ICML 2026 论文列表

Recent progress in text-to-image (T2I) diffusion models (DMs) has enabled high-quality visual synthesis from diverse textual prompts. Yet, most existing T2I DMs, even those equipped with large language model (LLM)-based text encoders, remain text-pixel mappers -- they employ LLMs merely as text encoders, without leveraging their inherent reasoning capabilities to infer what should be visually depicted given the textual prompt. To move beyond such literal generation, we propose the think-then-generate (T2G) paradigm, where the LLM-based text encoder is encouraged to reason about and rewrite raw user prompts; the states of the rewritten prompts then serve as diffusion conditioning. To achieve this, we first activate the think-then-rewrite pattern of the LLM encoder with a lightweight supervised fine-tuning process. Subsequently, the LLM encoder and diffusion backbone are co-optimized to ensure faithful reasoning about the context and accurate rendering of the semantics via Dual-GRPO. In particular, the text encoder is reinforced using image-grounded rewards to infer and recall world knowledge, while the diffusion backbone is pushed to produce semantically consistent and visually coherent images. Experiments show substantial improvements in factual consistency, semantic alignment, and visual realism across reasoning-based image generation and editing benchmarks, achieving 0.79 on WISE score, nearly on par with GPT-4. Our results constitute a promising step toward next-generation unified models with reasoning, expression, and demonstration capacities.

Large language models (LLMs) using chain-of-thought reasoning often waste substantial compute by producing long, incorrect responses. Abstention can mitigate this by withholding outputs unlikely to be correct. While most abstention methods decide to withhold outputs before or after generation, dynamic mid-generation abstention considers early termination of unpromising reasoning traces at each token position. Prior work has explored empirical variants of this idea, but principled guidance for the abstention rule remains lacking. We present a formal analysis of dynamic abstention for LLMs, modeling abstention as an explicit action within a regularized reinforcement learning framework. An abstention reward parameter controls the trade-off between compute and information. We show that abstaining when the value function falls below this reward strictly outperforms natural baselines under general conditions. We further derive a principled and efficient method to approximate the value function. Empirical results on mathematical reasoning tasks support our theory and demonstrate improved selective accuracy over existing methods.

We study how individual training examples shape the internal computation of looped transformers, where a shared block is applied for $\tau$ recurrent iterations to enable latent reasoning. Existing training-data influence estimators such as TracIn yield a single scalar score that aggregates over all loop iterations, obscuring when during the recurrent computation a training example matters. We introduce Step-Decomposed Influence (SDI), which decomposes TracIn into a length-$\tau$ influence trajectory by unrolling the recurrent computation graph and attributing influence to specific loop iterations. To make SDI practical at transformer scale, we propose a TensorSketch implementation that never materialises per-example gradients. Experiments on looped GPT-style models and algorithmic reasoning tasks show that SDI scales excellently, matches full-gradient baselines with low error and supports a broad range of data attribution and interpretability tasks with per-step insights into the latent reasoning process.

Inference-Time Scaling (ITS) improves language models by allocating more computation at generation time. Particle Filtering (PF) has emerged as a strong ITS method for complex mathematical reasoning tasks, but it is vulnerable when guided by process reward models, which often assign overconfident scores early in the reasoning process. This causes PF to suffer from premature exploitation: it myopically commits to locally promising trajectories, prunes potentially correct hypotheses, and converges to suboptimal solutions. This failure mode, known as particle impoverishment, is especially severe under constrained computational budgets. To address this, we analyze the problem and identify two root causes: a lack of diversity in the particle set due to overconfident resampling and consequent inability to assess the potential of a reasoning path. We introduce Entropic Particle Filtering (ePF), an algorithm that integrates two new techniques to solve these issues. The first technique, Entropic Annealing (EA), directly mitigates particle impoverishment by monitoring search diversity via entropy; when diversity drops, it intervenes by dynamically annealing the resampling distribution to preserve exploration. The second, an enhancement called Look-ahead Modulation (LaM), adds a predictive guide to evaluate a state's potential based on its successors. By effectively balancing exploration and exploitation, ePF significantly outperforms strong baselines on challenging math benchmarks, achieving up to a 50% relative improvement in task reward.

Scalable Vector Graphics (SVG) animation generation is pivotal for professional design due to their structural editability and resolution independence. However, this task remains challenging as it requires bridging discrete code representations with continuous visual dynamics. Existing optimization-based methods often destroy topological consistency, while general-purpose LLMs rely on rigid CSS/SMIL transformations, failing to model geometry-level non-rigid deformations. To address these limitations, we present VAnim, the first LLM-based framework for open-domain text-to-SVG animation. We reconceptualize animation not as sequence generation, but as Sparse State Updates (SSU) on a persistent SVG DOM tree. This paradigm compresses sequence length by over 9.8x while mathematically guaranteeing topological isomorphism and identity persistence. To enable precise control, we propose an Identification-First Motion Planning mechanism that grounds textual instructions in explicit visual entities. Furthermore, to overcome the non-differentiable nature of SVG rendering, we employ Rendering-Aware Reinforcement Learning via Group Relative Policy Optimization (GRPO). By leveraging a hybrid reward from a state-of-the-art video perception encoder, we align discrete code updates with high-fidelity visual feedback. We also introduce SVGAnim-134k, the first benchmark for vector animation. Extensive experiments demonstrate that VAnim significantly outperforms state-of-the-art baselines in semantic alignment and structural validity, demonstrating a robust capacity for synthesizing high-fidelity non-rigid deformations without requiring explicit temporal consistency constraints.

Inference-time compute has re-emerged as a practical way to improve LLM reasoning. Most test-time scaling (TTS) algorithms rely on autoregressive decoding, which is ill-suited to discrete diffusion language models (dLLMs) due to their parallel decoding over the entire sequence. As a result, developing effective and efficient TTS methods to unlock dLLMs' full generative potential remains an underexplored challenge. To address this, we propose \textbf{LLaDA-S}, an efficient TTS framework for dLLMs that (i) performs \textbf{Hierarchical Trajectory Search} (HTS) which dynamically prunes and reallocates compute in an early-to-mid denoising window, (ii) replaces external verifiers with \textbf{Self-Verified Feedback} (SVF) obtained via self-evaluation prompts on intermediate completions, and (iii) introduces \textbf{Local branching with partial remasking} to explore diverse implementations while preserving a high-confidence tokens. Across four mathematical reasoning and code generation benchmarks on three dLLMs, including LLaDA 8B Instruct, Dream 7B Instruct, and LLaDA 2.0-mini, our LLaDA-S achieves a favorable performance-efficiency trade-off, matching best-of-$N$ performance with substantially fewer function evaluations (NFE). The code will be released.

Large language models (LLMs) have achieved remarkable performance on a wide range of tasks, hindering real-world deployment due to their massive size. Existing pruning methods (e.g., Wanda) tailored for LLMs rely heavily on manual design pruning algorithms, thereby leading to $\textit{huge labor costs}$ and $\textit{requires expert knowledge}$. Furthermore, we are the first to identify the serious \textit{outlier value issue} behind dramatic performance degradation under high pruning ratios that are caused by uniform sparsity, raising an additional concern about how to design adaptive pruning sparsity ideal for LLMs. Can LLMs prune by themselves? In this work, we introduce an affirmative answer by proposing a novel pruning method called $\textbf{AutoPrune}$, which first overcomes expert knowledge limits by leveraging LLMs to design optimal pruning algorithms for themselves automatically without any expert knowledge. Specifically, to mitigate the black-box nature of LLMs, we propose a Graph-driven Chain-of-Thought (GCoT) to optimize prompts, significantly enhancing the reasoning process in learning the pruning algorithm and enabling us to generate pruning algorithms with superior performance and interpretability in the next generation. Finally, grounded in insights of outlier value issue, we introduce Skew-aware Dynamic Sparsity Allocation (SDSA) to overcome the outlier value issue, mitigating performance degradation under high pruning ratios. We conduct extensive experiments on mainstream LLMs benchmarks, demonstrating the superiority of AutoPrune, which consistently excels state-of-the-art competitors. The code is available at: \url{https://anonymous.4open.science/r/AutoPrune}.

Test-Time Adaptation (TTA) aims to reconcile model generalization in the presence of distribution shifts. Current TTA methods usually leverage sample uncertainty to select reliable samples for model adjustment via entropy minimization (EM). However, sample uncertainty often relies on a plausible metric and leaves many unreliable samples into EM process, potentially leading to model collapse. Importantly, these excluded samples incur biased data features of the shifted distribution in TTA. This paper introduces SaTeen, a **S**tructural **A**lignment-based **Te**st-Tim**e** Adaptatio**n** method that performs two-fold aligning the structures of test samples with the reliable reference structures. Specifically, the two-fold alignments are 1) Intra-sample structure alignment, where SaTeen maximizes cross-entropy discrepancy between a sample (reference) and its structure-disrupted counterpart, with the assumption of stable dominant features; 2) Inter-sample structure alignment, where SaTeen minimizes the reconstruction error of test samples in the reference subspace spanned by the Incremental PCA on reliable samples, with the assumption of stale intrinsic data manifold. Our extensive experiments demonstrate that SaTeen achieves the state-of-the-art performance across various scenarios for both TTA and continual TTA.

Modern vision-language models achieve strong performance in static perception, but remain limited in the complex spatiotemporal reasoning required for embodied, egocentric tasks. A major source of failure is their reliance on temporal priors learned from passive video data, which often leads to spatiotemporal hallucinations and poor generalization in dynamic environments. To address this, we present EgoTSR, a curriculum-based framework for learning task-oriented spatiotemporal reasoning. EgoTSR is built on the premise that embodied reasoning should evolve from explicit spatial understanding to internalized task-state assessment and finally to long-horizon planning. To support this paradigm, we construct EgoTSR-Data, a large-scale dataset comprising 46 million samples organized into three stages: Chain-of-Thought supervision for explicit reasoning, weakly supervised tagging for internalizing reasoning, and long-horizon sequences composed of orthogonal atomic subtasks. We further introduce a Reasoning-Enhanced Task Decomposition mechanism that explicitly models causal dependencies between actions and objects, enabling controllable planning from high-level task descriptions. To rigorously validate our approach, we establish a Dual-Level Evaluation Framework that covers both atomic spatial perception and logical planning. Extensive experiments demonstrate that EgoTSR effectively eliminates chronological biases, achieving 92.4% accuracy on long-horizon logical reasoning tasks while maintaining 88.2% fine-grained perceptual precision, significantly outperforming existing open-source and closed-source state-of-the-art models.

Current 3D spatial reasoning methods face a fundamental trade-off: neuro-symbolic 3D (NS3D) concept learners achieve interpretable reasoning through compositional programs but are constrained to closed-set concept vocabularies and simple programs; end-to-end 3D multi-modal LLMs (3D MLLMs) could handle complex natural language and open-vocabulary concepts but suffer from black-box reasoning without explicit spatial verification. We introduce APEIRIA, a neuro-symbolic 3D MLLM to bridge two paradigms by distilling symbolic reasoning patterns into MLLMs with natural language chain-of-thought. Our three-stage curriculum progressively builds reasoning capabilities: a) 3D perception alignment grounds object visual-geometric features to the LLM, b) CoT-SFT teaches query decomposition and stepwise verification from symbolic program traces, and c) CoT-RL extends reasoning patterns to open-set concepts and deeply nested instructions. By transferring reasoning patterns rather than concept-specific knowledge, APEIRIA preserves key NS3D virtues: transparent reasoning and modular interchangeability of planning and perception components. Evaluations on grounding, question answering, and captioning show that APEIRIA surpasses prior NS3D methods and matches state-of-the-art 3D MLLMs on 3D spatial reasoning datasets, unifying symbolic methods' systematic reasoning with MLLMs' flexibility. Code is available at https://github.com/oceanflowlab/APEIRIA.

While Large Reasoning Models (LRMs) have demonstrated impressive capabilities in solving complex tasks through the generation of long reasoning chains, this reliance on verbose generation results in significant latency and computational overhead. To address these challenges, we propose \textbf{CoSMo} (\textbf{Co}nsistency-Guided \textbf{S}plit-\textbf{M}erge \textbf{O}ptimization), a framework designed to eliminate structural redundancy rather than indiscriminately restricting token volume. Specifically, CoSMo utilizes a split-merge algorithm that dynamically refines reasoning chains by merging redundant segments and splitting logical gaps to ensure coherence. We then employ structure-aligned reinforcement learning with a novel segment-level budget to supervise the model in maintaining efficient reasoning structures throughout training. Extensive experiments across multiple benchmarks and backbones demonstrate that CoSMo achieves superior performance, improving accuracy by \textbf{3.3} points while reducing segment usage by \textbf{28.7\%} on average compared to reasoning efficiency baselines.

While AI models often refuse explicitly unlawful requests, in real-world scenarios illegality often depends on context. We evaluate frontier models on contextual illegality across four corporate law scenarios in which routine actions—editing documents, trading stock, requesting payment, approving communications—become unlawful due to circumstances such as pending investigations or bankruptcy filings. We study both chat and agentic settings and compare results to a human baseline. The best-performing models consistently followed lawful requests and refused unlawful requests, though performance varied substantially between different scenarios and models. We also identify distinct failure modes, such as excessive refusal of lawful requests, and find higher performance in reasoning models and agentic environments. By studying contextual illegality in these controlled environments, we develop a methodology that can be extended to evaluate the legal compliance of AI models in additional scenarios and domains.

Associative memory has long underpinned the design of sequential models. Beyond recall, humans reason by *projecting future states and selecting goal-directed actions*, a capability that modern language models increasingly require but do not natively encode. While prior work uses reinforcement learning or test-time training, planning remains external to the model architecture. We formulate reasoning as *optimal control* and introduce the *Test-Time Control (TTC)* layer, which performs finite-horizon *LQR* planning over latent states at inference time, represents a *value function* within neural architectures, and leverages it as the nested objective to enable *planning before prediction*. To ensure scalability, we derive a hardware-efficient LQR solver based on a symplectic formulation and implement it as a fused CUDA kernel, enabling parallel execution with minimal overhead. Integrated as an adapter into pretrained LLMs, TTC layers improve mathematical reasoning performance by up to +27.8% on MATH-500 and 2-3$\times$ Pass@8 improvements on AMC and AIME, demonstrating that embedding optimal control as an architectural component provides an effective and scalable mechanism for reasoning beyond test-time training.

Recent advances in Large Reasoning Models have significantly improved chain-of-thought (CoT) capabilities via reinforcement learning (RL). However, generated reasoning chains frequently suffer from structural redundancy (i.e., \emph{overthinking}), incurring high computational overhead without improving answer correctness. Existing mitigation strategies typically rely on token-uniform length penalties, which provide coarse, segment-agnostic pressure toward shorter outputs and can inadvertently suppress useful reasoning alongside redundancy. To address this, we demonstrate that inefficiency concentrates in high-probability segments with low marginal utility. We derive a theoretical characterization of segment suboptimality under the correctness-length trade-off objective and propose \textsc{SLAT} (Segment-Level Adaptive Trimming), an RL framework that selectively suppresses redundant segments based on this criterion. Empirical results on standard benchmarks indicate that \textsc{SLAT} establishes a superior accuracy-efficiency Pareto frontier, reducing reasoning length by 50\% relative to uncompressed baselines while maintaining competitive accuracy. Overall, our results suggest that theoretically grounded, segment-aware trimming is a promising direction for efficient CoT reasoning in large language models.

Despite progress of Multimodal Large Language Models (MLLMs) in biomedical visual question answering (VQA), existing benchmarks provide limited assessment of their scientific reasoning capabilities. Most datasets adopt single-image question construction and outcome-oriented evaluation, where correctness is judged by answer plausibility rather than alignment with experimental evidence. Such formulations fail to capture the evidence-constrained, multi-step nature of biomedical reasoning, and obscure whether models can derive conclusions through causal interpretation of experimental observations. To address these critical gaps in reasoning evaluation, we propose a principled benchmark construction framework that reconstructs scientific reasoning paths directly from biomedical literature. By jointly modeling clusters of experimentally related images together with their captions and context, the framework generates tightly coupled question–reasoning–answer triples that require multi-image integration and explicit evidence-driven inference. Based on this framework, we introduce SORBE (Scientific Observation & Reasoning for Biomedical Evaluation), a large-scale multi-image pathology-derived biomedical VQA benchmark designed to evaluate evidence alignment and multi-step experimental reasoning. Under a process-oriented evaluation metric, state-of-the-art biomedical-specialized MLLMs exhibit substantial performance degradation, revealing systematic limitations in evidence grounding and causal reasoning that are not reflected by existing benchmarks. Data and code are available at: https://github.com/UniverseOfUniverse/SORBE.git.

As Large Language Model (LLM) ecosystems grow, routing queries to the most suitable model in a diverse pool has become a critical strategy for building efficient and high-performing AI systems. A common approach is to train a supervised router; however, this requires vast, expensive human-annotated preference data and creates models that are notoriously brittle, failing to generalize when faced with inevitable distribution shifts in user queries. Consequently, developing robust, unsupervised routing methods that adapt without retraining is a crucial research frontier. This challenge is severely amplified by Large Reasoning Models (LRMs), which introduce a dual problem for any label-free method: their outputs have a causal thinking $\to$ answer structure that must be modeled, and a structural imbalance where long reasoning text can dominate the final answer signal. We introduce ReasoningRouter, a novel framework that resolves these issues with a length-balanced embedding strategy and a probabilistic model capturing the thinking-to-answer dependency. The proposed Causal Triangulation Property enables the label-free estimation of component qualities and their causal link. Beyond competitive routing accuracy, ReasoningRouter offers unprecedented insights into model behavior, enabling separate quality assessment of reasoning and answer components while maintaining computational efficiency.

As large language models (LLMs) are increasingly deployed as interactive agents, open-ended human-AI interactions can involve deceptive behaviors with serious real-world consequences, yet existing evaluations remain largely scenario-specific and model-centric. We introduce *OpenDeception*, a lightweight framework for jointly evaluating deception risk from both sides of human-AI dialogue. It consists of a scenario benchmark with 50 real-world deception cases, an *IntentNet* that infers deceptive intent from agent reasoning, and a *TrustNet* that estimates user susceptibility. To address data scarcity, we synthesize high-risk dialogues via LLM-based role-and-goal simulation, and train the *TrustNet* using contrastive learning on controlled response pairs, avoiding unreliable scalar labels. Experiments on 11 LLMs and three large reasoning models show that over 90% of goal-driven interactions in most models exhibit deceptive intent, with stronger models displaying higher risk. A real-world case study adapted from a documented AI-induced suicide incident further demonstrates that our joint evaluation can proactively trigger warnings before critical trust thresholds are reached.

Mathematical search problems present a unique challenge for Reinforcement Learning (RL) due to vast search spaces and sparse rewards. In previous works, the Andrews-Curtis (AC) conjecture was established as an illustrative example of such problems. In this work, we identify a critical structural barrier in the AC landscape: a "Two Hump" distribution, where problem instances are either trivially solvable or effectively impossible, with a scarcity of intermediate "hard-but-solvable" instances required for effective learning. We tackle this challenge through two primary avenues: novel data generation techniques to populate the difficulty gap, and significant algorithmic enhancements including the introduction of supermoves and Transformer-based architectures. We demonstrate substantial performance improvements over previous baselines, and release new comprehensive benchmark datasets including **AC-19** (125,192 AC-trivial presentations of varying difficulty with length at most 19) and **AC-1M** (1,136,154 hard AC-trivial presentations of length at most 30), the first large-scale, publicly available datasets of this kind.

Large language models (LLMs) have demonstrated impressive reasoning capabilities by scaling test-time compute via long Chain-of-Thought (CoT). However, recent findings suggest that raw token counts are unreliable proxies for reasoning quality: increased generation length does not consistently correlate with accuracy and may instead signal “overthinking,” leading to performance degradation. In this work, we quantify inference-time effort by identifying *deep-thinking tokens*—tokens where internal predictions undergo significant revisions in deeper model layers prior to convergence. Across four challenging mathematical and scientific benchmarks (AIME 24/25, HMMT 25, and GPQA-diamond) and a diverse set of reasoning-focused models (GPT-OSS, DeepSeek-R1, and Qwen3), we show that *deep-thinking ratio* (the proportion of deep-thinking tokens in a generated sequence) exhibits a robust and consistently positive correlation with accuracy, substantially outperforming both length-based and confidence-based baselines. Leveraging this insight, we introduce Think@$n$, a test-time scaling strategy that prioritizes samples with high deep-thinking ratios. We demonstrate that Think@$n$ matches or exceeds standard self-consistency performance while significantly reducing inference costs by enabling the early rejection of unpromising generations based on short prefixes.