Recursive Experiential-Working Memory Evolution for Long-Horizon Agent Harnesses

• URL: http://arxiv.org/abs/2608.24876v1
• Date: Tue, 25 Aug 2026 17:56:35 GMT
• Title: Recursive Experiential-Working Memory Evolution for Long-Horizon Agent Harnesses
• Abstract summary: Recuris is a Experiential-Working Memory architecture for long-horizon agent harnesses.<n>Working Memory tracks task progress and guides skill selection from Experiential Memory.<n>Across four long-horizon benchmarks and ten models, Recuris improves task success in 35 of the 37 completed model-benchmark pairs.
• Score: 83.32611586724165
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recursive self-improvement (RSI) remains hard in long-horizon tasks, where growing histories obscure the task state and misalign skill invocation. We introduce Recuris, a recursive Experiential-Working Memory architecture for long-horizon agent harnesses, in which Working Memory tracks task progress and guides skill selection from Experiential Memory, grounding skill use in current needs rather than the full history. This coupling also turns execution into structured evidence that localizes failures to specific memory components. Across tasks, a fixed Meta-Agent turns that evidence into localized, validation-gated updates to Skill Memory that reshape execution and yield new evidence, forming a bounded recursive memory-evolution loop. Across four long-horizon benchmarks and ten models, Recuris improves task success in 35 of the 37 completed model-benchmark pairs, carrying frontier models to SOTA-level task success: on tau-bench it adds +17.8 points to GPT-5.6 Sol and +15.6 to Claude Opus 5, taking Opus 5 to 87.9%, and +16.6/+13.5 points on Qwen3.6-27B/35B on SkillFlow. The advantage widens as the interaction horizon grows, to +32.2 points on the longest tasks, and common long-horizon failures fall by up to 80%. These results position recursively evolving memory as a scalable foundation for RSI, enabling agents to continuously transform accumulated experience into increasingly effective long-horizon behavior. Code: https://github.com/Gen-Verse/Recuris

Related papers

• HyperSkill: Self-Evolving LLM Agents via Hypergraph-Structured Skill Memory [3.6156240053949866]
  HyperSkill represents memory as a hypergraph with two node types, subtask steps and reusable skills, where each hyperedge links the subtasks and skills from a single trajectory.<n> Periodic structure-informed maintenance prunes low-utility nodes and redundant merges skills via quality-weighted propagation.<n>Across xBench, GAIA, and WebWalkerQA with GPT-4o and Qwen3-30B-A3B, HyperSkill outperforms ten memory baselines, yielding gains of up to +11.51 on GAIA and +11.18 on WebWalkerQA.
  arXiv  Detail & Related papers  (2026-08-17T05:10:27Z)
• Skills in Weights, Memory in Code: Hybrid Learning for Memory-Dependent Robot Manipulation [12.918310076135313]
  Real-world manipulation is often non-Markovian, requiring robots to retain and reason over task-relevant information.<n>We propose HyMeS, a hybrid learning framework that leverages the reasoning and memory-management capabilities of coding agents.<n>On RoboMemArena, HyMeS improves mean cumulative success from 52.5% to 66.2% and mean task success from 41.3% to 60.1% over pi0.5, while outperforming PrediMem by 4.5 points in cumulative success and 14.5 points in task success.
  arXiv  Detail & Related papers  (2026-08-10T10:35:47Z)
• AutoMem: Automated Learning of Memory as a Cognitive Skill [63.07128029793901]
  We show that memory expertise is a learned skill.<n>We introduce AutoMem, a framework that automates the two axes of memory management.<n>Our results show that memory management is an independently learnable skill.
  arXiv  Detail & Related papers  (2026-07-01T17:57:03Z)
• OPD-Evolver: Cultivating Holistic Agent Evolver via On-Policy Distillation [71.57258488733974]
  Memory has become a standard substrate for self-evolving agents, yet retaining experience is not the same as learning how to evolve through it.<n>We introduce OPD-Evolver, a slow-fast co-evolution framework that cultivates such an agent evolver through on-policy self-distillation.
  arXiv  Detail & Related papers  (2026-06-16T07:33:53Z)
• AdMem: Advanced Memory for Task-solving Agents [13.611633561917513]
  Large Language Models (LLMs) show promise as tool-using agents but remain limited in long-horizon tasks that require remembering, organizing, and reusing knowledge.<n>We introduce a unified and automatic memory framework that integrates semantic, episodic, and procedural memory in a bi-level design combining short-term and long-term stores.
  arXiv  Detail & Related papers  (2026-06-05T00:11:57Z)
• LongMemEval-V2: Evaluating Long-Term Agent Memory Toward Experienced Colleagues [80.29362825271768]
  LongMemEval-V2 is a benchmark for evaluating whether memory systems can help agents acquire the experience needed to become knowledgeable colleagues in customized environments.<n>LME-V2 contains 451 manually curated questions covering five core memory abilities for web agents.<n>We propose a suite of two memory methods: AgentRunbook-R, an efficient RAG-based memory with knowledge pools for raw state observations, events, and strategy notes, and AgentRunbook-C, which stores trajectories as files and invokes a coding agent to gather evidence in an augmented sandbox.
  arXiv  Detail & Related papers  (2026-05-12T17:59:34Z)
• Fine-Mem: Fine-Grained Feedback Alignment for Long-Horizon Memory Management [63.48041801851891]
  Fine-Mem is a unified framework designed for fine-grained feedback alignment.<n> Experiments on Memalpha and MemoryAgentBench demonstrate that Fine-Mem consistently outperforms strong baselines.
  arXiv  Detail & Related papers  (2026-01-13T11:06:17Z)
• Hindsight is 20/20: Building Agent Memory that Retains, Recalls, and Reflects [11.300084544174894]
  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.
  arXiv  Detail & Related papers  (2025-12-14T19:47:23Z)
• MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulation [59.31354761628506]
  Temporal context is essential for robotic manipulation because such tasks are inherently non-Markovian, yet mainstream VLA models typically overlook it.<n>We propose MemoryVLA, a Cognition-Memory-Action framework for long-horizon robotic manipulation.<n>We evaluate it on 150+ simulation and real-world tasks across three robots.
  arXiv  Detail & Related papers  (2025-08-26T17:57:16Z)

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.