setting.

Mental simulation, the ability to reason by constructing and updating internal visual states, is central to flexible human cognition, but remains elusive in current multimodal large language models. Latent multimodal reasoning offers a promising route toward this capability by interleaving text with continuous visual latent blocks, allowing models to maintain internal visual workspaces without decoding them into pixels. In this paper, we ask whether these latent visual states actually matter. Through a direct perturbation analysis across representative latent-reasoning MLLMs, we find that they often do not: dropping, replacing, or shuffling generated visual latents has only minor effects on the model's own final-answer probability, while equivalent perturbations to the linguistic reasoning trace are substantially more damaging. We call this failure mode Mental Simulation Collapse (MSC): the model appears to perform interleaved visual reasoning, but routes most answer-relevant computation through text. We further diagnose that MSC follows naturally from existing training objectives: visual alignment can make generated latents resemble helper-image embeddings, but it does not require the decoder to rely on them; subsequent text-only supervision further leaves the semantic role of the latent pathway unidentifiable. To address this, we introduce AnchorSim (Anchored Mental Simulation), a contrastive distillation framework that trains models to make their generated visual latents consequential. Across multiple visual reasoning benchmarks, AnchorSim improves performance, while diagnostic re-evaluation shows that visual perturbations now meaningfully affect predictions. Our results expose a fundamental failure mode of latent multimodal reasoning and demonstrate that mental simulation must be anchored to model behavior in order to matter.

Spiking neural networks (SNNs) with learnable membrane time constants can improve temporal processing by adapting neuronal integration timescales, but they also turn the decay factor $\beta$ into an optimized dynamical parameter that is fragile under hardware-induced parameter mismatch. We develop a perturbation-based account of how time-constant variation affects trained SNNs. In controlled software simulations, this fragility is strongly task-dependent: Spiking Heidelberg Digits (SHD) and Spiking Speech Commands (SSC) settings lose $7\text{--}20$ percentage points of accuracy under $20$% coefficient-of-variation (CV) perturbations in $\beta$, whereas DVS-Gesture and CIFAR-10 lose less than $3$ pp. We show that, under a surrogate-linearized first-order analysis, the failure mode is governed by the membrane sensitivity $\Psi$. This quantity admits a closed-form online recursion requiring only one additional state per layer and no extra temporal storage. The analysis identifies time-averaged sensitivity energy as the controllable term in deployment fragility, leading to $\textbf{MARS}$ ($\textbf{M}$embrane-$\textbf{A}$ware $\textbf{R}$obustness through $\textbf{S}ensitivity$ Regularization), a training objective derived from perturbation analysis rather than heuristic noise augmentation. We prove a conservative worst-case output-perturbation bound and introduce a typical-case diagnostic explaining why sensitivity remains predictive when worst-case constants are vacuous. At $20$% CV perturbation, MARS reduces the accuracy drop in the sensitive settings to at most $0.5$ pp while preserving nominal accuracy, with minimal effect on DVS-Gesture and CIFAR-10.

Medical language models promise expert clinical support, but the strongest open source LLMs remain too large for private, edge devices deployment, while compact medical models still trail substantially on knowledge-intensive and real-world healthcare tasks. We present MedPsy, a family of text-only 1.7B and 4B medical language models designed for edge deployment. Our recipe combines a synthetic medical data pipeline over biology, medicine, and health seeds with chain-of-thought targets from a 235B medical-focused LLM teacher; a four-stage post-training curriculum of two SFT stages followed by two RL stages with hard-sample mining; and a mobile-oriented quantization study over several GGUF variants per model. On seven closed-ended medical benchmarks, MedPsy-4B surpasses MedGemma-1.5-4B by +19.34 points and matches MedGemma-27B while being 6.75x smaller; MedPsy-1.7B outperforms MedGemma-1.5-4B by +11.42 points despite being less than half its size. On HealthBench-Hard, MedPsy-4B surpasses MedGemma-27B by +15.33 and MedPsy-1.7B surpasses it by +11.66 points despite being 16x smaller. Beyond accuracy, MedPsy reduces average response length by 1.7x (1.7B) and 3.2x (4B) versus its Qwen3 backbones, and 4-bit quantization retains accuracy within 1 point of BF16 while reducing disk footprint by ~69%, enabling practical deployment on resource-constrained edge devices.

Large language models (LLMs) in expert domains face a trade-off between \emph{agentic tool use}, which externalizes expertise behind brittle multi-turn runtimes, and \emph{end-to-end specialization}, which internalizes expertise only implicitly at task-level granularity. We propose \emph{internalized meta-capabilities}: atomic, parametrically internalized, and composable reasoning units that an LLM can select and combine within a single chain-of-thought (CoT). We instantiate this idea as \textbf{Med-Agentic} for medical visual diagnosis, where the model emits a capability-tagged structured CoT in one forward pass, turning capability invocation into tagged token generation rather than external tool calls. For training, \textbf{Med-OPD} performs multi-teacher on-policy distillation with \emph{token-level dual-factor teacher routing} conditioned on both the image and the active capability tag, strictly generalizing per-prompt teacher routing. We show that this routing gives an unbiased estimator of the same expected teacher-KL gradient. Across public medical imaging datasets spanning nine anatomies and eight modalities, Med-Agentic consistently improves in-distribution and out-of-distribution diagnostic accuracy over the strong competitors.

Language models are increasingly trained to "reason" before answering users' queries, outputting hundreds of intermediate tokens before a final answer. While reasoning is designed with direct model capabilities in mind, we argue that reasoning language models (RLMs) should also be assessed by interaction effects between their reasoning traces and weaker models. In contexts like safety monitoring and distillation, the performance of weak models increasingly depends on legibility---how thoroughly and precisely a reasoning trace externalizes an RLM's actions. Existing efficiency-based metrics for legibility fail to capture "thoroughness", instead focusing on conciseness. Thus, we introduce *transfer utility*, a method for measuring trace legibility derived from interactions where weak models finish tasks given incomplete traces. Evaluating 85k traces from 12 RLMs across three tasks, we find that reasoning traces generated by the highest-performing and the most efficient models rank the *lowest* for transfer utility. We also find evidence that transfer utility predicts the ability of weak monitors to verify procedurally dense traces for math or logical problem-solving, though the effect moderates when verifying fact-driven traces. Finally, we show that open-source reward models decouple from transfer utility signals on correctness. Together, these findings surface status quo trade-offs in weak-to-strong legibility, motivating an interaction-first framework for future applications.

Single-step retrosynthesis prediction serves as the core operational unit for automated synthesis planning and remains a fundamental computational challenge in pharmaceutical design. While a critical prior in organic chemistry is that chemical reactions typically preserve the majority of the molecular scaffold, current template-free deep learning models struggle to effectively exploit this characteristic. Existing methods attempt to exploit this by minimizing sequence-level edit distance through carefully chosen graph traversal orders. However, this structural correspondence is only indirectly induced and remains highly sensitive to imperfect traversal heuristics, which limits its effectiveness for complex transformations. To address this limitation, we introduce the Matching-while-Decoding paradigm, replacing implicit sequence alignment with direct structural supervision. We operationalize this paradigm within a graph-to-sequence architecture that explicitly maps generated reactant tokens back to the input product graph during decoding. Furthermore, our hierarchical autoregressive formulation utilizes a custom causal attention mask to enable highly efficient, single-pass parallel training. Extensive experiments across the USPTO-50K, USPTO-MIT, and USPTO-FULL benchmarks reveal a critical accuracy and robustness trade-off in existing methodologies, where models either over-rely on augmentation or fail to leverage it. Our approach uniquely resolves this bottleneck by delivering highly competitive canonical accuracy while scaling exceptionally well with test-time augmentation, establishing new state-of-the-art records on USPTO-MIT and augmented USPTO-FULL. By providing this balanced stability across diverse inference protocols, our approach emerges as a highly promising foundation for dependable single-step retrosynthesis prediction.