ICLR 2026 Papers

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.

While Key-Value (KV) cache succeeds in reducing redundant computations in auto-regressive models, it introduces significant memory overhead, limiting its practical deployment in long-sequence scenarios. Existing KV retrieval methods attempt to mitigate this by dynamically retaining only a subset of KV entries on the GPU. However, they still suffer from notable efficiency and accuracy bottlenecks due to per-token retrieval and coarse-grained page-level KV management strategy, especially in long-output reasoning scenarios. With the emergence of large reasoning models, efficiently handling such scenarios has become increasingly important. To address this issue, we present two key observations: (1) critical KVs exhibit strong temporal locality during decoding, and (2) these KVs exhibit distinct distribution patterns across the input prompt and the generated output. Building on these observations, we propose LouisKV, an efficient KV cache retrieval framework designed for various long-sequence scenarios. Specifically, LouisKV introduces a semantic-aware retrieval strategy that leverages temporal locality to trigger retrieval only at semantic boundaries, drastically reducing computation and data transfer overhead. LouisKV also designs a decoupled, fine-grained management scheme that tailors differentiated strategies for input and output sequences to create retrieval units that better match the model's attention patterns, thereby enabling the precise identification of critical KVs. Furthermore, to boost system efficiency, LouisKV incorporates several kernel-level optimizations, including custom Triton and CUDA kernels to accelerate the KV clustering and retrieval. Evaluation results show that LouisKV achieves up to 4.7$\times$ speedup over state-of-the-art KV retrieval methods while maintaining near-lossless accuracy across diverse long-sequence tasks, including long-input short-output, short-input long-output, and long-input long-output scenarios.

Multimodal encoders have pushed the boundaries of visual document retrieval, matching textual tokens directly to image patches and achieving state-of-the-art performance on challenging benchmarks. Recent models relying on this paradigm have massively scaled the dimensionality of their query and document representations, presenting obstacles to deployment and scalability in real-world pipelines. Furthermore, purely vision-centric approaches may be constrained by the inherent modality gap still exhibited by modern vision-language models. In this work, we connect these challenges to the paradigm of hybrid retrieval, investigating whether a lightweight dense text retriever can enhance a stronger vision-centric model. Existing hybrid methods, which rely on coarse-grained fusion of ranks or scores, fail to exploit the rich interactions within each model’s representation space. To address this, we introduce Guided Query Refinement (GQR), a novel test-time optimization method that refines a primary retriever’s query embedding using guidance from a complementary retriever’s scores. Through extensive experiments on visual document retrieval benchmarks, we demonstrate that GQR allows ColPali-based models to match the performance of models with significantly larger representations, while being up to 14x faster and requiring 54x less memory. Our findings show that GQR effectively pushes the Pareto frontier for performance and efficiency in multimodal retrieval. We release our code at https://github.com/IBM/test-time-hybrid-retrieval

Post-training for reasoning in large language models has increasingly relied on verifiable rewards: deterministic checkers that provide $0$–$1$ correctness signals. While reliable, such binary feedback is brittle—many tasks admit partially correct or alternative answers that verifiers under-credit, and the resulting all-or-nothing supervision limits learning. Reward models offer richer, continuous feedback, which can serve as a complementary supervisory signal to verifiers. We introduce HERO (Hybrid Ensemble Reward Optimization), a reinforcement learning framework that integrates sparse verifier signals with dense reward model scores in a structured way. HERO employs stratified normalization to bound reward-model scores within verifier-defined groups, preserving correctness while refining quality distinctions, and variance-aware weighting to emphasize challenging prompts where dense signals matter most. Across diverse mathematical reasoning benchmarks, HERO consistently outperforms reward model-only and verifier-only baselines, with strong gains on both verifiable and hard-to-verify tasks. Our results show that hybrid reward design retains the stability of verifiers while leveraging the nuance of reward models to advance reasoning.

Retrieval-augmented generation (RAG) enhances the response quality of large language models (LLMs) when handling domain-specific tasks, yet raises significant privacy concerns. This is because both the user query and documents within the knowledge base often contain sensitive or confidential information. To address these concerns, we propose $\texttt{Pisces}$, the first practical cryptography-based RAG framework that supports dual-path retrieval, while protecting both the query and documents. Along the semantic retrieval path, we reduce computation and communication overhead by leveraging a coarse-to-fine strategy. Specifically, a novel oblivious filter is used to privately select a candidate set of documents to reduce the scale of subsequent cosine similarity computations. For the lexical retrieval path, to reduce the overhead of repeatedly invoking labeled PSI, we implement a multi-instance labeled PSI protocol to compute term frequencies for BM25 scoring in a single execution. $\texttt{Pisces}$ can also be integrated with existing privacy-preserving LLM inference frameworks to achieve end-to-end privacy. Experiments demonstrate that $\texttt{Pisces}$ achieves retrieval accuracy comparable to the plaintext baselines, within a 1.87% margin.