COSMIR: Chain Orchestrated Structured Memory for Iterative Reasoning over Long Context

• URL: http://arxiv.org/abs/2510.04568v1
• Date: Mon, 06 Oct 2025 08:10:04 GMT
• Title: COSMIR: Chain Orchestrated Structured Memory for Iterative Reasoning over Long Context
• Abstract summary: 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.
• Score: 12.538401452822098
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reasoning over very long inputs remains difficult for large language models (LLMs). Common workarounds either shrink the input via retrieval (risking missed evidence), enlarge the context window (straining selectivity), or stage multiple agents to read in pieces. In staged pipelines (e.g., Chain of Agents, CoA), free-form summaries passed between agents can discard crucial details and amplify early mistakes. We introduce COSMIR (Chain Orchestrated Structured Memory for Iterative Reasoning), a chain-style framework that replaces ad hoc messages with a structured memory. A Planner agent first turns a user query into concrete, checkable sub-questions. worker agents process chunks via a fixed micro-cycle: Extract, Infer, Refine, writing all updates to the shared memory. A Manager agent then Synthesizes the final answer directly from the memory. This preserves step-wise read-then-reason benefits while changing both the communication medium (structured memory) and the worker procedure (fixed micro-cycle), yielding higher faithfulness, better long-range aggregation, and auditability. On long-context QA from the HELMET suite, COSMIR reduces propagation-stage information loss and improves accuracy over a CoA baseline.

Related papers

• CABLE: Extending the Reach of Memory Retrieval via Complementary Antecedent-Based Linking and Expansion [21.692254412768936]
  Link construction should instead prioritize a sparse set of retriever-complementary associations.<n>We present CABLE, a plug-in augmentation that constructs links to extend the host retriever's direct semantic reach.<n>CABLE yields higher mean LLM-judge scores in every evaluated system-level setting.
  arXiv  Detail & Related papers  (2026-08-18T15:40:29Z)
• Zero-Mem: Zero-Token Memory Operations for LLM Agents [17.228305588778]
  Zero-Mem preserves original interaction traces as its source of record.<n>Zero-Mem achieves competitive performance across long-memory and long-context question-answering benchmarks.
  arXiv  Detail & Related papers  (2026-07-31T13:01:06Z)
• PACMS: Submodular Context Selection as a Pluggable Engine for LLM Agents [0.9134244356393664]
  LLM agents operate over a context window that fills from several directions simultaneously.<n>The prevailing mechanism is recency truncation, sometimes paired with periodic summarization.<n>Retrieval augmented generation fetches external documents into the prompt but does not arbitrate the agent's emphalready-present pooled context.
  arXiv  Detail & Related papers  (2026-06-18T10:22:57Z)
• SAM: State-Adaptive Memory for Long-Horizon Reasoning Agent [51.274445160155864]
  Long-horizon agentic reasoning requires large language models to act over long interaction histories containing thoughts, tool calls, observations, and partial conclusions.<n>Existing approaches address this difficulty by truncating the interaction history, compressing it into shorter surrogates, or retrieving selected parts of it for reuse.<n>We propose State-Adaptive Memory, a standalone framework that consolidates ongoing interaction into compact memory cues while preserving raw trajectory pages for intent-driven recall.
  arXiv  Detail & Related papers  (2026-05-23T08:37:16Z)
• GenericAgent: A Token-Efficient Self-Evolving LLM Agent via Contextual Information Density Maximization (V1.0) [56.81743709880371]
  Long-horizon large language model (LLM) agents are fundamentally limited by context.<n>We argue that long-horizon performance is determined not by context length, but by how much decision-relevant information is maintained within a finite context budget.<n>We present GenericAgent (GA), a general-purpose, self-evolving LLM agent system built around a single principle: information density and context.
  arXiv  Detail & Related papers  (2026-04-18T17:59:15Z)
• Chow-Liu Ordering for Long-Context Reasoning in Chain-of-Agents [13.497579460482399]
  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.
  arXiv  Detail & Related papers  (2026-03-10T15:57:35Z)
• Beyond RAG for Agent Memory: Retrieval by Decoupling and Aggregation [22.803751188961865]
  We argue retrieval should move beyond similarity matching and instead operate over latent components.<n>We propose xMemory, which builds a hierarchy of intact units and maintains a searchable high-level node organisation.
  arXiv  Detail & Related papers  (2026-02-02T12:04:58Z)
• AMA: Adaptive Memory via Multi-Agent Collaboration [54.490349689939166]
  We propose Adaptive Memory via Multi-Agent Collaboration (AMA), a novel framework that leverages coordinated agents to manage memory across multiple granularities.<n>AMA significantly outperforms state-of-the-art baselines while reducing token consumption by approximately 80% compared to full-context methods.
  arXiv  Detail & Related papers  (2026-01-28T08:09:49Z)
• LSTM-MAS: A Long Short-Term Memory Inspired Multi-Agent System for Long-Context Understanding [24.027208865014064]
  Long language models (LLMs) are difficult to process because of the accumulation of errors and the propagation of hallucinations.<n>We design a Multi-Agent System called LSTM-MAS, emulating LSTM's hierarchical information flow and gated memory mechanisms for long-context understanding.<n>Our model achieves improvements of 40.93%, 43.70%,121.57% and 33.12%, on NarrativeQA, Qasper, HotpotQA, and MuSiQue, respectively.
  arXiv  Detail & Related papers  (2026-01-17T05:16:23Z)
• Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents [57.38404718635204]
  Large language model (LLM) agents face fundamental limitations in long-horizon reasoning due to finite context windows.<n>Existing methods typically handle long-term memory (LTM) and short-term memory (STM) as separate components.<n>We propose Agentic Memory (AgeMem), a unified framework that integrates LTM and STM management directly into the agent's policy.
  arXiv  Detail & Related papers  (2026-01-05T08:24:16Z)
• MemSearcher: Training LLMs to Reason, Search and Manage Memory via End-to-End Reinforcement Learning [73.27233666920618]
  We propose MemSearcher, an agent workflow that iteratively maintains a compact memory and combines the current turn with it.<n>At each turn, MemSearcher fuses the user's question with the memory to generate reasoning traces, perform search actions, and update memory to retain only information essential for solving the task.<n>We introduce multi-context GRPO, an end-to-end RL framework that jointly optimize reasoning, search strategies, and memory management of MemSearcher Agents.
  arXiv  Detail & Related papers  (2025-11-04T18:27:39Z)
• Tree of Agents: Improving Long-Context Capabilities of Large Language Models through Multi-Perspective Reasoning [11.045096250408067]
  Tree of Agents (TOA) is a multi-agent reasoning framework that segments the input into chunks processed by independent agents.<n>TOA enables agents to probe different reasoning orders for multi-perspective understanding.<n>To improve processing efficiency, we incorporate prefix-hash caching and adaptive pruning strategies.
  arXiv  Detail & Related papers  (2025-09-08T08:34:02Z)
• MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agents [84.62985963113245]
  We introduce MEM1, an end-to-end reinforcement learning framework that enables agents to operate with constant memory across long multi-turn tasks.<n>At each turn, MEM1 updates a compact shared internal state that jointly supports memory consolidation and reasoning.<n>We show that MEM1-7B improves performance by 3.5x while reducing memory usage by 3.7x compared to Qwen2.5-14B-Instruct on a 16-objective multi-hop QA task.
  arXiv  Detail & Related papers  (2025-06-18T19:44:46Z)
• From Single to Multi-Granularity: Toward Long-Term Memory Association and Selection of Conversational Agents [79.87304940020256]
  Large Language Models (LLMs) have been widely adopted in conversational agents.<n>MemGAS is a framework that enhances memory consolidation by constructing multi-granularity association, adaptive selection, and retrieval.<n> Experiments on four long-term memory benchmarks demonstrate that MemGAS outperforms state-of-the-art methods on both question answer and retrieval tasks.
  arXiv  Detail & Related papers  (2025-05-26T06:13:07Z)
• Task Memory Engine (TME): Enhancing State Awareness for Multi-Step LLM Agent Tasks [0.0]
  We propose a lightweight and structured memory module that tracks task execution using a hierarchical Task Memory Tree (TMT)<n>TME is designed to be graph-aware, supporting reusable substeps, converging task paths, and shared dependencies.
  arXiv  Detail & Related papers  (2025-04-11T13:38:36Z)
• Hierarchical Context Merging: Better Long Context Understanding for Pre-trained LLMs [61.40047491337793]
  We present Hierarchical cOntext MERging (HOMER), a new training-free scheme designed to overcome the limitations of large language models. HomeR uses a divide-and-conquer algorithm, dividing long inputs into manageable chunks. A token reduction technique precedes each merging, ensuring memory usage efficiency.
  arXiv  Detail & Related papers  (2024-04-16T06:34:08Z)
• 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)
• SCM: Enhancing Large Language Model with Self-Controlled Memory Framework [54.33686574304374]
  Large Language Models (LLMs) are constrained by their inability to process lengthy inputs, resulting in the loss of critical historical information.<n>We propose the Self-Controlled Memory (SCM) framework to enhance the ability of LLMs to maintain long-term memory and recall relevant information.
  arXiv  Detail & Related papers  (2023-04-26T07:25:31Z)

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.