arXiv:2610.08463v1 Announce Type: cross Abstract: Long-context inference and Retrieval-Augmented Generation (RAG) handle evidence selection at vastly different scales, from a single long prompt to an...
arXiv:2606.16661v2 Announce Type: replace-cross Abstract: Fixed-length chunking in Retrieval-Augmented Generation (RAG) often leads to boundary fragmentation, where critical evidence is split across...
The paper introduces STAIR, a retrieval system that uses a document’s Table of Contents to guide large language models in accessing global structure, thereby reducing hallucinations in Retrieval Augmented Generation. Experiments with a fine‑tuned Differentiable Search Index show that ToC‑based retrieval yields a low hallucination rate (<0.05%) and improves Recall@1 to 82.6% on the newly released SearchTome benchmark, outperforming baselines like BM25, DPR, and Mistral. The authors also release SearchTome, a diverse dataset of 18 books across six domains, to encourage further research in ToC‑based retrieval.
arXiv:2607. 02509v1 Announce Type: new Abstract: Understanding and reasoning over long contexts has become a key requirement for deploying large language models (LLMs) in realistic applications.
Understanding and reasoning over long contexts has become a key requirement for deploying large language models (LLMs) in realistic applications. Although recent LLMs support increasingly long context windows, they often fail to use relevant evidence that is already present in the input, revealing a gap between context access and effective context utilization.
The paper introduces REVA, a method for compressing retrieval-augmented generation (RAG) prompts by aggregating historical query–document–model interactions into reusable evidence views. REVA mines attention traces from the target generator, maps token-level attention to readable words, aggregates importance across repeated document accesses, and produces budget‑specific plain‑text views that maintain document order and the standard RAG interface. Experiments on four benchmarks with modern LLMs show that REVA improves generation quality by 1.0–5.8 points over existing compressors while reducing compression overhead by 5.3 to 15.6 times and adding less than 40 ms of latency.
arXiv:2607. 02980v1 Announce Type: cross Abstract: Scaling modern large language models (LLMs) to long contexts is limited by the quadratic computation cost, and poor length extrapolation of dense attention.
LLM agents increasingly answer questions over dynamic raw-document collections, where files may change before preprocessing, and relevant evidence (spans, sections, pages, or tables) is query-dependent. Existing retrieval-augmented approaches pre-materialize evidence via fixed chunking, embeddings, or persistent indexes: effective for lookup, yet costly, stale-prone, and committed to a granularity before the query is known.
arXiv:2608.29899v1 Announce Type: cross Abstract: Dense retrieval over long documents is expensive. Token-level encoders scale quadratically in sequence length, and most long-context embedding models...
The paper introduces a family of adapters that enhance language model reasoning by adding selective state-space control at token and context levels. The token-level MaLoRA makes the adapter’s scaling factor dynamic and recurrent, improving over static low‑rank adaptation. The context-level MaRA tracks cross‑segment reasoning state and retrieves relevant segments, outperforming an eight‑billion‑parameter dense retriever and boosting reasoning accuracy by an average of +6.4 F1 over LoRA.
JustMem is a new memory system for long‑term conversational AI that stores conversation history as compact atomic memories and adapts its access strategy to each query. It introduces two dimensions of memory access—discovery breadth and reading fidelity—implemented through LOOKUP for local evidence, COMPOSE for distributed evidence, and REPLAY for fidelity‑sensitive evidence. Experiments on LoCoMo and LongMemEval‑S show that JustMem outperforms competing memory systems in accuracy and recall while using fewer generative‑model tokens for memory construction and inference.
arXiv:2603. 26667v2 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) turns external documents into evidence for large language models.