Hindsight is 20/20: Building Agent Memory that Retains, Recalls, and Reflects

• URL: http://arxiv.org/abs/2512.12818v1
• Date: Sun, 14 Dec 2025 19:47:23 GMT
• Title: Hindsight is 20/20: Building Agent Memory that Retains, Recalls, and Reflects
• Abstract summary: We present Hindsight, a memory architecture that treats agent memory as a structured, first-class substrate for reasoning.<n>It supports three core operations -- retain, recall, and reflect -- that govern how information is added, accessed, and updated.<n>Hindsight with an open-source 20B model lifts overall accuracy from 39% to 83.6% over a full-context baseline.
• Score: 11.300084544174894
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Agent memory has been touted as a dimension of growth for LLM-based applications, enabling agents that can accumulate experience, adapt across sessions, and move beyond single-shot question answering. The current generation of agent memory systems treats memory as an external layer that extracts salient snippets from conversations, stores them in vector or graph-based stores, and retrieves top-k items into the prompt of an otherwise stateless model. While these systems improve personalization and context carry-over, they still blur the line between evidence and inference, struggle to organize information over long horizons, and offer limited support for agents that must explain their reasoning. We present Hindsight, a memory architecture that treats agent memory as a structured, first-class substrate for reasoning by organizing it into four logical networks that distinguish world facts, agent experiences, synthesized entity summaries, and evolving beliefs. This framework supports three core operations -- retain, recall, and reflect -- that govern how information is added, accessed, and updated. Under this abstraction, a temporal, entity aware memory layer incrementally turns conversational streams into a structured, queryable memory bank, while a reflection layer reasons over this bank to produce answers and to update information in a traceable way. On key long-horizon conversational memory benchmarks like LongMemEval and LoCoMo, Hindsight with an open-source 20B model lifts overall accuracy from 39% to 83.6% over a full-context baseline with the same backbone and outperforms full context GPT-4o. Scaling the backbone further pushes Hindsight to 91.4% on LongMemEval and up to 89.61% on LoCoMo (vs. 75.78% for the strongest prior open system), consistently outperforming existing memory architectures on multi-session and open-domain questions.

Related papers

• Memory is Reconstructed, Not Retrieved: Graph Memory for LLM Agents [51.30250860677378]
  We propose MRAgent, a framework that combines an associative memory graph with an active reconstruction mechanism.<n>Running on a Cue-Tag-Content graph, our active reconstruction mechanism integrates reasoning directly into memory access.<n>Experiments on the LoCoMo benchmark and LongMemEval benchmark demonstrate significant improvements over strong baselines.
  arXiv  Detail & Related papers  (2026-06-04T11:29:46Z)
• GroupMemBench: Benchmarking LLM Agent Memory in Multi-Party Conversations [25.703133924514884]
  Large Language Model (LLM) agents increasingly serve as personal assistants and workplace collaborators.<n>Existing memory systems and benchmarks are built around the dyadic, single-user setup.<n>We introduce GroupMemBench, a benchmark that exposes three properties of group memory.
  arXiv  Detail & Related papers  (2026-05-14T07:38:29Z)
• ByteRover: Agent-Native Memory Through LLM-Curated Hierarchical Context [7.906778920268216]
  We propose ByteRover, an agent-native memory architecture that inverts the memory pipeline.<n>ByteRover represents knowledge in a hierarchical Context Tree, a file-based knowledge graph organized as Domain, Topic, Subtopic, and Entry.<n> Experiments on LoCoMo and LongMemEval demonstrate that ByteRover achieves state-of-the-art accuracy on LoCoMo and competitive results on LongMemEval.
  arXiv  Detail & Related papers  (2026-04-02T04:15:42Z)
• MemMA: Coordinating the Memory Cycle through Multi-Agent Reasoning and In-Situ Self-Evolution [52.29303869050117]
  Memory-augmented LLM agents maintain external memory banks to support long-horizon interaction.<n>MemMA is a plug-and-play multi-agent framework that coordinates the memory cycle along both the forward and backward paths.
  arXiv  Detail & Related papers  (2026-03-19T10:15:59Z)
• AdaMem: Adaptive User-Centric Memory for Long-Horizon Dialogue Agents [49.63422082885992]
  We propose AdaMem, an adaptive user-centric memory framework for long-horizon dialogue agents.<n>AdaMem organizes dialogue history into working, episodic, persona, and graph memories.<n>We evaluate AdaMem on the LoCoMo and PERSONAMEM benchmarks for long-horizon reasoning and user modeling.
  arXiv  Detail & Related papers  (2026-03-17T13:22:54Z)
• Memory for Autonomous LLM Agents:Mechanisms, Evaluation, and Emerging Frontiers [0.42061757959666934]
  Large language model (LLM) agents increasingly operate in settings where a single context window is too small to capture what has happened.<n>Memory is what turns a stateless text generator into a genuinely adaptive agent.<n>This survey offers a structured account of how memory is designed, implemented, and evaluated in modern LLM-based agents.
  arXiv  Detail & Related papers  (2026-03-08T15:08:01Z)
• Graph-based Agent Memory: Taxonomy, Techniques, and Applications [63.70340159016138]
  Memory emerges as the core module in the Large Language Model (LLM)-based agents for long-horizon complex tasks.<n>Among diverse paradigms, graph stands out as a powerful structure for agent memory due to the intrinsic capabilities to model relational dependencies.<n>This survey presents a comprehensive review of agent memory from the graph-based perspective.
  arXiv  Detail & Related papers  (2026-02-05T13:49:05Z)
• The AI Hippocampus: How Far are We From Human Memory? [77.04745635827278]
  Implicit memory refers to the knowledge embedded within the internal parameters of pre-trained transformers.<n>Explicit memory involves external storage and retrieval components designed to augment model outputs with dynamic, queryable knowledge representations.<n>Agentic memory introduces persistent, temporally extended memory structures within autonomous agents.
  arXiv  Detail & Related papers  (2026-01-14T03:24:08Z)
• Memory Matters More: Event-Centric Memory as a Logic Map for Agent Searching and Reasoning [55.251697395358285]
  Large language models (LLMs) are increasingly deployed as intelligent agents that reason, plan, and interact with their environments.<n>To effectively scale to long-horizon scenarios, a key capability for such agents is a memory mechanism that can retain, organize, and retrieve past experiences.<n>We propose CompassMem, an event-centric memory framework inspired by Event Theory.
  arXiv  Detail & Related papers  (2026-01-08T08:44:07Z)
• Memory in the Age of AI Agents [217.9368190980982]
  This work aims to provide an up-to-date landscape of current agent memory research.<n>We identify three dominant realizations of agent memory, namely token-level, parametric, and latent memory.<n>To support practical development, we compile a comprehensive summary of memory benchmarks and open-source frameworks.
  arXiv  Detail & Related papers  (2025-12-15T17:22:34Z)
• Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory [89.65731902036669]
  Evo-Memory is a streaming benchmark and framework for evaluating self-evolving memory in large language model (LLM) agents.<n>We evaluate over ten representative memory modules and evaluate them across 10 diverse multi-turn goal-oriented and single-turn reasoning and QA datasets.
  arXiv  Detail & Related papers  (2025-11-25T21:08:07Z)
• SEDM: Scalable Self-Evolving Distributed Memory for Agents [23.182291416527764]
  SEDM is a verifiable and adaptive framework that transforms memory from a passive repository into an active, self-optimizing component.<n>We show that SEDM improves reasoning accuracy while reducing token overhead compared with strong memory baselines.<n>Results highlight SEDM as a scalable and sustainable memory mechanism for open-ended multi-agent collaboration.
  arXiv  Detail & Related papers  (2025-09-11T14:37:37Z)
• Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning [89.55738101744657]
  Large Language Models (LLMs) have demonstrated impressive capabilities across a wide range of NLP tasks, but they remain fundamentally stateless.<n>We present Memory-R1, a reinforcement learning framework that equips LLMs with the ability to actively manage and utilize external memory.
  arXiv  Detail & Related papers  (2025-08-27T12:26:55Z)
• Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions [22.190297901876278]
  We identify four core competencies essential for memory agents: accurate retrieval, test-time learning, long-range understanding, and selective forgetting.<n>Existing benchmarks either rely on limited context lengths or are tailored for static, long-context settings like book-based QA.<n>We introduce MemoryAgentBench, a new benchmark specifically designed for memory agents.
  arXiv  Detail & Related papers  (2025-07-07T17:59:54Z)
• 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)

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.