Chained Recursive Language Models for Multi-Iteration Reasoning

• URL: http://arxiv.org/abs/2608.05124v1
• Date: Wed, 05 Aug 2026 17:50:08 GMT
• Title: Chained Recursive Language Models for Multi-Iteration Reasoning
• Abstract summary: Chained Recursive Language Models (Chained RLM) is an inference-time architecture.<n>Each root receives the original problem and context, but does not inherit the full conversational history.<n>In each staged computation, intermediate artifacts can be inspected, corrected, and extended by a later fresh inference by the same model.
• Score: 46.765013720309064
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Long context reasoning in large language models (LLMs) is usually constrained by the fact that a single inference trajectory has to simultaneously explore the context, store intermediate state, verify evidence, and produce the final answer. This becomes particularly difficult in tasks that require extraction, counting, ordering, or multi-hop reasoning, where an early mistake can propagate until the final response. In this work, we propose Chained Recursive Language Models (Chained RLM), an inference-time architecture, in which the same underlying model is called repeatedly as a sequence of fresh reasoning roots. Each root receives the original problem and context, but does not inherit the full conversational history. Instead, it receives a compact plain-text summary, a plain-text blackboard, and some durable task-specific artifacts written by predecessor roots. The motivation is to manage the context by chopping into partial tasks rather than one large inference response; in each staged computation, intermediate artifacts can be inspected, corrected, and extended by a later fresh inference by the same model. We describe the system model, handoff mechanism, artifact workspace, and evaluation protocol for this system. We study when fresh-context artifact continuation gives a measurable gain in accuracy over direct LLM answering even with recursive tool-calling.

Related papers

• RepoReasoner: Evaluating Repository-Level Code Reasoning Ability of Long-Context Language Models [54.53236295237077]
  We introduce RepoReasoner, a benchmark for evaluating repository-level code reasoning.<n> Output Prediction measures fine-grained, stateful execution reasoning across files.<n>Call Chain Prediction evaluates high-level architectural dependency understanding under noisy context.
  arXiv  Detail & Related papers  (2026-07-28T17:12:41Z)
• 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)
• Chain-of-thought Reviewing and Correction for Time Series Question Answering [22.889720488678076]
  We propose T3LLM, which performs multi-step reasoning with an explicit correction mechanism for time series question answering.<n>Within this framework, the worker generates step-wise chains of thought (CoT) under structured prompts, while the reviewer inspects the reasoning, identifies erroneous steps, and provides corrective comments.<n>Experiments on multiple real-world TSQA benchmarks demonstrate that T3LLM achieves state-of-the-art performance over strong LLM-based baselines.
  arXiv  Detail & Related papers  (2025-12-27T15:54:18Z)
• Decomposition-Enhanced Training for Post-Hoc Attributions In Language Models [64.49342399229529]
  We argue that post-hoc attribution can be reframed as a reasoning problem, where answers are decomposed into constituent units, each tied to specific context.<n>We introduce DecompTune, a post-training method that teaches models to produce answer decompositions as intermediate reasoning steps.<n>Across extensive experiments and ablations, DecompTune substantially improves attribution quality, outperforming prior methods and matching or exceeding state-of-the-art frontier models.
  arXiv  Detail & Related papers  (2025-10-29T17:58:59Z)
• SQuARE: Sequential Question Answering Reasoning Engine for Enhanced Chain-of-Thought in Large Language Models [4.328173053224842]
  This paper introduces SQuARE, a novel prompting technique designed to improve reasoning through a self-interrogation paradigm.<n>Building upon CoT frameworks, SQuARE prompts models to generate and resolve multiple auxiliary questions before tackling the main query.<n>Our evaluations, conducted with Llama 3 and GPT-4o models across multiple question-answering datasets, demonstrate that SQuARE significantly surpasses traditional CoT prompts and existing rephrase-and-respond methods.
  arXiv  Detail & Related papers  (2025-02-13T15:07:20Z)
• Larger Language Models Don't Care How You Think: Why Chain-of-Thought Prompting Fails in Subjective Tasks [25.562937159039038]
  In-Context Learning (ICL) in Large Language Models (LLM) has emerged as the dominant technique for performing natural language tasks. We show that ICL relies mostly on the retrieval of task priors and less so on "learning" to perform tasks. We find that, surprisingly, Chain-of-Thought (CoT) indeed suffers from the same posterior collapse as ICL for larger language models.
  arXiv  Detail & Related papers  (2024-09-10T03:06:17Z)
• Large Language Model Prompt Chaining for Long Legal Document Classification [2.3148470932285665]
  Chaining is a strategy used to decompose complex tasks into smaller, manageable components. We demonstrate that through prompt chaining, we can not only enhance the performance over zero-shot, but also surpass the micro-F1 score achieved by larger models.
  arXiv  Detail & Related papers  (2023-08-08T08:57:01Z)
• Retrieval-Augmented Generative Question Answering for Event Argument Extraction [66.24622127143044]
  We propose a retrieval-augmented generative QA model (R-GQA) for event argument extraction. It retrieves the most similar QA pair and augments it as prompt to the current example's context, then decodes the arguments as answers. Our approach outperforms substantially prior methods across various settings.
  arXiv  Detail & Related papers  (2022-11-14T02:00:32Z)
• Text Modular Networks: Learning to Decompose Tasks in the Language of Existing Models [61.480085460269514]
  We propose a framework for building interpretable systems that learn to solve complex tasks by decomposing them into simpler ones solvable by existing models. We use this framework to build ModularQA, a system that can answer multi-hop reasoning questions by decomposing them into sub-questions answerable by a neural factoid single-span QA model and a symbolic calculator.
  arXiv  Detail & Related papers  (2020-09-01T23:45:42Z)

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.