Chow-Liu Ordering for Long-Context Reasoning in Chain-of-Agents

• URL: http://arxiv.org/abs/2603.09835v1
• Date: Tue, 10 Mar 2026 15:57:35 GMT
• Title: Chow-Liu Ordering for Long-Context Reasoning in Chain-of-Agents
• Abstract summary: Chain-of-Agents (CoA) handle long-context queries by decomposing inputs into chunks and processing them sequentially.<n>CoA achieves this through a latent-state factorization in which only bounded summaries of previously processed evidence are passed between agents.<n>We use the well-known Chow-Liu trees to learn a dependency structure that prioritizes strongly related chunks.
• Score: 13.497579460482399
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Sequential multi-agent reasoning frameworks such as Chain-of-Agents (CoA) handle long-context queries by decomposing inputs into chunks and processing them sequentially using LLM-based worker agents that read from and update a bounded shared memory. From a probabilistic perspective, CoA aims to approximate the conditional distribution corresponding to a model capable of jointly reasoning over the entire long context. CoA achieves this through a latent-state factorization in which only bounded summaries of previously processed evidence are passed between agents. The resulting bounded-memory approximation introduces a lossy information bottleneck, making the final evidence state inherently dependent on the order in which chunks are processed. In this work, we study the problem of chunk ordering for long-context reasoning. We use the well-known Chow-Liu trees to learn a dependency structure that prioritizes strongly related chunks. Empirically, we show that a breadth-first traversal of the resulting tree yields chunk orderings that reduce information loss across agents and consistently outperform both default document-chunk ordering and semantic score-based ordering in answer relevance and exact-match accuracy across three long-context benchmarks.

Related papers

• Query-Adaptive Semantic Chunking for Retrieval-Augmented Generation: A Dynamic Strategy with Contextual Window Expansion [0.0]
  We present Query-Adaptive Semantic Chunking (QASC), which dynamically constructs chunks by integrating queries into segmentation through three mechanisms.<n>QASC achieves an F1-score of 0.85, a relative improvement of 18-27% over fixed chunking and 8-12% over semantic and agentic alternatives.
  arXiv  Detail & Related papers  (2026-04-29T06:40:53Z)
• HCRE: LLM-based Hierarchical Classification for Cross-Document Relation Extraction with a Prediction-then-Verification Strategy [54.91468501159335]
  Cross-document relation extraction (RE) aims to identify relations between the head tail entities located in different documents.<n>We propose an inference strategy that improves reliability through multi-view verification at each level.
  arXiv  Detail & Related papers  (2026-04-09T07:55:27Z)
• TeaRAG: A Token-Efficient Agentic Retrieval-Augmented Generation Framework [62.66056331998838]
  TeaRAG is a token-efficient agentic RAG framework capable of compressing both retrieval content and reasoning steps.<n>Our reward function evaluates the knowledge sufficiency by a knowledge matching mechanism, while penalizing excessive reasoning steps.
  arXiv  Detail & Related papers  (2025-11-07T16:08:34Z)
• ToM: Leveraging Tree-oriented MapReduce for Long-Context Reasoning in Large Language Models [107.86069298500855]
  ToM is a novel Tree-oriented MapReduce framework for long-context reasoning.<n>We show that ToM significantly outperforms existing divide-and-conquer frameworks and retrieval-augmented generation methods.
  arXiv  Detail & Related papers  (2025-11-01T10:43:58Z)
• 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)
• COSMIR: Chain Orchestrated Structured Memory for Iterative Reasoning over Long Context [12.538401452822098]
  We introduce COSMIR, a chain-style framework that replaces ad hoc messages with a structured memory.<n>Agents process chunks via a fixed micro-cycle: Extract, Infer, Refine, writing all updates to the shared memory.<n>A Manager agent then Synthesizes the final answer directly from the memory.
  arXiv  Detail & Related papers  (2025-10-06T08:10:04Z)
• When Does Divide and Conquer Work for Long Context LLM? A Noise Decomposition Framework [39.66331560468973]
  We investigate the challenge of applying Large Language Models (LLMs) to long texts.<n>We propose a theoretical framework that distinguishes the failure modes of long context tasks into three categories: cross-chunk dependence (task noise), confusion that grows with context size (model noise), and the imperfect integration of partial results (aggregator noise)
  arXiv  Detail & Related papers  (2025-06-19T15:49:34Z)
• Meta-Chunking: Learning Text Segmentation and Semantic Completion via Logical Perception [10.614437503578856]
  This paper proposes the Meta-Chunking framework, which specifically enhances chunking quality.<n>We design two adaptive chunking techniques based on uncertainty, namely Perplexity Chunking and Margin Sampling Chunking.<n>We establish the global information compensation mechanism, encompassing a two-stage hierarchical summary generation process and a three-stage text chunk rewriting procedure.
  arXiv  Detail & Related papers  (2024-10-16T17:59:32Z)
• CONFLARE: CONFormal LArge language model REtrieval [0.0]
  Retrieval-augmented generation (RAG) frameworks enable large language models (LLMs) to retrieve relevant information from a knowledge base and incorporate it into the context for generating responses. RAG does not guarantee valid responses if retrieval fails to identify the necessary information as the context for response generation. We introduce a four-step framework for applying conformal prediction to quantify retrieval uncertainty in RAG frameworks.
  arXiv  Detail & Related papers  (2024-04-04T02:58:21Z)
• Walking Down the Memory Maze: Beyond Context Limit through Interactive Reading [63.93888816206071]
  We introduce MemWalker, a method that processes the long context into a tree of summary nodes. Upon receiving a query, the model navigates this tree in search of relevant information, and responds once it gathers sufficient information. We show that, beyond effective reading, MemWalker enhances explainability by highlighting the reasoning steps as it interactively reads the text; pinpointing the relevant text segments related to the query.
  arXiv  Detail & Related papers  (2023-10-08T06:18:14Z)
• Complex Event Forecasting with Prediction Suffix Trees: Extended Technical Report [70.7321040534471]
  Complex Event Recognition (CER) systems have become popular in the past two decades due to their ability to "instantly" detect patterns on real-time streams of events. There is a lack of methods for forecasting when a pattern might occur before such an occurrence is actually detected by a CER engine. We present a formal framework that attempts to address the issue of Complex Event Forecasting.
  arXiv  Detail & Related papers  (2021-09-01T09:52:31Z)

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.