Skills in Weights, Memory in Code: Hybrid Learning for Memory-Dependent Robot Manipulation

• URL: http://arxiv.org/abs/2608.09410v1
• Date: Mon, 10 Aug 2026 10:35:47 GMT
• Title: Skills in Weights, Memory in Code: Hybrid Learning for Memory-Dependent Robot Manipulation
• Abstract summary: 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.
• Score: 12.918310076135313
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Modern vision-language-action (VLA) policies have acquired broad manipulation skills, but typically generate each action chunk from the current observation or a short fixed-length history. However, real-world manipulation is often non-Markovian, requiring robots to retain and reason over task-relevant information from long-horizon interaction histories to determine the next action. To address this challenge, we propose HyMeS, a hybrid learning framework that leverages the reasoning and memory-management capabilities of coding agents to steer a Markovian VLA for memory-dependent manipulation. Specifically, HyMeS learns low-level motor skills through gradient-based imitation learning, while a coding agent acquires high-level memory-management strategies through heuristic learning by iteratively updating an executable heuristic system from rollout feedback. Furthermore, we close the loop between steering and execution through multimodal stage-completion verification, which updates memory using proprioceptive signals and multi-frame VLM judgments. Compared with end-to-end memory-augmented VLAs, HyMeS requires demonstrations only for reusable motor skills rather than for every history-dependent task configuration, enabling data-efficient compositional generalization. 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.

Related papers

• Recursive Experiential-Working Memory Evolution for Long-Horizon Agent Harnesses [83.32611586724165]
  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.
  arXiv  Detail & Related papers  (2026-08-25T17:56:35Z)
• 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)
• 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)
• Task-Focused Memorization for Multimodal Agents [9.026427508263641]
  Long-term memory is essential for multimodal agents to build coherent experience, accumulate world knowledge, and achieve continual learning.<n>We introduce TaskMem, a reinforcement-learning-based framework that enables the policy to adjust its focus to the demands of real tasks encountered in the environment.
  arXiv  Detail & Related papers  (2026-05-29T09:43:35Z)
• 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)
• RoboMME: Benchmarking and Understanding Memory for Robotic Generalist Policies [54.23445842621374]
  Memory is critical for long-horizon and history-dependent robotic manipulation.<n>Recent vision-language-action (VLA) models have begun to incorporate memory mechanisms.<n>We introduce RoboMME: a large-scale standardized benchmark for evaluating and advancing VLA models.
  arXiv  Detail & Related papers  (2026-03-04T21:59:32Z)
• 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)
• Memp: Exploring Agent Procedural Memory [72.41472703974935]
  Large Language Models (LLMs) based agents excel at diverse tasks, yet they suffer from brittle procedural memory that is manually engineered or entangled in static parameters.<n>We propose Memp that distills past agent trajectories into both fine-grained, step-by-step instructions and higher-level, script-like abstractions.<n>We show that as the memory repository is refined, agents achieve steadily higher success rates and greater efficiency on analogous tasks.
  arXiv  Detail & Related papers  (2025-08-08T16:20:56Z)
• RoboMemory: A Brain-inspired Multi-memory Agentic Framework for Interactive Environmental Learning in Physical Embodied Systems [41.89907261427986]
  Embodied agents face persistent challenges in real-world environments, including partial observability, limited spatial reasoning, and high-latency multi-memory integration.<n>We present RoboMemory, a brain-inspired framework that unifies Spatial, Temporal, Episodic, and Semantic memory under a parallelized architecture for efficient long-horizon planning and interactive environmental learning.<n> Experiments on EmbodiedBench show that RoboMemory, built on Qwen2.5-VL-72B-Ins, improves average success rates by 25% over its baseline and exceeds the closed-source state-of-the-art (SOTA) Gemini-1.5-
  arXiv  Detail & Related papers  (2025-08-02T15:39:42Z)
• From RAG to Memory: Non-Parametric Continual Learning for Large Language Models [6.380729797938521]
  retrieval-augmented generation (RAG) has become the dominant way to introduce new information.<n>Recent RAG approaches augment vector embeddings with various structures like knowledge graphs to address some gaps, namely sense-making and associativity.<n>We propose HippoRAG 2, a framework that outperforms standard RAG comprehensively on factual, sense-making, and associative memory tasks.
  arXiv  Detail & Related papers  (2025-02-20T18:26:02Z)
• Robot Learning of Mobile Manipulation with Reachability Behavior Priors [38.49783454634775]
  Mobile Manipulation (MM) systems are ideal candidates for taking up the role of a personal assistant in unstructured real-world environments. Among other challenges, MM requires effective coordination of the robot's embodiments for executing tasks that require both mobility and manipulation. We study the integration of robotic reachability priors in actor-critic RL methods for accelerating the learning of MM for reaching and fetching tasks.
  arXiv  Detail & Related papers  (2022-03-08T12:44:42Z)

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.