ICLR 2026 论文列表

With the rapid progress of multimodal large language models (MLLMs), AI already performs well at literature retrieval and certain reasoning tasks, serving as a capable assistant to human researchers, yet it remains far from autonomous research. The fundamental reason is that current work on scholarly paper reasoning is largely confined to a search-oriented paradigm centered on pre-specified targets, with reasoning grounded in relevance retrieval, which struggles to support researcher-style full-document understanding, reasoning, and verification. To bridge this gap, we propose ScholScan, a new benchmark for scholarly paper reasoning. ScholScan introduces a scan-oriented task setting that asks models to read and cross-check entire papers like human researchers, scanning the document to identify consistency issues. The benchmark comprises 1,800 carefully annotated questions drawn from 9 error families across 13 natural-science domains and 715 papers, and provides detailed annotations for evidence localization and reasoning traces, together with a unified evaluation protocol. We assessed 15 models across 24 input configurations and conduct a fine-grained analysis of MLLM capabilities across error families. Across the board, retrieval-augmented generation (RAG) methods yield no significant improvements, revealing systematic deficiencies of current MLLMs on scan-oriented tasks and underscoring the challenge posed by ScholScan. We expect ScholScan to be the leading and representative work of the scan-oriented task paradigm.

Hard negative generation (HNG) provides valuable signals for deep learning, but existing methods mostly rely on local correlations while neglecting the global geometry of the embedding space. This limitation often leads to weak discrimination, particularly in cross-modal hashing, which obtains compact binary codes. We propose Deep Global-sense Hard-negative Discriminative Generation Hashing (DGHDGH), a framework that constructs a structured graph with dual-iterative message propagation to capture global correlations, and then performs difficulty-adaptive, channel-wise interpolation to synthesize semantically consistent hard negatives aligned with global Hamming geometry. Our approach yields more informative negatives, sharpens semantic boundaries in the Hamming co-space, and substantially enhances cross-modal retrieval. Experiments on multiple benchmarks consistently demonstrate improvements in retrieval accuracy, verifying the discriminative advantages brought by global-sense HNG in cross-modal hashing.

Large language models (LLMs) can be enhanced with external knowledge through two dominant approaches: (1) **retrieval-augmented generation (RAG)**, which supplements LLMs with in-context retrieved passages, and (2) **parametric knowledge adaptation (PKA)**, which directly updates model parameters with new domain knowledge. Recently, parametric RAG (PRAG) has emerged as a promising framework, extending RAG by translating retrieved passages into parameter updates, thereby mitigating inefficiency and noise sensitivity inherent to RAG. However, existing PRAG methods remain limited to single-pass retrieval, falling short of the \textbf{multi-hop RAG} setting that requires iterative retrieval and reasoning. We propose **MergePRAG**(*Orthogonal Merging of Passage-experts for Multi-hop PRAG*), a novel framework that sequentially integrates retrieved passages into LLM parameters through a continual merging mechanism, which is advanced by two key proposals: (1) **orthogonal merging** using the Gram–Schmidt process to minimize conflicts between "passage experts", and (2) **critical-layer parameterization** to efficiently encode in-context passages. Experiments on multi-hop open-domain QA and reasoning-aware knowledge editing show that MergePRAG consistently outperforms both standard and state-of-the-art RAGs as well as existing parametric adaptation methods, achieving superior effectiveness and efficiency. All datasets and code will be released at {https://anonymous.4open.science/r/MhQA_hypernetwork-B31F.

Generating a street-level 3D scene from a single satellite image is a crucial yet challenging task. Current methods present a stark trade-off: geometry-colorization models achieve high geometric fidelity but are typically building-focused and lack semantic diversity. In contrast, proxy-based models use feed-forward image-to-3D frameworks to generate holistic scenes by jointly learning geometry and texture, a process that yields rich content but coarse and unstable geometry. We attribute these geometric failures to the extreme viewpoint gap and sparse, inconsistent supervision inherent in satellite-to-street data. We introduce Sat3DGen to address these fundamental challenges, which embodies a geometry-first methodology. This methodology enhances the feed-forward paradigm by integrating novel geometric constraints with a perspective-view training strategy, explicitly countering the primary sources of geometric error. This geometry-centric strategy yields a dramatic leap in both 3D accuracy and photorealism. For validation, we first constructed a new benchmark by pairing the VIGOR-OOD test set with high-resolution DSM data. On this benchmark, our method improves geometric RMSE from 6.76m to 5.20m. Crucially, this geometric leap also boosts photorealism, reducing the Fr\'echet Inception Distance (FID) from $\sim$40 to 19 against the leading method, Sat2Density++, despite using no extra tailored image-quality modules. We demonstrate the versatility of our high-quality 3D assets through diverse downstream applications, including semantic-map-to-3D synthesis, multi-camera video generation, large-scale meshing, and unsupervised single-image Digital Surface Model (DSM) estimation.

Protein-protein interactions (PPIs) are mediated at the residue level. Most sequence-based PPI models consider residue-residue interactions across two proteins, which can yield accurate interaction scores but are too slow to scale. At proteome scale, identifying candidate PPIs requires evaluating nearly *all possible protein pairs*. For $N$ proteins of average length $L$, exhaustive all-against-all search requires $\mathcal{O}(N^2L^2)$ computation, rendering conventional approaches computationally impractical. We introduce RaftPPI, a scalable framework that approximates residue-level PPI modeling while enabling efficient large-scale retrieval. RaftPPI represents residue interactions with a Gaussian kernel, approximated efficiently via structured random Fourier features, and applies a low-rank factorized attention mechanism that admits pooling into a compact embedding per protein. Each protein is encoded once into an indexable embedding, allowing approximate nearest-neighbor search to replace exhaustive pairwise scoring, reducing proteome-wide retrieval from *months* to *minutes* on a single GPU. On the human proteome with the D-SCRIPT dataset, RaftPPI retrieves the top 20\% candidate pairs ($\sim$200M) in 6 GPU minutes, covering 75.1\% of the true interacting pairs, compared to 4.9 GPU months for the best prior method (61.2\%). Across seven benchmarks with sequence- and degree-controlled splits, RaftPPI achieves state-of-the-art PPI classification and retrieval performance, while enabling residue-aware, retrieval-friendly screening at proteome scale.

Recent benchmarks for Large Language Model (LLM) agents primarily focus on evaluating reasoning, planning, and execution capabilities, while another critical component—memory, encompassing how agents memorize, update, and retrieve long-term information—is under-evaluated due to the lack of benchmarks. We term agents with memory mechanisms as memory agents. In this paper, based on classic theories from memory science and cognitive science, we identify four core competencies essential for memory agents: accurate retrieval, test-time learning, long-range understanding, and selective forgetting. Existing benchmarks either rely on limited context lengths or are tailored for static, long-context settings like book-based QA, which do not reflect the interactive, multi-turn nature of memory agents that incrementally accumulate information. Moreover, no existing benchmarks cover all four competencies. We introduce MemoryAgentBench, a new benchmark specifically designed for memory agents. Our benchmark transforms existing long-context datasets and incorporates newly constructed datasets into a multi-turn format, effectively simulating the incremental information processing characteristic of memory agents. By carefully selecting and curating datasets, our benchmark provides comprehensive coverage of the four core memory competencies outlined above, thereby offering a systematic and challenging testbed for assessing memory quality. We evaluate a diverse set of memory agents, ranging from simple context-based and retrieval-augmented generation (RAG) systems to advanced agents with external memory modules and tool integration. Empirical results reveal that current methods fall short of mastering all four competencies, underscoring the need for further research into comprehensive memory mechanisms for LLM agents.

Information retrieval (IR) evaluation remains challenging due to incomplete IR benchmark datasets that contain unlabeled relevant chunks. While LLMs and LLM-human hybrid strategies reduce costly human effort, they remain prone to LLM overconfidence and ineffective AI-to-human escalation. To address this, we propose DREAM, a multi-round debate-based relevance assessment framework with LLM agents, built on opposing initial stances and iterative reciprocal critique. Through our agreement-based debate, it yields more accurate labeling for certain cases and more reliable AI-to-human escalation for uncertain ones, achieving 95.2% labeling accuracy with only 3.5% human involvement. Using DREAM, we build BRIDGE, a refined benchmark that mitigates evaluation bias and enables fairer retriever comparison by uncovering 29,824 missing relevant chunks. We then re-benchmark IR systems and extend evaluation to RAG, showing that unaddressed holes not only distort retriever rankings but also drive retrieval–generation misalignment. Code and data will be released upon acceptance.

Trustworthy language models should provide both correct and verifiable answers. However, citations generated directly by standalone LLMs are often unreliable due to hallucinations. As a result, current systems insert citations by querying an external retriever at inference time, introducing latency, infrastructure dependence, and vulnerability to retrieval noise. We explore whether LLMs can be made to reliably attribute to the documents seen during (continual) pretraining, without test‑time retrieval, by revising the training process. To study this, we construct **CitePretrainBench**, a benchmark that mixes real‑world corpora (Wikipedia, Common Crawl, arXiv) with novel, unseen documents and probes both short‑form (single fact) and long‑form (multi‑fact) citation tasks. Our approach follows a two-stage process: (1) Continual-pretraining to index factual knowledge by binding it to persistent document identifiers; (2) Instruction tuning to elicit citation behavior. We introduce **Active Indexing** for the first stage, which creates generalizable, source-anchored bindings by augmenting training with synthetic data that (i) restate each fact in diverse, compositional forms and (ii) enforce bidirectional training (source$\to$fact and fact$\to$source). This equips the model to both generate content from a cited source and attribute its own answers, improving robustness to paraphrase and composition. Experiments with Qwen‑2.5‑7B and 3B show that Active Indexing consistently outperforms a Passive Indexing baseline, which simply appends an identifier to each document, achieving citation precision gains of up to 30.2\% across all tasks and models. Our ablation studies reveal that performance continues to improve as we scale the amount of augmented data, showing a clear upward trend even at 16× the original token count. Finally, we show that internal citations complement external ones by making the model more robust to retrieval noise.

Universal multimodal retrieval (UMR), which aims to address complex retrieval tasks where both queries and candidates span diverse modalities, has been significantly advanced by the emergence of MLLMs. While state-of-the-art MLLM-based methods in the literature predominantly adopt contrastive learning principles, they often differ in their specific training recipes. Despite their success, the mechanisms underlying their retrieval capabilities remain largely unexplored, potentially resulting in suboptimal performance and limited generalization ability. To address these issues, we present a comprehensive study aimed at uncovering the key factors that drive effective embedding learning for UMR using MLLMs. We begin by implementing a general MLLM-based embedding learning pipeline, and systematically analyze the primary contributors to high-performing universal retrieval systems. Based on this, we explore various aspects of the details in embedding generation and training strategies, including progressive transition, hard negative mining and re-ranker distillation. Notably, our findings reveal that often-overlooked factors can have a substantial impact on model performance. Building on these discoveries, we introduce a unified framework termed U-MARVEL (Universal MultimodAl RetrieVal via Embedding Learning), which outperforms state-of-the-art competitors on the M-BEIR benchmark by a large margin in supervised settings, and also exhibits strong zero-shot performance on several tasks such as composed image retrieval and text-to-video retrieval. These results underscore the generalization potential of our framework across various embedding-based retrieval tasks.

Accurate auto-formalization of theorem statements is essential for advancing automated discovery and verification of research-level mathematics, yet remains a major bottleneck for LLMs due to hallucinations, semantic mismatches, and their inability to synthesize new definitions. To tackle these issues, we present Aria (**A**gent for **R**etrieval and **I**terative **A**utoformalization), a system for conjecture-level formalization in Lean that emulates human expert reasoning via a two-phase Graph-of-Thought process: recursively decomposing statements into a dependency graph and then constructing formalizations from grounded concepts. To ensure semantic correctness, we introduce **AriaScorer**, a checker that retrieves definitions from Mathlib for term-level grounding, enabling rigorous and reliable verification. We evaluate Aria on diverse benchmarks. On ProofNet, it achieves 91.6\% compilation success rate and 68.5\% final accuracy, surpassing previous methods. On FATE-X, a suite of challenging algebra problems from research literature, it outperforms the best baseline with 44.0\% vs. 24.0\% final accuracy. On a dataset of homological conjectures, Aria reaches 42.9\% final accuracy while all other models score 0\%.

Large Language Model (LLM)-based search agents have shown remarkable capabilities in solving complex tasks by dynamically decomposing problems and addressing them through interleaved reasoning and retrieval. However, this interleaved paradigm introduces substantial efficiency bottlenecks. First, we observe that both highly accurate and overly approximate retrieval methods degrade system efficiency: exact search incurs significant retrieval overhead, while coarse retrieval requires additional reasoning steps during generation. Second, we identify inefficiencies in system design, including improper scheduling and frequent retrieval stalls, which lead to cascading latency---where even minor delays in retrieval amplify end-to-end inference time. To address these challenges, we introduce \texttt{SearchAgent-X}, a high-efficiency inference framework for LLM-based search agents. \texttt{SearchAgent-X} leverages high-recall approximate retrieval and incorporates two key techniques: priority-aware scheduling and non-stall retrieval. Extensive experiments demonstrate that \texttt{SearchAgent-X} consistently outperforms state-of-the-art systems such as vLLM and HNSW-based retrieval across diverse tasks, achieving up to 3.4$\times$ higher throughput and 5$\times$ lower latency, without compromising generation quality. Code is available at \url{https://anonymous.4open.science/r/SearchAgent-X}.

Retrieval-Augmented Generation (RAG) significantly enhances Large Language Models by integrating external knowledge sources, but at the cost of substantial computational overhead from extended input sequences. Current RAG systems exhibit two fundamental inefficiencies: redundant processing of frequently retrieved text chunks across multiple queries, and uniform deep retrieval that over-provisions context regardless of query complexity. We present AdaCache, an adaptive caching framework that addresses these limitations through dual optimization strategies. First, we introduce a cache-aware partial recomputation mechanism that profiles attention patterns to construct selective cache variants, enabling flexible reuse while preserving cross-chunk dependencies. Second, we develop adaptive context augmentation that dynamically determines optimal retrieval depth via lightweight confidence estimation, avoiding unnecessary overhead on simple queries. Comprehensive experiments across diverse datasets and LLMs demonstrate that AdaCache delivers substantial improvements in Time-To-First-Token compared to state-of-the-art RAG caching systems, while preserving generation quality.

Large Language Models (LLMs) achieve impressive performance across many tasks but remain prone to hallucination, especially in long-form generation where redundant retrieved contexts and lengthy reasoning chains amplify factual errors. Recent studies highlight a critical phenomenon: the closer key information appears to the model outputs, the higher the factual accuracy. However, existing retrieval-augmented language models (RALMs) lack effective mechanisms to ensure this proximity — external evidence is injected into reasoning via multi-turn retrieval, but this cannot ensure key information stays close to the outputs. We propose Micro–Macro Retrieval ($M^2R$), a novel retrieve-while-generate framework to fill this gap. At the macro level, $M^2R$ retrieves coarse-grained evidence from external sources; at the micro level, it extracts essential results from a key information repository built during reasoning and reuses them while generating answers. This design directly addresses the key-information–to-output proximity bottleneck, effectively reducing hallucination in long-form tasks. $M^2R$ is trained with a curriculum learning–based reinforcement learning strategy using customized rule-based rewards, enabling stable acquisition of retrieval and grounding skills. Extensive experiments across different benchmarks demonstrate the effectiveness of $M^2R$, especially in lengthy-context settings.

Retrieval augmentation has primarily been studied in limited settings, such as factoid question answering; more challenging, reasoning-intensive benchmarks have seen limited success from minimal RAG. In this work, we challenge this prevailing view on a set of established, reasoning-intensive benchmarks: MMLU, MMLU Pro, AGI Eval, GPQA, and MATH. We identify a key missing component in prior work: a usable, web-scale datastore aligned with the breadth of pretraining data. To this end, we introduce CompactDS: a diverse, high-quality, web-scale datastore that achieves high retrieval accuracy and subsecond latency on a single-node deployment, making it suitable for academic use. Its core design combines a compact set of high-quality, diverse data sources with in-memory approximate nearest neighbor (ANN) retrieval and on-disk exact search. Using CompactDS, a minimal RAG pipeline achieves consistent accuracy improvements across all benchmarks and model sizes (8B--70B), with relative gains of 11% on MMLU, 34% on MMLU Pro, 26% on GPQA, and 14% on MATH. No single data source suffices alone, highlighting the importance of diversity of sources (web crawls, curated math, academic papers, textbooks), and a combination of ANN and exact search is shown to be critical for balancing usability and accuracy. Finally, we show that our in-house datastore even outperforms commercial search engines like Google Search. We release CompactDS and our retrieval pipeline as a fully reproducible alternative to commercial search, supporting future research exploring retrieval-based AI systems.

Behavior cloning suffers from poor generalization to out-of-distribution states due to compounding errors during deployment. We present Difference-Aware Retrieval Polices for Imitation Learning (DARP), a novel nearest-neighbor-based imitation learning approach that addresses this limitation by reparameterizing the imitation learning problem in terms of local neighborhood structure rather than direct state-to-action mappings. Instead of learning a global policy, DARP trains a model to predict actions based on k-nearest neighbors from expert demonstrations, their corresponding actions, and the relative distance vectors between neighbor states and query states. Our method requires no additional data collection, online expert feedback, or task-specific knowledge beyond standard behavior cloning prerequisites. We demonstrate consistent performance improvements of 15-46\% over standard behavior cloning across diverse domains, including continuous control and robotic manipulation, and across different representations, including high-dimensional visual features.

Knowledge graphs provide structured context for multi‑hop question answering, but deployed systems must balance answer accuracy with strict latency and cost targets while preserving provenance. Static $k$‑hop expansions and ``think‑longer'' prompting often over‑retrieve, inflate context, and yield unpredictable runtime. Thus, we introduce CLAUSE, an agentic three-agent neuro‑symbolic framework that treats context construction as a sequential decision process over knowledge graphs, deciding what to expand, which paths to follow or backtrack, what evidence to keep and when to stop. Latency (interaction steps) and prompt cost (selected tokens) are exposed as user‑specified budgets or prices, allowing per‑query adaptation to trade‑offs among accuracy, latency, and cost without retraining. CLAUSE employs the proposed Lagrangian‑Constrained Multi‑Agent Proximal Policy Optimization (LC‑MAPPO) algorithm to coordinate three agents: Subgraph Architect, Path Navigator, and Context Curator, so that subgraph construction, reasoning paths discovery, and evidence selection are jointly optimized under per‑query's resource budgets on edge edits, interaction steps, and selected tokens. Across HotpotQA, MetaQA, and FactKG, CLAUSE yields higher EM@1 while reducing subgraph growth and end-to-end latency at equal or lower token budgets. On MetaQA-2-hop, relative to the strongest RAG baseline (GraphRAG), CLAUSE achieves $+39.3$ EM@1 with 18.6% lower latency, and 40.9% lower edge growth. The resulting contexts are compact, provenance‑preserving, and deliver predictable performance under deployment constraints.

Molecular Dynamics (MD) simulations provide a fundamental tool for characterizing molecular behavior at full atomic resolution, but their applicability is severely constrained by the computational cost. To address this, a surge of deep generative models has recently emerged to learn dynamics at coarsened timesteps for efficient trajectory generation, yet they either generalize poorly across systems or, due to limited molecular diversity of trajectory data, fail to fully exploit structural information to improve generative fidelity. Here, we present the Pretrained Variational Bridge (PVB) in an encoder-decoder fashion, which maps the initial structure into a noised latent space and transports it toward stage-specific targets through augmented bridge matching. This unifies training on both single-structure and paired trajectory data, enabling consistent use of cross-domain structural knowledge across training stages. Moreover, for protein-ligand complexes, we further introduce a reinforcement learning-based optimization via adjoint matching that speeds progression toward the holo state, which supports efficient post-optimization of docking poses. Experiments on proteins and protein-ligand complexes demonstrate that PVB faithfully reproduces thermodynamic and kinetic observables from MD while delivering stable and efficient generative dynamics.

Unified, generalizable semantic control in video generation remains a critical open challenge. Existing methods either introduce artifacts by enforcing inappropriate pixel-wise priors from structure-based controls, or rely on non-generalizable, condition-specific finetuning or task-specific architectures. We introduce Video-As-Prompt (VAP), a new paradigm that reframes this problem as in-context generation. VAP leverages a reference video as a direct semantic prompt, guiding a frozen Video Diffusion Transformer (DiT) via a plug-and-play Mixture-of-Transformers (MoT) expert. This architecture prevents catastrophic forgetting and is guided by a temporally biased position embedding that eliminates spurious mapping priors for robust context retrieval. To power this approach and catalyze future research, we built VAP-Data, the largest dataset for this task with over 100K paired videos across 100 semantic conditions. As a single unified model, VAP sets a new state-of-the-art for open-source methods, achieving a 38.7\% user preference rate that rivals leading condition-specific commercial models. VAP's strong zero-shot generalization and support for various applications mark a significant advance toward general-purpose, controllable video generation.

Retrieval-Augmented Generation (RAG) leverages large language models (LLMs) combined with external contexts to enhance the accuracy and reliability of generated responses. However, reliably attributing generated content to specific context segments, context attribution, remains challenging due to the computationally intensive nature of current methods, which often require extensive fine-tuning or human annotation. In this work, we introduce a novel Jensen–Shannon Divergence driven method to Attribute Response to Context (ARC-JSD), enabling efficient and accurate identification of essential context sentences without additional fine-tuning, gradient-calculation or surrogate modelling. Evaluations on a wide range of RAG benchmarks, such as TyDi QA, Hotpot QA, and Musique, using instruction-tuned LLMs in different scales demonstrate superior accuracy and significant computational efficiency improvements compared to the previous baselines. Furthermore, our mechanistic analysis reveals specific attention heads and multilayer perceptron (MLP) layers responsible for context attribution, providing valuable insights into the internal workings of RAG models and how they affect RAG behaviours.