MedMemoryBench supplies a 2,000-session synthetic medical trajectory dataset and an evaluate-while-constructing streaming protocol to expose memory saturation and reasoning failures in current agent architectures for personalized healthcare.
hub Mixed citations
MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory
Mixed citation behavior. Most common role is background (60%).
35
Pith papers citing it
Background
60% of classified citations
abstract
The hallmark of human intelligence is the self-evolving ability to master new skills by learning from past experiences. However, current AI agents struggle to emulate this self-evolution: fine-tuning is computationally expensive and prone to catastrophic forgetting, while existing memory-based methods rely on passive semantic matching that often retrieves noise. To address these challenges, we propose MemRL, a non-parametric approach that evolves via reinforcement learning on episodic memory. By decoupling stable reasoning from plastic memory, MemRL employs a Two-Phase Retrieval mechanism to filter noise and identify high-utility strategies through environmental feedback. Extensive experiments on HLE, BigCodeBench, ALFWorld, and Lifelong Agent Bench demonstrate that MemRL significantly outperforms state-of-the-art baselines, confirming that MemRL effectively reconciles the stability-plasticity dilemma, enabling continuous runtime improvement without weight updates. Code is available at https://github.com/MemTensor/MemRL.
hub tools
citation-role summary
background 3
baseline 2
citation-polarity summary
years
2026 35representative citing papers
OSL-MR is a learning-augmented framework that casts memory retention as constrained stochastic optimization under partial observability and outperforms heuristic baselines on LoCoMo and LongMemEval.
SkeMex distills agent trajectories into value-aware skills organized in general/task/action branches and evolves them via a closed-loop Read-Write-Assess-Govern process, outperforming prior memory agents on clinical tasks.
Framework estimates context-dependent marginal utility of candidate skills via reward gaps in matched base vs. skill-augmented rollouts to filter skills and co-train policy as generator.
CORE distills contrasts between successful and unsuccessful reasoning traces into compact natural-language insights that enable faster model self-improvement on reasoning tasks with fewer rollouts than parametric or other non-parametric baselines.
EXG is an experience graph framework for self-evolving LLM agents that supports online real-time growth and offline reuse to enhance solution quality and efficiency on code generation and reasoning benchmarks.
SkillTTA synthesizes temporary task-specific skills from retrieved training trajectories to boost LLM agent Pass@1 scores on SpreadsheetBench and BigCodeBench without parameter updates.
ClawForge is a generator framework that creates reproducible executable benchmarks for command-line agents under state conflict, with ClawForge-Bench showing frontier models reach at most 45.3% strict accuracy and that state inspection drives most performance gaps.
EvolveMem enables autonomous self-evolution of LLM memory retrieval configurations via LLM diagnosis and safeguards, delivering 25.7% gains over strong baselines on LoCoMo and 18.9% on MemBench with positive cross-benchmark transfer.
MAGE uses a four-subgraph co-evolutionary knowledge graph plus dual bandits to externalize and retrieve experience for stable self-evolution of frozen language-model agents, showing gains on nine diverse benchmarks.
EDV decouples execution, distillation by a third-party agent, and consensus verification to filter erroneous trajectories in LLM agent experience learning, outperforming baselines on tau2-bench, Mind2Web, and MMTB.
HORMA builds a hierarchical memory structure from agent experiences and trains a lightweight RL navigator to retrieve minimal sufficient context, yielding better task performance with at most 22.17% of baseline token usage on ALFWorld, LoCoMo, and LongMemEval.
ExpGraph builds a graph of summarized agent experiences and uses graph diffusion plus an RL-trained retrieval copilot to improve frozen LLM executors on QA, math, code, and agentic tasks without parameter updates.
FluxMem evolves memory as a heterogeneous graph via three refinement stages and reports consistent state-of-the-art results on LoCoMo, Mind2Web, and GAIA benchmarks.
Auto-Dreamer trains an offline memory consolidator via GRPO on agent performance to abstract cross-session patterns, outperforming baselines by 7 points on ScienceWorld with 12x smaller memory and generalizing to ALFWorld and WebArena.
SkillGraph represents skills as nodes in an evolving directed graph with typed dependency edges and updates the graph from RL trajectories to boost compositional task performance.
Shepherd provides a reversible execution trace substrate for LLM agents that enables meta-agents to inspect and transform runs, yielding reported gains on coding and terminal benchmarks via supervision, counterfactual repair, and RL credit assignment.
RL Developer Memory is a feedback-normalized, safety-gated memory architecture for RL coding agents that logs contextual decisions and applies conservative off-policy gates to maintain 80% decision accuracy and full hard-negative suppression on a 200-case benchmark.
CreativeGame enables iterative HTML5 game generation via mechanic-guided planning, lineage memory, runtime validation, and programmatic rewards to produce inspectable version-to-version mechanic evolution.
Holos is a five-layer LLM-based multi-agent system architecture using the Nuwa engine for agent generation, a market-driven Orchestrator for coordination, and an endogenous value cycle for incentive-compatible persistence in the Agentic Web.
Self-evolving LLM agents introduce persistent, amplifying security threats that static defenses cannot address, as shown by analysis of 25 attack surface cells and case studies.
A survey that maps safety risks in personalized LLMs, introduces a unified taxonomy, and highlights three structural inadequacies in existing research on user-invariant safety, isolated techniques, and short-term evaluations.
ConMem distills agent trajectories into structured memory cards organized in a relation-aware graph to enable training-free, relation-coordinated adaptation in LLM-based multi-agent systems.
Introduces FinEvolveBench and Tree-of-Experience showing structured experience management improves LLM agent performance over baselines in low-repetition implicit-reward settings.