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

arXiv:2608.24876 · cs.AI, cs.CL · Submitted 2026-08-25 · Read on arXiv

cs.AI, cs.CL

Submitted: 2026-08-25

Updated: 2026-08-25

Comments: Code: https://github.com/Gen-Verse/Recuris

Code: https://github.com/Gen-Verse/Recuris

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Working Memory — 59× in this paper
• Benchmark — 34× in this paper · explained in 2 episodes
• Adaptation — 25× in this paper · explained in 1 episode
• Trace — 24× in this paper · explained in 2 episodes
• Experiential Memory — 21× in this paper
• Verifier — 13× in this paper · explained in 2 episodes
• Agent Harness — 7× in this paper · explained in 1 episode
• Agent Skills — 7× in this paper · explained in 1 episode
• Verification — 4× in this paper · explained in 2 episodes
• Ablation — 3× in this paper · explained in 1 episode
• Benchmarking — 3× in this paper · explained in 3 episodes
• Grounding — 3× in this paper · explained in 3 episodes
• Consistency — 2× in this paper · explained in 3 episodes
• Decode — 2× in this paper · explained in 2 episodes
• Fine-Tuning — 2× in this paper · explained in 5 episodes
• Generalization — 2× in this paper · explained in 13 episodes
• International Conference on Machine Learning — 2× in this paper
• Multi-Agent System — 2× in this paper · explained in 5 episodes
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Self-Evolving Agents — 2× in this paper · explained in 2 episodes
• AI Agents — 1× in this paper · explained in 2 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Agentic Reasoning — 1× in this paper · explained in 1 episode
• Agentic System — 1× in this paper · explained in 2 episodes
• Alignment — 1× in this paper · explained in 1 episode
• Core — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Fourteenth International Conference on Learning Representations — 1× in this paper
• Hallucination — 1× in this paper · explained in 3 episodes
• In Conference on Language Modeling — 1× in this paper
• Large Language Model (LLM) — 1× in this paper · explained in 3 episodes
• Meeting of the Association for Computational Linguistics — 1× in this paper
• Pruning — 1× in this paper · explained in 4 episodes
• Scaffolding — 1× in this paper · explained in 3 episodes

Sources

• GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
• SagaLLM: Context Management, Validation, and Transaction Guarantees for Multi-Agent LLM Planning
• Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution
• AutoGuide: Automated Generation and Selection of Context-Aware Guidelines for Large Language Model Agents
• Automated Design of Agentic Systems
• DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines
• ReflAct: World-Grounded Decision Making in LLM Agents via Goal-State Reflection
• SkillsInjector: Dynamic Skill Context Construction for LLM Agents
• How Well Do Agentic Skills Work in the Wild: Benchmarking LLM Skill Usage in Realistic Settings
• A Self-Improving Coding Agent
• StateAct: Enhancing LLM Base Agents via Self-prompting and State-tracking
• Goedel Machines: Self-Referential Universal Problem Solvers Making Provably Optimal Self-Improvements
• AgentSquare: Automatic LLM Agent Search in Modular Design Space
• Your Agent May Misevolve: Emergent Risks in Self-evolving LLM Agents
• PACE: Anytime-Valid Acceptance Tests for Self-Evolving Agents
• Reflexion: Language Agents with Verbal Reinforcement Learning
• LADDER: Self-Improving LLMs Through Recursive Problem Decomposition
• Cognitive Architectures for Language Agents
• Voyager: An Open-Ended Embodied Agent with Large Language Models
• SAGE: A Novelty Gate for Efficient Memory Evolution in Agentic LLMs

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems