RecaLLM: Addressing the Lost-in-Thought Phenomenon with Explicit In-Context Retrieval

• URL: http://arxiv.org/abs/2604.09494v1
• Date: Fri, 10 Apr 2026 17:04:32 GMT
• Title: RecaLLM: Addressing the Lost-in-Thought Phenomenon with Explicit In-Context Retrieval
• Abstract summary: RecaLLM is a set of reasoning language models post-trained to make effective use of long-context information.<n>We introduce a negligible-overhead constrained decoding mechanism that enables verbatim copying of evidence spans.<n>We observe consistent gains at context windows of up to 128K tokens using training samples of at most 10K tokens, far shorter than those used by existing long-context approaches.
• Score: 0.8594140167290097
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We propose RecaLLM, a set of reasoning language models post-trained to make effective use of long-context information. In-context retrieval, which identifies relevant evidence from context, and reasoning are deeply intertwined: retrieval supports reasoning, while reasoning often determines what must be retrieved. However, their interaction remains largely underexplored. In preliminary experiments on several open-source LLMs, we observe that in-context retrieval performance substantially degrades even after a short reasoning span, revealing a key bottleneck for test-time scaling that we refer to as lost-in-thought: reasoning steps that improve performance also make subsequent in-context retrieval more challenging. To address this limitation, RecaLLM interleaves reasoning with explicit in-context retrieval, alternating between reasoning and retrieving context information needed to solve intermediate subproblems. We introduce a negligible-overhead constrained decoding mechanism that enables verbatim copying of evidence spans, improving the grounding of subsequent generation. Trained on diverse lexical and semantic retrieval tasks, RecaLLM achieves strong performance on two long-context benchmarks, RULER and HELMET, significantly outperforming baselines. Notably, we observe consistent gains at context windows of up to 128K tokens using training samples of at most 10K tokens, far shorter than those used by existing long-context approaches, highlighting a promising path toward improving long-context performance without expensive long-context training data.

Related papers

• ReContext: Recursive Evidence Replay as LLM Harness for Long-Context Reasoning [78.94047086588078]
  We propose Recursive Evidence as LLM Harness for Long-Context Reasoning.<n>It is a training-free inference method for improving long-context reasoning.<n> Experiments on eight long-context datasets with 128K context length show it consistently improves evidence utilization.
  arXiv  Detail & Related papers  (2026-07-02T17:59:26Z)
• Reasoning-Augmented Representations for Multimodal Retrieval [27.4146940988752]
  Universal Multimodal Retrieval (UMR) seeks any-to-any search across text and vision.<n>We argue this brittleness is often data-specified: when images carry "silent" evidence and queries leave key semantics implicit, a single embedding pass must both reason and compress.<n>We propose a data-centric framework that decouples these roles by externalizing reasoning before retrieval.
  arXiv  Detail & Related papers  (2026-02-06T19:01:54Z)
• LongR: Unleashing Long-Context Reasoning via Reinforcement Learning with Dense Utility Rewards [57.993003392037174]
  LongR is a framework that enhances long-context performance by integrating a dynamic "Think-and-Read" mechanism.<n>LongR consistently enhances performance across diverse RL algorithms.
  arXiv  Detail & Related papers  (2026-02-05T15:26:47Z)
• Improving Context Fidelity via Native Retrieval-Augmented Reasoning [35.50952279309109]
  Large language models (LLMs) often struggle with context fidelity, producing inconsistent answers when responding to questions based on provided information.<n>We propose CARE, a novel native retrieval-augmented reasoning framework that teaches LLMs to explicitly integrate in-context evidence within their reasoning process with the model's own retrieval capabilities.<n>Our method requires limited labeled evidence data while significantly enhancing both retrieval accuracy and answer generation performance through strategically retrieved in-context tokens in the reasoning chain.
  arXiv  Detail & Related papers  (2025-09-17T04:28:07Z)
• ELITE: Embedding-Less retrieval with Iterative Text Exploration [5.8851517822935335]
  Large Language Models (LLMs) have achieved impressive progress in natural language processing.<n>Their limited ability to retain long-term context constrains performance on document-level or multi-turn tasks.
  arXiv  Detail & Related papers  (2025-05-17T08:48:43Z)
• Reducing Distraction in Long-Context Language Models by Focused Learning [6.803882766744194]
  We propose a novel training method that enhances Large Language Models' ability to discern relevant information. During fine-tuning with long contexts, we employ a retriever to extract the most relevant segments. We then introduce an auxiliary contrastive learning objective to explicitly ensure that outputs from the original context and the retrieved sub-context are closely aligned.
  arXiv  Detail & Related papers  (2024-11-08T19:27:42Z)
• Rethinking Visual Dependency in Long-Context Reasoning for Large Vision-Language Models [62.698520962933195]
  Large Vision-Language Models (LVLMs) excel in cross-model tasks but experience performance declines in long-context reasoning.<n>We propose a novel training-free context pruning method that selectively removes less critical textual information.
  arXiv  Detail & Related papers  (2024-10-25T17:59:09Z)
• A Controlled Study on Long Context Extension and Generalization in LLMs [85.4758128256142]
  Broad textual understanding and in-context learning require language models that utilize full document contexts. Due to the implementation challenges associated with directly training long-context models, many methods have been proposed for extending models to handle long contexts. We implement a controlled protocol for extension methods with a standardized evaluation, utilizing consistent base models and extension data.
  arXiv  Detail & Related papers  (2024-09-18T17:53:17Z)
• NeedleBench: Evaluating LLM Retrieval and Reasoning Across Varying Information Densities [51.07379913779232]
  NeedleBench is a framework for assessing retrieval and reasoning performance in long-context tasks.<n>It embeds key data points at varying depths to rigorously test model capabilities.<n>Our experiments reveal that reasoning models like Deep-R1 and OpenAI's o3 struggle with continuous retrieval and reasoning in information-dense scenarios.
  arXiv  Detail & Related papers  (2024-07-16T17:59:06Z)
• Phrase Retrieval Learns Passage Retrieval, Too [77.57208968326422]
  We study whether phrase retrieval can serve as the basis for coarse-level retrieval including passages and documents. We show that a dense phrase-retrieval system, without any retraining, already achieves better passage retrieval accuracy. We also show that phrase filtering and vector quantization can reduce the size of our index by 4-10x.
  arXiv  Detail & Related papers  (2021-09-16T17:42:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.