Retrieval Memory

As retrieval-augmented generation (RAG) becomes increasingly widespread, the role of information retrieval (IR) is shifting from retrieving information for human users to retrieving contextual knowledge for artificial intelligence (AI) systems, where relevance becomes difficult to define or annotate beforehand. To address this challenge, we propose R3, a Retrieval framework optimized for RAG through trial-and-feedback Reinforced contrastive learning. Unlike prior approaches that rely on annotated or synthetic data for supervised fine-tuning, R3 enables the retriever to dynamically explore and optimize relevance within the RAG environment. During training, the retrieved results interact with the environment to produce contrastive signals that automatically guide the retriever’s self-improvement. Extensive experiments across diverse tasks demonstrate that R3 improves RAG performance by 5.2% over the original retriever and surpasses state-of-the-art retrievers by 4.9%, while achieving comparable results to LLM-augmented retrieval and RAG systems built on post-trained or instruction-tuned LLMs. It is both efficient and practical, requiring only 4 GPUs and completing training within a single day.

Graph Foundation Models (GFMs) have demonstrated remarkable potential across graph learning tasks but face significant challenges in knowledge updating and reasoning faithfulness. To address these issues, we introduce the Retrieval-Augmented Generation (RAG) paradigm for GFMs, which leverages graph knowledge retrieval. We propose RAG4GFM, an end-to-end framework that seamlessly integrates multi-level graph indexing, task-aware retrieval, and graph fusion enhancement. RAG4GFM implements a hierarchical graph indexing architecture, enabling multi-granular graph indexing while achieving efficient logarithmic-time retrieval. The task-aware retriever implements adaptive retrieval strategies for node, edge, and graph-level tasks to surface structurally and semantically relevant evidence. The graph fusion enhancement module fuses retrieved graph features with query features and augments the topology with sparse adjacency links that preserve structural and semantic proximity, yielding a fused graph for GFM inference. Extensive experiments conducted across diverse GFM applications demonstrate that RAG4GFM significantly enhances both the efficiency of knowledge updating and reasoning faithfulness\footnote{Code: \url{https://github.com/Matrixmax/RAG4GFM}.}.

Large language models (LLMs) have been widely integrated into information retrieval to advance traditional techniques. However, effectively enabling LLMs to seek accurate knowledge in complex tasks remains a challenge due to the complexity of multi-hop queries as well as the irrelevant retrieved content. To address these limitations, we propose ExSearch, an agentic search framework, where the LLM learns to retrieve useful information as the reasoning unfolds through a self-incentivized process. At each step, the LLM decides what to retrieve (thinking), triggers an external retriever (search), and extracts fine-grained evidence (recording) to support next-step reasoning. To enable LLM with this capability, we adopts a Generalized Expectation-Maximization algorithm. In the E-step, the LLM generates multiple search trajectories and assigns an importance weight to each; the M-step trains the LLM on them with a re-weighted loss function. This creates a self-incentivized loop, where the LLM iteratively learns from its own generated data, progressively improving itself for search. We further theoretically analyze this training process, establishing convergence guarantees. Extensive experiments on four knowledge-intensive benchmarks show that ExSearchS substantially outperforms baselines, e.g., +7.8% improvement on exact match score. Motivated by these promising results, we introduce ExSearch-Zoo, an extension that extends our method to broader scenarios, to facilitate future work.

Standard Retrieval-Augmented Generation (RAG) relies on chunk-based retrieval, whereas GraphRAG advances this approach by graph-based knowledge representation. However, existing graph-based RAG approaches are constrained by binary relations, as each edge in an ordinary graph connects only two entities, limiting their ability to represent the n-ary relations (n >= 2) in real-world knowledge. In this work, we propose HyperGraphRAG, the first hypergraph-based RAG method that represents n-ary relational facts via hyperedges. HyperGraphRAG consists of a comprehensive pipeline, including knowledge hypergraph construction, retrieval, and generation. Experiments across medicine, agriculture, computer science, and law demonstrate that HyperGraphRAG outperforms both standard RAG and previous graph-based RAG methods in answer accuracy, retrieval efficiency, and generation quality.

Object-goal navigation (ObjNav) tasks an agent with navigating to the location of a specific object in an unseen environment. Embodied agents equipped with large language models (LLMs) and online constructed navigation maps can perform ObjNav in a zero-shot manner. However, existing agents heavily rely on giant LLMs on the cloud, e.g., GPT-4, while directly switching to small LLMs, e.g., LLaMA3.2-11b, suffer from significant success rate drops due to limited model capacity for understanding complex navigation maps, which prevents deploying ObjNav on local devices. At the same time, the long prompt introduced by the navigation map description will cause high planning latency on local devices. In this paper, we propose EfficientNav to enable on-device efficient LLM-based zero-shot ObjNav. To help the smaller LLMs better understand the environment, we propose semantics-aware memory retrieval to prune redundant information in navigation maps. To reduce planning latency, we propose discrete memory caching and attention-based memory clustering to efficiently save and re-use the KV cache. Extensive experimental results demonstrate that EfficientNav achieves 11.1\% improvement in success rate on HM3D benchmark over GPT-4-based baselines, and demonstrates 6.7$\times$ real-time latency reduction and 4.7$\times$ end-to-end latency reduction over GPT-4 planner. Our code is available on https://github.com/PKU-SEC-Lab/EfficientNav.

Traffic flow data are of great value in smart city applications. However, limited by data collection costs and privacy sensitivity, it is rather difficult to obtain large-scale traffic flow data. Therefore, various data generation methods have been proposed in the literature. Nevertheless, these methods often require data from a specific city for training and are difficult to directly apply to new cities lacking data. To address this problem, this paper proposes a retrieval-augmented diffusion generation model with representation alignment. We use data from multiple source cities for training, extract consistent representations across multiple cities, and leverage retrieval-augmented generation (RAG) technology to incorporate historical data from source cities under similar conditions into the condition, aiming to improve the accuracy of data generation in the target city. Experiments on four real-world datasets demonstrate that, compared with existing deep learning methods, our method achieves better cross-city transfer performance.

We describe KVLink, an approach for efficient key-value (KV) cache reuse in large language models (LLMs). In many LLM applications, different inputs can share overlapping context, such as the same retrieved document appearing in multiple queries. However, the LLMs still need to encode the entire context for each query, leading to redundant computation. In this paper, we investigate a new strategy to eliminate such inefficiency, where the KV cache of each document is precomputed independently. During inference, the KV caches of retrieved documents are concatenated, allowing the model to reuse cached representations instead of recomputing them. To mitigate the performance degradation when using KV caches computed independently for each document, KVLink introduces two key techniques: adjusting positional embeddings of the KV cache at inference to match the global position after concatenation, and using trainable special tokens to restore self-attention across independently encoded documents. Experiments across 7 datasets demonstrate that KVLink improves question answering accuracy by an average of 4% over state-of-the-art methods. Furthermore, by leveraging precomputed KV caches, our approach reduces time-to-first-token by up to 96% compared to standard LLM inference, making it a scalable and efficient solution for context reuse. Additionally, KVLink can be combined with KV cache compression to further save cache loading and storage overhead while outperforming the baselines.

Over the last decades, developing more powerful neural architectures and simultaneously designing optimization algorithms to effectively train them have been the core of research efforts to enhance the capability of machine learning models. Despite the recent progresses, particularly in developing Language Models (LMs), there are fundamental challenges and unanswered questions about how such models can continually learn/memorize, self-improved, and find ''effective solutions,''. In this paper, we present a new learning paradigm, called Nested Learning (NL), that coherently represents a model with a set of nested, multi-level, and/or parallel optimization problems, each of which with its own ''context flow''. NL reveals that existing deep learning methods learns from data through \emph{compressing} their own context flow, and explain how in-context learning emerges in large models. NL suggests a path (a new dimension to deep learning) to design more expressive learning algorithms with more ''levels'', resulting in higher-order in-context learning abilities. In addition to its neuroscientifically plausible and mathematically white-box nature, we advocate for its importance by presenting three core contributions: (1) Deep Optimizers: Based on NL, we show that well-known gradient-based optimizers (e.g., Adam, SGD with Momentum, etc.) are in fact associative memory modules that aim to compress the gradients with gradient descent. Building on this insight, we present a set of more expressive optimizers with deep memory and/or more powerful learning rules; (2) Self-Modifying Titans: Taking advantage of NL's insights on learning algorithms, we present a novel sequence model that learns how to modify itself by learning its own update algorithm; and (3) Continuum Memory System: We present a new formulation for memory system that generalizes the traditional viewpoint of ``long-term/short-term memory''. Combining our self-modifying sequence model with the continuum memory system, we present a learning module, called Hope, showing promising results in language modeling, continual learning, and long-context reasoning tasks.

With the increasing adoption of Retrieval-Augmented Generation (RAG) systems for knowledge-intensive tasks, ensuring the adequacy of retrieved documents has become critically important for generation quality. Traditional reranking approaches face three significant challenges: substantial computational overhead that scales with document length, dependency on plain text that limits application in sensitive scenarios, and insufficient assessment of document value beyond simple relevance metrics. We propose EAReranker, an efficient embedding-based adequacy assessment framework that evaluates document utility for RAG systems without requiring access to original text content. The framework quantifies document adequacy through a comprehensive scoring methodology considering verifiability, coverage, completeness and structural aspects, providing interpretable adequacy classifications for downstream applications. EAReranker employs a Decoder-Only Transformer architecture that introduces embedding dimension expansion method and bin-aware weighted loss, designed specifically to predict adequacy directly from embedding vectors. Our comprehensive evaluation across four public benchmarks demonstrates that EAReranker achieves competitive performance with state-of-the-art plaintext rerankers while maintaining constant memory usage ($\sim$550MB) regardless of input length and processing 2-3x faster than traditional approaches. The semantic bin adequacy prediction accuracy of 92.85\% LACC@10 and 86.12\% LACC@25 demonstrates its capability to effectively filter out inadequate documents that could potentially mislead or adversely impact RAG system performance, thereby ensuring only high-utility information serves as generation context. These results establish EAReranker as an efficient and practical solution for enhancing RAG system performance through improved context selection while addressing the computational and privacy challenges of existing methods.

Organisms constantly pivot between tasks such as evading predators, foraging, traversing rugged terrain, and socializing, often within milliseconds. Remarkably, they preserve knowledge of once-learned environments sans catastrophic forgetting, a phenomenon neuroscientists hypothesize, is due to a singular neural circuitry dynamically overlayed by neuromodulatory agents such as dopamine and acetylcholine. In parallel, deep learning research addresses analogous challenges via domain generalization ($\textbf{DG}$) and continual learning ($\textbf{CL}$), yet these methods remain siloed, despite the brain’s ability to perform them seamlessly. In particular, prior work has not explored architectures involving associative memories ($\textbf{AM}$s), which are an integral part of biological systems, to jointly address these tasks. We propose Memory-Integrated Reconfigurable Adapters ($\textbf{MIRA}$), a unified framework that integrates Hopfield-style associative memory modules atop a shared backbone. These memory modules store adapter-weight updates as values and retrieve them via learned keys. Associative memory keys are learned post-hoc to index and retrieve an affine combination of stored adapter updates for any given task or domain on a per-sample basis. By varying only the task-specific objectives, we demonstrate that $\textbf{MIRA}$ seamlessly accommodates domain shifts and sequential task exposures under one roof. Empirical evaluations on standard benchmarks confirm that our $\textbf{AM}$-augmented architecture significantly enhances adaptability and retention: in $\textbf{DG}$, $\textbf{MIRA}$ achieves SoTA out-of-distribution accuracy, and in incremental learning settings, it outperforms architectures explicitly designed to handle catastrophic forgetting using generic $\textbf{CL}$ algorithms. Extensive ablation studies validate the necessity of both associative memory storage and post-hoc key learning for robust interpolated retrieval of adapters. By unifying adapter-based modulation with biologically inspired associative memory, $\textbf{MIRA}$ delivers rapid task switching and enduring knowledge retention in a single extensible architecture, charting a path toward more versatile and memory-augmented AI systems.

The dynamic nature of real-world information demands efficient knowledge editing in multimodal large language models (MLLMs) to ensure continuous knowledge updates. However, existing methods often struggle with precise matching in large-scale knowledge retrieval and lack multi-level guidance for coordinated editing, leading to less reliable outcomes. To tackle these challenges, we propose CARML, a novel retrieval-augmented editing framework that integrates conflict-aware dynamic retrieval with multi-level implicit and explicit guidance for reliable lifelong multimodal editing. Specifically, CARML introduces intra-modal uncertainty and inter-modal conflict quantification to dynamically integrate multi-channel retrieval results, so as to pinpoint the most relevant knowledge to the incoming edit samples. Afterwards, an edit scope classifier discerns whether the edit sample semantically aligns with the edit scope of the retrieved knowledge. If deemed in-scope, CARML refines the retrieved knowledge into information-rich continuous prompt prefixes, serving as the implicit knowledge guide. These prefixes not only include static knowledge prompt that capture key textual semantics but also incorporate token-level, context-aware dynamic prompt to explore fine-grained cross-modal associations between the edit sample and retrieved knowledge. To further enhance reliability, CARML incorporates a "hard correction" mechanism, leveraging explicit label knowledge to adjust the model’s output logits. Extensive experiments across multiple MLLMs and datasets indicate the superior performance of CARML in lifelong multimodal editing scenarios.

This paper introduces an approach for training o1-like RAG models that retrieve and reason over relevant information step by step before generating the final answer. Conventional RAG methods usually perform a single retrieval step before the generation process, which limits their effectiveness in addressing complex queries due to imperfect retrieval results. In contrast, our proposed method, CoRAG (Chain-of-Retrieval Augmented Generation), allows the model to dynamically reformulate the query based on the evolving state. To train CoRAG effectively, we utilize rejection sampling to automatically generate intermediate retrieval chains, thereby augmenting existing RAG datasets that only provide the correct final answer. At test time, we propose various decoding strategies to scale the model's test-time compute by controlling the length and number of sampled retrieval chains. Experimental results across multiple benchmarks validate the efficacy of CoRAG, particularly in multi-hop question answering tasks, where we observe more than $10$ points improvement in EM score compared to strong baselines. On the KILT benchmark, CoRAG establishes a new state-of-the-art performance across a diverse range of knowledge-intensive tasks. Furthermore, we offer comprehensive analyses to understand the scaling behavior of CoRAG, laying the groundwork for future research aimed at developing factual and grounded foundation models.

Protein language models (PLMs) learn probability distributions over natural protein sequences. By learning from hundreds of millions of natural protein sequences, protein understanding and design capabilities emerge. Recent works have shown that scaling these models improves structure prediction, but does not seem to improve mutation understanding and representation quality for protein function prediction. We introduce PoET-2, a multimodal, retrieval-augmented protein foundation model that incorporates in-context learning of family-specific evolutionary constraints with optional structure conditioning to learn generative distributions over protein sequences. PoET-2 uses a hierarchical transformer encoder that is equivariant to sequence context ordering and a dual decoder architecture with both causal and masked language modeling objectives, allowing PoET-2 to operate in both fully generative and bidirectional representation learning modes. PoET-2 achieves state-of-the-art performance on zero-shot variant effect prediction, excelling at scoring variants with multiple mutations and challenging indel mutations. In supervised settings, PoET-2 embeddings outperform previous methods for learning sequence-function relationships, especially with small datasets. This work highlights the benefits of combining retrieval augmentation with multimodal, family-centric modeling for advancing protein foundation models.

We propose a novel energy function for Dense Associative Memory (DenseAM) networks, the log-sum-ReLU (LSR), inspired by optimal kernel density estimation. Unlike the common log-sum-exponential (LSE) function, LSR is based on the Epanechnikov kernel and enables exact memory retrieval with exponential capacity without requiring exponential separation functions. Uniquely, it introduces abundant additional emergent local minima while preserving perfect pattern recovery --- a characteristic previously unseen in DenseAM literature. Empirical results show that LSR energy has significantly more local minima (memories) that have comparable log-likelihood to LSE-based models. Analysis of LSR's emergent memories on image datasets reveals a degree of creativity and novelty, hinting at this method's potential for both large-scale memory storage and generative tasks.

Language models (LMs) and their extension, vision-language models (VLMs), have achieved remarkable performance across various tasks. However, they still struggle with complex reasoning tasks that require multimodal or multilingual real world knowledge. To support such capabilities, an external memory system that can efficiently provide relevant multimodal information is essential. Existing approaches generally concatenate image and text tokens into a long sequence as memory, which, however, may drastically increase context length and even degrade performance. In contrast, we propose using continuous memory-a compact set of dense embeddings-to more effectively and efficiently represent multimodal and multilingual knowledge. Our key insight is that a VLM can serve as its own continuous memory encoder. We empirically show that this design improves performance on complex multimodal reasoning tasks. Building on this, we introduce a data-efficient and parameter-efficient method to fine-tune the VLM into a memory encoder, requiring only 1.2\% of the model’s parameters and a small corpus of 15.6K self-synthesized samples. Our approach CoMEM utilizes VLM's original capabilities to encode arbitrary multimodal and multilingual knowledge into just 8 continuous embeddings. Since the inference-time VLM remains frozen, our memory module is plug-and-play and can be flexibly integrated as needed. Extensive experiments across eight multimodal reasoning benchmarks demonstrate the effectiveness of our approach. Code and data is publicly released here https://github.com/WenyiWU0111/CoMEM.

Spatio-Temporal Graph Neural Networks (STGNNs) have emerged as a powerful tool for modeling dynamic graph-structured data across diverse domains. However, they often fail to generalize in Spatio-Temporal Out-of-Distribution (STOOD) scenarios, where both temporal dynamics and spatial structures evolve beyond the training distribution. To address this problem, we propose an innovative Spatio-Temporal Retrieval-Augmented Pattern Learning framework, STRAP, which enhances model generalization by integrating retrieval-augmented learning into the STGNN continue learning pipeline. The core of STRAP is a compact and expressive pattern library that stores representative spatio-temporal patterns enriched with historical, structural, and semantic information, which is obtained and optimized during the training phase. During inference, STRAP retrieves relevant patterns from this library based on similarity to the current input and injects them into the model via a plug-and-play prompting mechanism. This not only strengthens spatio-temporal representations but also mitigates catastrophic forgetting. Moreover, STRAP introduces a knowledge-balancing objective to harmonize new information with retrieved knowledge. Extensive experiments across multiple real-world streaming graph datasets show that STRAP consistently outperforms state-of-the-art STGNN baselines on STOOD tasks, demonstrating its robustness, adaptability, and strong generalization capability without task-specific fine-tuning.

Recently, Large Language Models (LLMs) have been increasingly used to support various decision-making tasks, assisting humans in making informed decisions. However, when LLMs confidently provide incorrect information, it can lead humans to make suboptimal decisions. To prevent LLMs from generating incorrect information on topics they are unsure of and to improve the accuracy of generated content, prior works have proposed Retrieval Augmented Generation (RAG), where external documents are referenced to generate responses. However, previous RAG methods focus only on retrieving documents most relevant to the input query, without specifically aiming to ensure that the human user's decisions are well-calibrated. To address this limitation, we propose a novel retrieval method called Calibrated Retrieval-Augmented Generation (CalibRAG), which ensures that decisions informed by RAG are well-calibrated. Then we empirically validate that CalibRAG improves calibration performance as well as accuracy, compared to other baselines across various datasets.

Existing large video-language models (LVLMs) struggle to comprehend long videos correctly due to limited context. To address this problem, fine-tuning long-context LVLMs and employing GPT-based agents have emerged as promising solutions. However, fine-tuning LVLMs would require extensive high-quality data and substantial GPU resources, while GPT-based agents would rely on proprietary models (e.g., GPT-4o). In this paper, we propose Video Retrieval-Augmented Generation (Video-RAG), a training-free and cost-effective pipeline that employs visually-aligned auxiliary texts to help facilitate cross-modality alignment while providing additional information beyond the visual content. Specifically, we leverage open-source external tools to extract visually-aligned information from pure video data (e.g., audio, optical character, and object detection), and incorporate the extracted information into an existing LVLM as auxiliary texts, alongside video frames and queries, in a plug-and-play manner. Our Video-RAG offers several key advantages: (i) lightweight with low computing overhead due to single-turn retrieval; (ii) easy implementation and compatibility with any LVLM; and (iii) significant, consistent performance gains across long video understanding benchmarks, including Video-MME, MLVU, and LongVideoBench. Notably, our model demonstrates superior performance over proprietary models like Gemini-1.5-Pro and GPT-4o when utilized with a 72B model.

We develop hybrid memory architectures for general-purpose sequence processing neural networks, that combine key-value memory using softmax attention (KV-memory) with fast weight memory through dynamic synaptic modulation (FW-memory)---the core principles of quadratic and linear transformers, respectively. These two memory systems have complementary but individually limited properties: KV-memory offers precise retrieval but is constrained by quadratic complexity in sequence length, while FW-memory supports arbitrarily long sequences and enables more expressive computation but sacrifices precise recall. We propose and compare three methods to blend these two systems into a single memory system, differing in how and when input information is delivered to each system, to leverage the strengths of both. We conduct experiments on general language modeling and retrieval tasks by training 340M- and 1.3B-parameter models from scratch, as well as on synthetic algorithmic tasks designed to precisely illustrate the benefits of certain hybrid methods over others. We also evaluate our hybrid memory systems on reinforcement learning in partially observable environments. Overall, we demonstrate how a well-designed hybrid can overcome the limitations of its individual components, offering new insights into the design principle of neural memory systems.

Retrieval-augmented generation (RAG) systems combine large language models (LLMs) with external knowledge retrieval, making them highly effective for knowledge-intensive tasks. A crucial but often under-explored component of these systems is the reranker, which refines retrieved documents to enhance generation quality and explainability. The challenge of selecting the optimal number of documents (k) remains unsolved: too few may omit critical information, while too many introduce noise and inefficiencies. Although recent studies have explored LLM-based rerankers, they primarily leverage internal model knowledge and overlook the rich supervisory signals that LLMs can provide, such as using response quality as feedback for optimizing reranking decisions. In this paper, we propose DynamicRAG, a novel RAG framework where the reranker dynamically adjusts both the order and number of retrieved documents based on the query. We model the reranker as an agent optimized through reinforcement learning (RL), using rewards derived from LLM output quality. Across seven knowledge-intensive datasets, DynamicRAG demonstrates superior performance, achieving state-of-the-art results.