ICLR 2026 Papers

Fulfilling user needs through Large Language Model multi-turn, multi-step tool-use is rarely a straightforward process. Real user interactions are inherently $\textbf{wild}$, being intricate, messy, and flexible. We identify three key challenges from user behaviour: $\textit{compositional tasks}$ that demand efficient orchestration of tool-call topologies, $\textit{implicit intent}$ spread across dialogue turns that require contextual inference, and $\textit{instruction transition}$, which mixes task queries, clarifications, and casual conversation, forcing LLMs to adjust their policies on the fly. Existing benchmarks overlook these behaviors, making the apparent progress of LLMs on tool-use spurious. To address this, we introduce $\textbf{\textit{WildToolBench}}$, an LLM tool-use benchmark grounded in real-world user behavior patterns. Comprehensive evaluations of 57 LLMs reveal that no model achieves an accuracy of more than 15\%, indicating a substantial gap in the robustness of LLMs' agentic ability. Controlled experiments and in-depth analyses further indicate that the real challenge for LLM tool-use lies not in artificially complex tasks, but in the wild nature of user behavior, emphasizing the need to reconsider the interactions among $\textit{LLMs}$, $\textit{users}$, and $\textit{tools}$.

While message-passing NNs (MPNNs) are naturally invariant on graphs, they are fundamentally limited in expressive power. Canonicalization offers a powerful alternative by mapping each graph to a unique, invariant representation on which expressive encoders can operate. However, existing approaches rely on a single canonical sequence, which flattens the structure, distorts graph distances, and restricts expressivity. To address these limitations, we introduce Canonical Tree Cover Neural Networks (CTNNs), which represent the graph with a canonical spanning tree cover, i.e., a small collection of canonical trees covering all edges. Each tree is then processed with an existing expressive tree encoder. Theoretically, tree covers better preserve graph distances than sequences, and on sparse graphs, the cover recovers all edges with a logarithmic number of trees in the graph size, making CTNNs strictly more expressive than sequence-based canonicalization pipelines. Empirically, CTNNs consistently outperform invariant GNNs, random samplers, and sequence canonicalizations across graph classification benchmarks. Overall, CTNNs advance graph learning by providing an efficient, invariant, and expressive representation learning framework via tree cover-based canonicalization.

Tensor-based incomplete multi-view clustering has attracted significant research attention due to its capability to exploit high-order correlations across different views for revealing underlying cluster structures from partially observed multi-view data. However, most existing approaches construct tensors from adjacency matrices, which necessitate post-processing operations (e.g., singular value decomposition, SVD) and thereby introduce additional computational overhead and potential errors. Some approaches instead employ latent embedding tensors to avoid post-processing, but they often fail to capture the geometric structure of the underlying graph. To address these limitations, we propose **C**onst**A**nt degree **M**trix-driv**E**n incomp**L**ete multi-view clustering via connectivity-structure and embedding tensor learning (**CAMEL**). Specifically, CAMEL jointly learns view-specific latent embeddings under structured constraints and organizes them into a tensor with an ${\ell_{\delta}}$ low-rank constraint, thereby enabling coordinated optimization of graph connectivity and high-order correlations. To further mitigate the $\mathcal{O}(n^2)$ or ever higher complexity complexity associated with conventional connectivity constraints, CAMEL approximates the variable Laplacian degree matrix with a constant-degree matrix, reducing the computational cost to $\mathcal{O}(1)$. Clustering assignments are subsequently derived via $k$-means on the concatenated embeddings, eliminating the need for post-processing operations on adjacency matrices such as SVD. Extensive experiments on nine benchmark datasets demonstrate the superior effectiveness and efficiency of CAMEL.

Speech inherently contains rich acoustic information that extends far beyond the textual language. In real-world spoken communication, effective interpretation often requires integrating semantic meaning (e.g., content), paralinguistic features (e.g., emotions, speed, pitch) and phonological characteristics (e.g., prosody, intonation, rhythm), which are embedded in speech. While recent multimodal Speech Large Language Models (SpeechLLMs) have demonstrated remarkable capabilities in processing audio, their ability to perform fine-grained perception and complex reasoning in natural speech remains largely unexplored. To address this gap, we introduce MMSU, a comprehensive benchmark designed specifically for understanding and reasoning in speech. MMSU comprises 5,000 meticulously curated audio-question-answer triplets across 47 distinct tasks. Notably, linguistic theory forms the foundation of speech language understanding (SLU), yet existing benchmarks have paid insufficient attention to this fundamental aspect and fail to capture the broader linguistic picture. To ground our benchmark in linguistic principles, we systematically incorporate a wide range of linguistic phenomena, including phonetics, prosody, rhetoric, syntactics, semantics, and paralinguistics. Through a rigorous evaluation of 22 advanced SpeechLLMs, we identify substantial room for improvement in existing models. MMSU establishes a new standard for comprehensive assessment of SLLU, providing valuable insights for developing more sophisticated human-AI speech interaction systems.

Evaluating the abilities of large language models (LLMs) for tasks that require long-term memory and thus long-context reasoning, for example in conversational settings, is hampered by the existing benchmarks, which often lack narrative coherence, cover narrow domains, and only test simple recall-oriented tasks. This paper introduces a comprehensive solution to these challenges. First, we present a novel framework for automatically generating long (up to 10M tokens), coherent, and topically diverse conversations, accompanied by probing questions targeting a wide range of memory abilities. From this, we construct BEAM, a new benchmark comprising 100 conversations and 2,000 validated questions. Second, to enhance model performance, we propose LIGHT–a framework inspired by human cognition that equips LLMs with three complementary memory systems: a long-term episodic memory, a short-term working memory, and a scratchpad for accumulating salient facts. Our experiments on BEAM reveal that even LLMs with 1M token context windows (with and without retrieval-augmentation) struggle as dialogues lengthen. In contrast, LIGHT consistently improves performance across various models, achieving an average improvement of 3.5%–12.69% over the strongest baselines, depending on the backbone LLM. An ablation study further confirms the contribution of each memory component.

Despite rapid advances in code generation, current Large Language Models (LLMs) still lack an essential capability for reliable and verifiable code generation: compositional reasoning across multi-function programs. To explore this potential and important gap, we introduce DafnyCOMP, a benchmark designed to systematically evaluate LLMs on the generation of compositional specifications in Dafny. Unlike prior benchmarks that primarily target single-function annotation, DafnyCOMP focuses on programs composed of multiple interacting functions with necessary data dependencies, requiring LLMs to produce specifications that ensure correctness across component boundaries. Our benchmark comprises 300 automatically synthesized programs, each carefully constructed by combining 2–5 originally independent functions in a chain-based manner through LLM-driven synthesis. We evaluate LLMs from five leading research groups that represent the current frontier of reasoning-centric AI, including the GPT, Claude, Gemini, DeepSeek, and Qwen families. Our results reveal a striking dichotomy: while LLMs achieve both high syntax correctness (>99%) and moderate verification rates (>58%) in prior single-function benchmarks, they exhibit degraded syntax correctness (95.67%) and a catastrophic verification failure (3.69%) in DafnyCOMP's compositional tasks— a 92% performance gap. Even the most powerful LLM achieves only 7% verification at Pass@8, with most LLMs below 2%. Further analysis reveals that LLMs systematically fail at cross-functional reasoning through three primary failure modes: specification fragility (39.2%), implementation-proof misalignment (21.7%), and reasoning instability (14.1%). These failures clearly reveal the absence of compositional reasoning capabilities in current LLMs. DafnyCOMP thus establishes a diagnostic benchmark for tracking progress in verifiable code generation with LLMs, highlighting that the path from local to compositional verification remains largely uncharted.

We present **THEMIS**, a novel multi-task benchmark designed to comprehensively evaluate Multimodal Large Language Models (MLLMs) on visual fraud reasoning within real-world academic scenarios. Compared to existing benchmarks, THEMIS introduces three major advancements. (1) **Real-world Scenarios & Complexity**: Our benchmark comprises over 4K questions spanning 7 scenarios, derived from authentic retracted-paper cases and carefully curated multimodal synthetic data. With 73.73% complex-texture images, THEMIS bridges the critical gap between existing benchmarks and the complexity of real-world academic fraud. (2) **Task Diversity & Granularity**: THEMIS systematically covers five challenging tasks and introduces 16 fine-grained manipulation operations. On average, each sample undergoes multiple stacked manipulation operations, with the diversity and difficulty of these manipulations demanding a high level of visual fraud reasoning from the models. (3) **Multi-dimensional Capability Evaluation**: We establish a mapping from fraud tasks to five core visual fraud reasoning capabilities, thereby enabling an evaluation that reveals the distinct strengths and specific weaknesses of different models across these core capabilities. Experiments on 11 leading MLLMs show that even the best-performing model still falls below the passing threshold, demonstrating that our benchmark presents a stringent test. We expect THEMIS to advance the development of MLLMs for complex, real-world fraud detection tasks. The data and code will be updated on url: https://anonymous.4open.science/r/themis1638.

The rapid advancement of multimodal large language models has demonstrated impressive capabilities, yet nearly all operate in an offline paradigm, hindering real-time interactivity. Addressing this gap, we introduce the Real-tIme Video intERaction Bench (RIVER Bench), designed for evaluating online video comprehension. RIVER Bench introduces a novel framework comprising Retrospective Memory, Live-Perception, and Proactive Anticipation tasks, closely mimicking interactive dialogues rather than responding to entire videos at once. We conducted detailed annotations using videos from diverse sources and varying lengths, and precisely defined the real-time interactive format. Evaluations across various model categories reveal that while offline models perform well in single question-answering tasks, they struggle with real-time processing. Addressing the limitations of existing models in online video interaction, especially their deficiencies in long-term memory and future perception, we proposed a general improvement method that enables models to interact with users more flexibly in real time. We believe this work will significantly advance the development of real-time interactive video understanding models and inspire future research in this emerging field. The code and data will be released.

The sequential structure of videos poses a challenge to the ability of multimodal large language models (MLLMs) to locate multi-frame evidence and conduct multimodal reasoning. However, existing video benchmarks mainly focus on understanding tasks, which only require models to match frames mentioned in the question (hereafter referred to as "question frame'') and perceive a few adjacent frames. To address this gap, we propose **MMR-V: A Benchmark for Multimodal Deep Reasoning in Videos**. The benchmark is characterized by the following features. **(1) Long-range, multi-frame reasoning**: Models are required to infer and analyze evidence frames that may be far from the question frame. **(2) Beyond perception**: Questions cannot be answered through direct perception alone but require reasoning over hidden information. **(3) Reliability**: All tasks are manually annotated, referencing extensive real-world user understanding to align with common perceptions. **(4) Confusability**: Carefully designed distractor annotation strategies to reduce model shortcuts. MMR-V consists of 317 videos and 1,257 tasks. Our experiments reveal that current models still struggle with multi-modal reasoning; even the best-performing model, Gemini-2.5-pro, achieves only 64.3% accuracy. Additionally, current reasoning enhancement strategies (Chain-of-Thought and scaling test-time compute) bring limited gains. Error analysis indicates that the CoT demanded for multi-modal reasoning differs from it in textual reasoning, which partly explains the limited performance gains. We hope that MMR-V can inspire further research into enhancing multi-modal reasoning capabilities.

Recent advances in AI agents capable of solving complex, everyday tasks-- from software engineering to customer service-- have enabled deployment in real-world settings, but their possibilities for unsafe behavior demands rigorous evaluation. While prior benchmarks have attempted to assess agent safety, most fall short by relying on simulated environments, narrow task domains, or unrealistic tool abstractions. We introduce OpenAgentSafety, a comprehensive and modular framework for evaluating agent behavior across eight critical risk categories. Unlike prior work, our framework evaluates agents that interact with real tools, including web browsers, code execution environments, file systems, bash shells, and messaging platforms; and supports over 350 multi-turn, multi-user tasks spanning both benign and adversarial user intents. OpenAgentSafety is designed for extensibility, allowing researchers to add tools, tasks, websites, and adversarial strategies with minimal effort. It combines rule-based evaluation with LLM-as-judge assessments to detect both overt and subtle unsafe behaviors. Empirical analysis of five prominent LLMs in agentic scenarios reveals unsafe behavior in 51.2% of safety-vulnerable tasks with Claude-Sonnet-3.7, to 72.7% with o3-mini, highlighting critical risks and the need for stronger safeguards before real-world deployment of LLM agents.

Large language models learn from their vast pre-training corpora, gaining the ability to solve an ever increasing variety of tasks; yet although researchers work to improve these datasets, there is little effort to understand how efficient the pre-training apparatus is at extracting ideas and knowledge from the data. In this work, we use retrieval augmented generation along with test-time compute as a way to quantify how much dataset value was left behind by the process of pre-training, and how this changes across scale. We demonstrate that pre-training then retrieving from standard and largely open-sourced datasets results in significant accuracy gains in MMLU, Math-500, and SimpleQA, which persist through decontamination. For MMLU we observe that retrieval acts as a ~5x compute multiplier versus pre-training alone. We show that these results can be further improved by leveraging additional compute at test time to parse the retrieved context, demonstrating a 10 percentage point improvement on MMLU for the public LLaMA 3.1 8B model. Overall, our results suggest that today's pre-training methods do not make full use of the information in existing pre-training datasets, leaving significant room for progress.

Long-form legal reasoning remains a key challenge for large language models (LLMs) in spite of recent advances in test-time scaling. To address this, we introduce ***LEXam***, a novel benchmark derived from 340 law exams spanning 116 law school courses across a range of subjects and degree levels. The dataset comprises 4,886 law exam questions in English and German, including 2,841 long-form, open-ended questions and 2,045 multiple-choice questions. Besides reference answers, the open questions are also accompanied by explicit guidance outlining the expected legal reasoning approach such as issue spotting, rule recall, or rule application. Our evaluation on both open-ended and multiple-choice questions present significant challenges for current LLMs; in particular, they notably struggle with open questions that require structured, multi-step legal reasoning. Moreover, our results underscore the effectiveness of the dataset in differentiating between models with varying capabilities. Deploying an ensemble LLM-as-a-Judge paradigm with rigorous human expert validation, we demonstrate how model-generated reasoning steps can be evaluated consistently and accurately, closely aligning with human expert assessments. Our evaluation setup provides a scalable method to assess legal reasoning quality beyond simple accuracy metrics. Anonymous repository: [this URL](https://anonymous.4open.science/r/LEXam-anonymous-12EB).

RAG (Retrieval-Augmented Generation) systems and web agents are increasingly evaluated on multi-hop deep search tasks, yet current practice suffers from two major limitations. First, most benchmarks leak the reasoning path in the question text, allowing models to follow surface cues rather than discover reasoning chains autonomously. Second, evaluation is typically reduced to a single pass rate, which collapses diverse behaviors into one score and obscures whether failures stem from inadequate search, poor knowledge use, or inappropriate refusal. To address these issues, we present WebDetective, a benchmark of hint-free multi-hop questions paired with a controlled Wikipedia sandbox that ensures full traceability of model actions, and a holistic evaluation framework that separates search sufficiency, knowledge utilization, and refusal behavior. Our evaluation of 25 state-of-the-art models reveals systematic weaknesses across all architectures: models struggle with knowledge utilization despite having sufficient evidence and demonstrate near-absent appropriate refusal when evidence is lacking. These patterns expose a fundamental gap—today's systems excel at executing given reasoning paths but fail when required to discover them. We develop an agentic workflow EvidenceLoop that explicitly targets the challenges our benchmark identifies, incorporating verification loops and systematic evidence tracking that improve both search and synthesis capabilities. This baseline demonstrates that WebDetective's diagnostic framework can guide concrete architectural improvements, establishing our benchmark as a critical tool for developing genuinely autonomous reasoning systems rather than pattern-following agents.

Understanding human behavior traits is central to applications in human-computer interaction, computational social science, and personalized AI systems. Such understanding often requires integrating multiple modalities to capture nuanced patterns and relationships. However, existing resources rarely provide datasets that combine behavioral descriptors with complementary modalities such as facial attributes and biographical information. To address this gap, we present PersonaX, a curated collection of multimodal datasets designed to enable comprehensive analysis of public traits across modalities. PersonaX consists of (1) CelebPersona, featuring 9444 public figures from diverse occupations, and (2) AthlePersona, covering 4181 professional athletes across 7 major sports leagues. Each dataset includes behavioral trait assessments inferred by three high-performing large language models, alongside facial imagery and structured biographical features. We analyze PersonaX at two complementary levels. First, we abstract high-level trait scores from text descriptions and apply five statistical independence tests to examine their relationships with other modalities. Second, we introduce a novel causal representation learning (CRL) framework tailored to multimodal and multi-measurement data, providing theoretical identifiability guarantees. Experiments on both synthetic and real-world data demonstrate the effectiveness of our approach. By unifying structured and unstructured analysis, PersonaX establishes a foundation for studying LLM-inferred behavioral traits in conjunction with visual and biographical attributes, advancing multimodal trait analysis and causal reasoning. The code is available at https://github.com/lokali/PersonaX.

Motivated by the prevalence and success of machine learning, a line of recent work has studied learning-augmented algorithms in the streaming model. These results have shown that for natural and practical oracles implemented with machine learning models, we can obtain streaming algorithms with improved space efficiency that are otherwise provably impossible. On the other hand, our understanding is much more limited for the sliding window model, which captures applications where either recent data leads to better or older data must be expunged from the dataset, e.g., by privacy regulation laws. In this paper, we utilize an oracle for the heavy-hitters of datasets to give learning-augmented algorithms for a number of fundamental problems in the sliding window model, such as norm/moment estimation, frequency estimation, cascaded norms, and rectangular moment estimation. We complement our theoretical results with a number of empirical evaluations that demonstrate the practical efficiency of our algorithms on real and synthetic datasets.

The ability of modern language models to easily extract unstructured sensitive information has made redaction—the selective removal of such information—an essential task for data security. However, existing benchmarks and evaluation methods for redaction are often limited to predefined categories of data like personally identifiable information (PII), or particular techniques like masking. To bridge this gap, we introduce RedacBench, a novel benchmark for a comprehensive evaluation of redaction capabilities, independent of specific domains or redaction strategies. Constructed from 514 human-written texts from individuals, corporations, and governments, along with 187 security policies, RedacBench measures a model's ability to selectively remove policy-violating information while preserving the original text's utility. We robustly quantify this performance using metrics derived from 8,053 inferable propositions, assessing both security—through the redaction of sensitive propositions—and utility—through the preservation of non-sensitive ones. Our experiments on various redaction strategies using state-of-the-art language models reveal that while more advanced models and strategies can increase security, maintaining utility remains a significant challenge. To facilitate future research, we publicly release RedacBench along with a web-based playground for custom dataset creation and evaluation at https://redacbench.vercel.app/.

Methods addressing Learning with Noisy Labels (LNL) and multi-source Domain Generalization (DG) use training techniques to improve downstream task performance in the presence of label noise or domain shifts, respectively. Prior work often explores these tasks in isolation, with only limited work that evaluates how label noise affects existing DG methods without also exploring methods to reduce its effect. However, many applications require methods that are robust to both label noise and distribution shifts, which we refer to as Noise-Aware Generalization (NAG), and when these problems are considered together new challenges emerge. E.g., most LNL methods identify noise by detecting distribution shifts in a class’s samples, i.e., they assume that distribution shifts often correspond to label noise. In NAG distribution shifts can be due to label noise or domain shifts, breaking the assumptions used by LNL methods. DG methods often overlook the effect of label noise entirely, which can confuse a model during training, reducing performance. A naive solution to this issue is to make a similar assumption as many DG methods, where we presume to have domain labels during training, enabling us to isolate the two types of shifts. However, this ignores valuable cross-domain information. Specifically, our proposed DL4ND approach improves noise detection by taking advantage of the observation that noisy samples that may appear indistinguishable within a single domain often show greater variation when compared across domains. Experiments show DL4ND significantly improves performance across seven diverse datasets, offering a promising direction for tackling NAG.

Subcellular localization is a crucial biological task for drug target identification and function annotation. Although it has been biologically realized that subcellular localization is closely associated with protein structure, no existing dataset offers comprehensive 3D structural information with detailed subcellular localization annotations, thus severely hindering the application of promising structure-based models on this task. To address this gap, we introduce a new benchmark called $\textbf{CAPSUL}$, a $\textbf{C}$omprehensive hum$\textbf{A}$n $\textbf{P}$rotein benchmark for $\textbf{SU}$bcellular $\textbf{L}$ocalization. It features a dataset that integrates diverse 3D structural representations with fine-grained subcellular localization annotations carefully curated by domain experts. We evaluate this benchmark using a variety of state-of-the-art sequence-based and structure-based models, showcasing the importance of involving structural features in this task. Furthermore, we explore reweighting and single-label classification strategies to facilitate future investigation on structure-based methods for this task. Lastly, we showcase the powerful interpretability of structure-based methods through a case study on the Golgi apparatus, where we discover a decisive localization pattern $\alpha$-helix from attention mechanisms, demonstrating the potential for bridging the gap with intuitive biological interpretability and paving the way for data-driven discoveries in cell biology.

Large language models (LLMs) have recently demonstrated remarkable progress in formal theorem proving. Yet their ability to serve as practical assistants for mathematicians—filling in missing steps within complex proofs—remains underexplored. We identify this challenge as the task of subgoal completion, where an LLM must discharge short but nontrivial proof obligations left unresolved in a human-provided sketch. To study this problem, we introduce FormalML, a Lean 4 benchmark built from foundational theories of machine learning. Using a translation tactic that converts procedural proofs into declarative form, we extract 4,937 problems spanning optimization and probability inequalities, with varying levels of difficulty. FormalML is the first subgoal completion benchmark to combine premise retrieval and complex research-level contexts. Evaluation of state-of-the-art provers highlights persistent limitations in accuracy and efficiency, underscoring the need for more capable LLM-based theorem provers for effective subgoal completion.