ICLR 2026 Papers

Dynamic Text-Attribute Graphs (DyTAGs), characterized by time-evolving graph interactions and associated text attributes, are prevalent in real-world applications. Existing methods, such as Graph Neural Networks (GNNs) and Large Language Models (LLMs), mostly focus on static TAGs. Extending these existing methods to DyTAGs is challenging as they largely neglect the *recent-global temporal semantics*: the recent semantic dependencies among interaction texts and the global semantic evolution of nodes over time. Furthermore, applying LLMs to the abundant and evolving text in DyTAGs faces efficiency issues. To tackle these challenges, we propose $\underline{Dy}$namic $\underline{G}$lobal-$\underline{R}$ecent $\underline{A}$daptive $\underline{S}$emantic $\underline{P}$rocessing (DyGRASP), a novel method that leverages LLMs and temporal GNNs to efficiently and effectively reason on DyTAGs. Specifically, we first design a node-centric implicit reasoning method together with a sliding window mechanism to efficiently capture recent temporal semantics. In addition, to capture global semantic dynamics of nodes, we leverage explicit reasoning with tailored prompts and an RNN-like chain structure to infer long-term semantics. Lastly, we intricately integrate the recent and global temporal semantics as well as the dynamic graph structural information using updating and merging layers. Extensive experiments on DyTAG benchmarks demonstrate DyGRASP's superiority, achieving up to 34\% improvement in Hit@10 for destination node retrieval task. Besides, DyGRASP exhibits strong generalization across different temporal GNNs and LLMs.

Geometric problem solving constitutes a critical branch of mathematical reasoning, requiring precise analysis of shapes and spatial relationships. Current evaluations of geometric reasoning in vision-language models (VLMs) face limitations, including the risk of test data contamination from textbook-based benchmarks, overemphasis on final answers over reasoning processes, and insufficient diagnostic granularity. To address these issues, we present GeoBench, a hierarchical benchmark featuring four reasoning levels in geometric problem-solving: Visual Perception, Goal-Oriented Planning, Rigorous Theorem Application, and Self-Reflective Backtracking. Through six formally verified tasks generated via TrustGeoGen, we systematically assess capabilities ranging from attribute extraction to logical error correction. Experiments reveal that while reasoning models like OpenAI-o3 outperform general MLLMs, performance declines significantly with increasing task complexity. Key findings demonstrate that sub-goal decomposition and irrelevant premise filtering critically influence final problem-solving accuracy, whereas Chain-of-Thought prompting unexpectedly degrades performance in some tasks. These findings establish GeoBench as a comprehensive benchmark while offering actionable guidelines for developing geometric problem-solving systems. Our benchmark and code are released at https://anonymous.4open.science/r/GeoBench-4BF4.

Large language models (LLMs) often solve drill-style math exercises yet fail to apply the concept right when the problem requires genuine understanding. Popular outcome-based RL pipelines reinforce final answers but provide little fine-grained conceptual signal, so models improve at pattern reuse rather than concept selection and use. We introduce $\textit{CORE}$ (Concept-Oriented REinforcement), an algorithm-agnostic training framework that turns explicit concepts into a controllable supervision signal. Starting from a high-quality, low-contamination textbook resource that links verifiable exercises to concise concept descriptions, we run a sanity probe showing LLMs can restate definitions while missing concept-linked quizzes, quantifying the conceptual reasoning gap. $\textit{CORE}$ then (i) synthesizes additional concept-aligned quizzes, (ii) injects concept snippets into rollouts, and (iii) reinforces trajectories that correctly apply the injected concept while constraining drift with a lightweight divergence penalty; the procedure is compatible with standard policy-gradient methods (e.g., GRPO). On a 7B-class model, $\textit{CORE}$ yields consistent gains over a vanilla baseline and reinforcement-only training across in-domain concept–exercise suites and diverse out-of-domain math benchmarks (GSM8K, SVAMP, MAWPS, SAT-Math, OlympiadBench, Gaokao, Minerva-Math, CounterMath, TheoremQA). Improvements are largest on concept-heavy categories while maintaining or modestly improving drill performance. $\textit{CORE}$ demonstrates that concept-injected, outcome-regularized rollouts supply the missing fine-grained supervision needed to bridge drill competence and true conceptual reasoning—without committing to a particular RL algorithm or certain process-based verifiers.

Reinforcement Learning (RL) has become the _de facto_ standard for tuning LLMs to solve tasks involving reasoning. However, growing evidence shows that such models often suffer from a significant loss in diversity. We argue that this arises because RL implicitly optimizes the Reverse KL to a target distribution, which concentrates on certain high-probability regions of the target while neglecting others. In this work, we instead begin from an explicit target distribution, obtained by filtering out incorrect answers while preserving the relative probabilities of correct ones. Starting from a pre-trained LLM, we approximate this target distribution using Amari's $\alpha$-divergence family, which unifies prior approaches and enables direct control of the precision–diversity trade-off by interpolating between mode-seeking and mass-covering divergences. On a Lean theorem-proving benchmark, our method achieves state-of-the-art performance along the coverage–precision Pareto frontier, unmatched by other methods along the coverage axis.

Large Language Models (LLMs) are increasingly applied to complex tasks that require extended reasoning. In such settings, models often benefit from diverse chains-of-thought to arrive at multiple candidate solutions. This requires two competing objectives: to inject enough stochasticity to explore multiple reasoning chains, and to ensure sufficient accuracy and quality in each path. Existing works pursue the first objective by increasing exploration at highly uncertain steps with higher temperature or larger candidate token sets, while others improve reliability by rejecting samples with low confidence post generation, implying that low confidence correlates with low answer quality. These two lines of thought are in conflict, as they conflate different sources of uncertainty. To resolve this, we argue that the decoding rule should be calibrated by *correctness*, not confidence alone. We should sample from tokens with higher estimated correctness, and reduce sampling where expected correctness is low. We propose simple strategies that achieve this goal: **Greedy-Threshold** makes sampling greedy at very low confidence steps. **Calibrated-TopK** and **Calibrated-ε** set truncation threshold based on estimated rank-wise correctness. Together, our findings challenge prevailing heuristics about decoding under uncertainty, showing consistent gains across math and general reasoning benchmarks.

Omni-modal reasoning is essential for intelligent systems to understand and draw inferences from diverse data sources. While existing omni-modal large language models (OLLM) excel at perceiving diverse modalities, they lack the complex reasoning abilities of recent large reasoning models (LRM). However, enhancing the reasoning ability of OLLMs through additional training presents significant challenges, including the need for high-quality data, task-specific adaptation, and substantial computational costs. To address these limitations, we propose ThinkOmni, a training-free and data-free framework that lifts textual reasoning to omni-modal scenarios. ThinkOmni introduces two key components: 1) LRM-as-a-Guide, which leverages off-the-shelf LRMs to guide the OLLM decoding process; 2) Stepwise Contrastive Scaling, which adaptively balances perception and reasoning signals without manual hyperparameter tuning. Experiments on six multi-modal reasoning benchmarks demonstrate that ThinkOmni consistently delivers performance improvements, with main results achieving 70.2 on MathVista and 75.5 on MMAU. Overall, ThinkOmni offers a flexible and generalizable solution for omni-modal reasoning and provides new insights into the generalization and application of reasoning capabilities.

Scaling inference-time compute for Large Language Models (LLMs) has unlocked unprecedented reasoning capabilities. However, existing inference-time scaling methods typically rely on inefficient and suboptimal discrete search algorithms or trial-and-error prompting to improve the online policy. In this paper, we propose $\nabla$-reasoner, an iterative generation framework that integrates differentiable optimization over token logits into the decoding loop to refine the policy on the fly. Our core component, Differentiable Textual Optimization (DTO), leverages gradient signals from both the LLM’s likelihood and a reward model to refine textual representations. $\nabla$-reasoner further incorporates rejection sampling and acceleration design to robustify and speed up decoding. Theoretically, we show that performing inference-time gradient descent in the sample space to maximize reward is dual to aligning an LLM policy via KL-regularized reinforcement learning. Empirically, $\nabla$-reasoner achieves over 20% accuracy improvement on a challenging mathematical reasoning benchmark, while reducing number of model calls by approximately 10-40% compared to strong baselines. Overall, our work introduces a paradigm shift from zeroth-order search to first-order optimization at test time, offering a cost-effective path to amplify LLM reasoning.

The ability to distinguish subtle differences between visually similar images is essential for diverse domains such as industrial anomaly detection, medical imaging, and aerial surveillance. While comparative reasoning benchmarks for vision-language models (VLMs) have recently emerged, they primarily focus on images with large, salient differences and fail to capture the nuanced reasoning required for real-world applications. In this work, we introduce **VLM-SubtleBench**, a benchmark designed to evaluate VLMs on *subtle comparative reasoning*. Our benchmark covers ten difference types—Attribute, State, Emotion, Temporal, Spatial, Existence, Quantity, Quality, Viewpoint, and Action—and curate paired question–image sets reflecting these fine-grained variations. Unlike prior benchmarks restricted to natural image datasets, our benchmark spans diverse domains, including industrial, aerial, and medical imagery. Through extensive evaluation of both proprietary and open-source VLMs, we reveal systematic gaps between model and human performance across difference types and domains, and provide controlled analyses highlighting where VLMs’ reasoning sharply deteriorates. Together, our benchmark and findings establish a foundation for advancing VLMs toward human-level comparative reasoning.

Reinforcement learning (RL) has shown strong potential for enhancing reasoning in multimodal large language models (MLLMs), yet existing video reasoning methods often rely on coarse sequence-level rewards or single-factor token selection. Such approaches neglect fine-grained links among visual inputs, temporal dynamics, and linguistic outputs, limiting both accuracy and interpretability. We propose Video-KTR, a modality-aware policy shaping framework that performs selective, token-level RL by combining three attribution signals: (1) visual-aware tokens identified via counterfactual masking to reveal perceptual dependence; (2) temporal-aware tokens detected through frame shuffling to expose causal and temporal sensitivity; and (3) high-entropy tokens signaling predictive uncertainty. By reinforcing only the union of key tokens, Video-KTR focuses learning on semantically informative, modality-sensitive content while filtering out low-value tokens. Across five challenging benchmarks, Video-KTR achieves state-of-the-art or highly competitive results—42.7% on Video-Holmes, surpassing GPT-4o—with consistent gains on both reasoning-centric and general video understanding tasks. Ablation studies verify the complementary roles of the attribution signals and the robustness of targeted token-level updates. Overall, Video-KTR improves accuracy and interpretability, offering a simple, drop-in extension to RL for complex video reasoning.

Multimodal large language models (MLLMs) are well suited to image aesthetic assessment, as they can capture high-level aesthetic features leveraging their cross-modal understanding capacity. However, the scarcity of multimodal aesthetic reasoning data and the inherently subjective nature of aesthetic judgment make it difficult for MLLMs to generate accurate aesthetic judgments with interpretable rationales. To this end, we propose Aes-R1, a comprehensive aesthetic reasoning framework with reinforcement learning (RL). Concretely, Aes-R1 integrates a pipeline, AesCoT, to construct and filter high-quality chain-of-thought aesthetic reasoning data used for cold-start. After teaching the model to generate structured explanations prior to scoring, we then employ the Relative-Absolute Policy Optimization (RAPO), a novel RL algorithm that jointly optimizes absolute score regression and relative ranking order, improving both per-image accuracy and cross-image preference judgments. Aes-R1 enables MLLMs to generate grounded explanations alongside faithful scores, thereby enhancing aesthetic scoring and reasoning in a unified framework. Extensive experiments demonstrate that Aes-R1 improves the backbone’s average PLCC/SRCC by 47.9%/34.8%, surpassing state-of-the-art baselines of similar size. More ablation studies validate Aes-R1's robust generalization under limited supervision and in out-of-distribution scenarios.

State-of-the-art models for code representation, such as GraphCodeBERT, embed the hierarchical structure of source code into Euclidean space. This approach can lead to significant representation distortion, especially when embedding deep or highly branched hierarchies,limiting the models' ability to capture deep program semantics. We argue that the natural geometry for code is hyperbolic, as its exponential volume growth perfectly matches the tree-like structure of a code's Abstract Syntax Tree (AST), enabling low-distortion hierarchical embeddings. We introduce {HypeCodeNet}, a geometric deep learning framework that operates natively in hyperbolic space. Formulated in the numerically stable Lorentz model, its manifold-aware components include a hyperbolic embedding layer, a tangent space message-passing mechanism, and a geodesic-based attention module. On code clone detection, code completion, and link prediction, HypeCodeNet significantly outperforms existing Euclidean models, especially on tasks requiring deep structural understanding. Our work suggests that hyperbolic geometry offers a geometrically sound foundation for code representation, establishing hyperbolic geometry as a key to unlocking the structured semantics of code.

Large Reasoning Models (LRMs) demonstrate exceptional capability in tackling complex mathematical, logical, and coding tasks by leveraging extended Chain-of-Thought (CoT) reasoning. Test-time scaling methods—such as prolonging CoT with explicit token-level exploration—can push LRMs’ accuracy boundaries, but they incur significant decoding overhead. A key inefficiency source is LRMs often generate redundant thinking CoTs, which demonstrate clear structured overthinking and underthinking patterns. Inspired by human cognitive reasoning processes and numerical optimization theories, we propose TrimR, a verifier-based, training-free, efficient framework to trim reasoning and enhance test-time scaling, explicitly tailored for production-level deployment. Our method employs a lightweight, pretrained, instruction-tuned verifier to detect and truncate redundant intermediate thoughts of LRMs without any LRM or verifier fine-tuning. We present both the core algorithm and asynchronous online system engineered for high-throughput industrial applications. Empirical evaluations on Ascend NPUs and vLLM show that our framework delivers substantial gains in inference efficiency under large-batch workloads. In particular, on the four MATH500, AIME24/25, and GPQA benchmarks, the reasoning runtime of QwQ-32B, DeepSeek-R1-Distill-Qwen-32B, and Pangu-R-38B is improved by up to 70% with negligible impact on accuracy.

Post-training methods, especially Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL), play an important role in improving large language models' (LLMs) complex reasoning abilities. However, the dominant two-stage pipeline (SFT then RL) suffers from a key inconsistency: SFT enforces rigid imitation that suppresses exploration and induces forgetting, limiting RL's potential for improvements. We address this inefficiency with TRAPO (**T**rust-**R**egion **A**daptive **P**olicy **O**ptimization), a hybrid framework that interleaves SFT and RL within each training instance by optimizing SFT loss on expert prefixes and RL loss on the model's own completions, unifying external supervision and self-exploration. To stabilize training, we introduce Trust-Region SFT (TrSFT), which minimizes forward KL divergence inside a trust region but attenuates optimization outside, effectively shifting toward reverse KL and yielding stable, mode-seeking updates favorable for RL. An adaptive prefix-selection mechanism further allocates expert guidance based on measured utility. Experiments on five mathematical reasoning benchmarks show that TRAPO consistently surpasses standard SFT, RL, and SFT-then-RL pipelines, as well as recent state-of-the-art approaches, establishing a strong new paradigm for reasoning-enhanced LLMs.

We present Mixture-of-Length (MoL), an approach for Question Answering (QA) with context that aims to improve the balance between reasoning quality and response efficiency. Our method introduces a principled difficulty assessment based on information-theoretic principles and a dual-objective reward mechanism that adaptively modulates response length. In our experiments, MoL exhibits an emergent behavior termed "intelligent brevity": the model tends to produce shorter responses for simpler queries and longer ones for more complex inputs. This property is desirable for human-computer interaction and can reduce inference costs. A post-hoc analysis of internal activations suggests a correlation between this output adaptivity and the effective number of layers that contribute during inference. On multiple QA benchmarks, MoL demonstrates competitive accuracy while substantially reducing tokens compared to baselines, indicating that difficulty-aware length modulation is a promising direction for efficient QA with context.

Obtaining high-quality generations in modern LLMs has largely been framed as a selection problem: identifying a single winning generation from a diverse pool of $N$ samples, the Best-of-$N$ (BoN). Yet, this approach is inherently zero-sum, discarding diverse and potentially useful information from the pool. Instead, we explore a collaborative setup, where all candidates can potentially contribute to the final winning generation. To this end, we propose Fusion-of-$N$ (FusioN): a method that uses a general LLM judge to synthesize the most informative elements of each sample into a single final answer. We compare FusioN to BoN in two settings, (i) test-time scaling, where we sample and aggregate from a single model at test-time (ii) synthetic data generation, where we fuse samples from a pool of diverse teachers to improve a student model. We extensively benchmark both setups across 11 languages, 3 diverse benchmarks and varying model scales. Across the bench, FusionN consistently outperforms BoN showing versatility and robustness both in test-time scaling and in downstream gains from synthetic data generation. We also perform extensive analysis on FusioN, where it shows surprising strengths and robustness under challenging settings. These results show that we should shift how we think about evaluating and utilizing LLM generations from a monolithic measure of quality, to embracing their polylithic nature. This shift allows us to integrate diverse strengths, unlock latent potential, and achieve improvements that were previously inaccessible through selection alone.

Abductive reasoning in knowledge graphs aims to generate plausible logical hypotheses from observed entities, with broad applications in areas such as clinical diagnosis and scientific discovery. However, due to a lack of controllability, a single observation may yield numerous plausible but redundant or irrelevant hypotheses on large-scale knowledge graphs. To address this limitation, we introduce the task of controllable hypothesis generation to improve the practical utility of abductive reasoning. This task faces two key challenges when controlling for generating long and complex logical hypotheses: hypothesis space collapse and hypothesis reward oversensitivity. To address these challenges, we propose **CtrlHGen**, a **C**on**tr**ollable **l**ogcial **H**ypothesis **Gen**eration framework for abductive reasoning over knowledge graphs, trained in a two-stage paradigm including supervised learning and subsequent reinforcement learning. To mitigate hypothesis space collapse, we design a dataset augmentation strategy based on sub-logical decomposition, enabling the model to learn complex logical structures by leveraging semantic patterns in simpler components. To address hypothesis reward oversensitivity, we incorporate smoothed semantic rewards including Dice and Overlap scores, and introduce a condition-adherence reward to guide the generation toward user-specified control constraints. Extensive experiments on three benchmark datasets demonstrate that our model not only better adheres to control conditions but also achieves superior semantic similarity performance compared to baselines. Our code is available at https://github.com/HKUST-KnowComp/CtrlHGen.

Recent advances in multimodal large language models (MLLMs) have catalyzed transformative progress in affective computing, enabling models to exhibit emergent emotional intelligence. Despite substantial methodological progress, current emotional benchmarks remain limited, as it is still unknown: (a) the generalization abilities of MLLMs across distinct scenarios, and (b) their reasoning capabilities to identify the triggering factors behind emotional states. To bridge these gaps, we present MME-Emotion, a systematic benchmark that assesses both emotional understanding and reasoning capabilities of MLLMs, enjoying scalable capacity, diverse settings, and unified protocols. As the largest emotional intelligence benchmark for MLLMs, MME-Emotion contains over 6,000 curated video clips with task-specific questioning-answering (QA) pairs, spanning broad scenarios to formulate eight emotional tasks. It further incorporates a holistic evaluation suite with hybrid metrics for emotion recognition and reasoning, analyzed through a multi-agent system framework. Through a rigorous evaluation of 20 advanced MLLMs, we uncover both their strengths and limitations, yielding several key insights: (1) Current MLLMs exhibit unsatisfactory emotional intelligence, with the best-performing model achieving only $39.3\%$ recognition score and $56.0\%$ Chain-of-Thought (CoT) score on our benchmark. (2) Generalist models (\emph{e.g.}, Gemini-2.5-Pro) derive emotional intelligence from generalized multimodal understanding capabilities, while specialist models (\emph{e.g.}, R1-Omni) can achieve comparable performance through domain-specific post-training adaptation. By introducing MME-Emotion, we hope that it can serve as a foundation for advancing MLLMs' emotional intelligence in the future.

Retrofitting large language models (LLMs) with new behaviors typically requires full finetuning or distillation—costly steps that must be repeated for every architecture. In this work, we introduce ⌘V (Command-V), a backpropagation-free behavior transfer method that copies an existing residual representation adapter from a donor model and pastes its effect into an architecturally different recipient model. ⌘V profiles layer activations on a small prompt set, derives linear converters between corresponding layers, and applies the donor intervention in the recipient’s activation space. This process does not require access to the original training data and needs minimal compute. In three case studies—safety-refusal enhancement, jailbreak facilitation, and automatic chain-of-thought reasoning—⌘V matches the performance of direct finetuning while using orders of magnitude less resources.

While humans naturally learn and adapt from past experiences, large language models (LLMs) and their agentic counterparts often fail to retain reasoning from previous tasks and apply it in future contexts. We introduce **L**og-**A**ugmented **G**eneration (LAG), a novel framework that *directly reuses* prior computation and reasoning from past logs at test time, enabling models to learn from previous tasks and perform better on new, unseen challenges, without sacrificing the system's efficiency or scalability. Our approach represents task logs as key-value (KV) caches that encode the full reasoning context of prior tasks, while storing KV values for only a selected subset of tokens. When a new task arises, LAG retrieves KV values from relevant logs to augment generation. Unlike reflection-based memory mechanisms, which require additional extraction or distillation steps, LAG reuses prior reasoning verbatim. Moreover, it extends beyond existing KV caching techniques, which have primarily targeted efficiency, by explicitly improving accuracy through log reuse. Experiments on knowledge- and reasoning-intensive datasets demonstrate that our method significantly outperforms standard agentic systems that do not utilize logs, as well as existing solutions based on reflection and KV cache techniques.