Continual Learning for LLM Agents

LLM: Large Language Model

Ask about this topic

Overview

Continual learning for large language model agents asks how they can improve from ongoing interaction, feedback, and changing environments rather than starting each task from scratch. Common approaches store and retrieve episodes, rules, or reusable skills; refine prompts and agent harnesses; or use reinforcement learning and fine-tuning to consolidate experience into model parameters. Work evaluates these methods in long-horizon settings such as web tasks, coding, games, and embodied environments, where agents must transfer what they learn to later tasks. A central tension is balancing adaptation with retention: accumulated memories and updates can cause interference, stale guidance, or forgetting, and gains in one setting do not always transfer to another.

Latest papers

CardsList

202 papers45 papers in the last four weeks, up 105% on the four weeks before. 0.3% of all new papers.

Mar 23, 2026

SOLAR: A Self-Optimizing Open-Ended Autonomous Agent for Lifelong Learning and Continual Adaptation

Despite the remarkable success of large language models (LLMs), they still face bottlenecks while deploying in dynamic, real-world settings with primary challenges being concept drift and the high cost of gradient-based adaptation. Traditional fine-tuning (FT) struggles to adapt to non-stationary data streams without resulting in catastrophic for getting or requiring extensive manual data curation. To address these limitations within the streaming and continual learning paradigm, we propose the Self-Optimizing Lifelong Autonomous Reasoner (SOLAR) which is an open-ended autonomous agent that leverages parameter-level meta-learning to self-improve, treating model weights as an environment for exploration. It initiates the process by consolidating a strong prior over common-sense knowledge making it effective for transfer-learning. By utilizing a multi-level reinforcement learning approach, SOLAR autonomously discovers adaptation strategies, enabling efficient test-time adaptation to unseen domains. Crucially, SOLAR maintains an evolving knowledge base of valid modification strategies, implicitly acting as an episodic memory buffer to balance plasticity (adaptation to new tasks) and stability (retention of meta-knowledge). Experiments demonstrate that SOLAR outperforms strong baselines on common-sense, mathematical, medical, coding, social and logical reasoning tasks, marking a significant step toward autonomous agents capable of lifelong adaptation in evolving environments.

Nitin Vetcha, Dianbo Liu

Department of Ophthalmology, Yong Loo Lin School of Medicine, National University of Singapore, Singapore · Department of Computational and Data Sciences, Indian Institute of Science, Bangalore, Karnataka, India

Continual Learning for LLM AgentsContinual Learning for LLMsRL for LLM AgentsMeta-LearningTest-Time AdaptationMemory-Augmented Language Model Agents
AskPDF
Mar 21, 2026

REVERE: Reflective Evolving Research Engineer

Existing prompt-optimization techniques rely on local signals, causing poor generalization across tasks. In addition, they also rely on weak update mechanisms, such as full-prompt rewrites or unstructured merges, which cause knowledge loss and unstable adaptation. These limitations are magnified in research-coding workflows, which involve heterogeneous repositories and weak feedback, limiting abstraction and learning across tasks. We introduce Reflective Evolving Research Engineer (REVERE), a lightweight, self-adapting agent framework that learns from a Global Training Context, distills recurring cross-repository failure modes into reusable heuristics, and applies targeted, code-based edits to agent prompts. REVERE is evaluated across settings ranging from long-horizon to single-shot benchmarks, and improves over prior expert-crafted instructions by 4.50% on SUPER, 1.3% on ResearchCodeBench, and 4.89% on ScienceAgentBench. It does so at nearly 10x lower cost and 2.7x faster adaptation than existing prompt-optimization baselines, demonstrating that self-adapting agents with continual learning and global memory consolidation can meaningfully evolve their capabilities over time.

Balaji Dinesh Gangireddi, Aniketh Garikaparthi, Manasi Patwardhan +1

TCS Research · Yale University

LLM Agent Self-ImprovementPrompt OptimizationSoftware Engineering AgentsContinual Learning for LLM AgentsMemory-Augmented Agents
AskPDF
Mar 19, 2026

Memento-Skills: Let Agents Design Agents

We introduce Memento-Skills, a generalist, continually-learnable LLM agent system that functions as an agent-designing agent: it autonomously constructs, adapts, and improves task-specific agents through experience. The system is built on a memory-based reinforcement learning framework with stateful prompts, where reusable skills (stored as structured markdown files) serve as persistent, evolving memory. These skills encode both behaviour and context, enabling the agent to carry forward knowledge across interactions. Starting from simple elementary skills (like Web search and terminal operations), the agent continually improves via the Read--Write Reflective Learning mechanism introduced in Memento~2~\cite{wang2025memento2}. In the read phase, a behaviour-trainable skill router selects the most relevant skill conditioned on the current stateful prompt; in the write phase, the agent updates and expands its skill library based on new experience. This closed-loop design enables continual learning without updating LLM parameters, as all adaptation is realised through the evolution of externalised skills and prompts. Unlike prior approaches that rely on human-designed agents, Memento-Skills enables a generalist agent to design agents end-to-end for new tasks. Through iterative skill generation and refinement, the system progressively improves its own capabilities. Experiments on the General AI Assistants benchmark and Humanity's Last Exam demonstrate sustained gains, achieving 26.2% and 116.2% relative improvements in overall accuracy, respectively. Code is available at https://github.com/Memento-Teams/Memento-Skills.

Huichi Zhou, Siyuan Guo, Anjie Liu +14

Agentic AILLM Agent Skill LearningContinual Learning for LLM AgentsMemory-Augmented Language Model AgentsRL for LLM AgentsLLM Agent Skill Retrieval
AskPDF
Mar 18, 2026

AgentFactory: A Self-Evolving Framework Through Executable Subagent Accumulation and Reuse

Building LLM-based agents has become increasingly important. Recent works on LLM-based agent self-evolution primarily record successful experiences as textual prompts or reflections, which cannot reliably guarantee efficient task re-execution in complex scenarios. We propose AgentFactory, a new self-evolution paradigm that preserves successful task solutions as executable subagent code rather than textual experience. Crucially, these subagents are continuously refined based on execution feedback, becoming increasingly robust and efficient as more tasks are encountered. Saved subagents are pure Python code with standardized documentation, enabling portability across any Python-capable system. We demonstrate that AgentFactory enables continuous capability accumulation: its library of executable subagents grows and improves over time, progressively reducing the effort required for similar tasks without manual intervention. Our implementation is open-sourced at https://github.com/zzatpku/AgentFactory, and our demonstration video is available at https://youtu.be/iKSsuAXJHW0.

Zhang Zhang, Shuqi Lu, Hongjin Qian +2

Peking University · Beijing Academy of Artificial Intelligence · Hong Kong Polytechnic University

Self-Evolving AgentsLLM Agent Skill LearningContinual Learning for LLM Agents
AskPDF
Mar 17, 2026

MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wild

Large language model (LLM) agents are increasingly used for complex tasks, yet deployed agents often remain static, failing to adapt as user needs evolve. This creates a tension between the need for continuous service and the necessity of updating capabilities to match shifting task distributions. On platforms like OpenClaw, which handle diverse workloads across 20+ channels, existing methods either store raw trajectories without distilling knowledge, maintain static skill libraries, or require disruptive downtime for retraining. We present MetaClaw, a continual meta-learning framework that jointly evolves a base LLM policy and a library of reusable behavioral skills. MetaClaw employs two complementary mechanisms. Skill-driven fast adaptation analyzes failure trajectories via an LLM evolver to synthesize new skills, enabling immediate improvement with zero downtime. Opportunistic policy optimization performs gradient-based updates via cloud LoRA fine-tuning and Reinforcement Learning with a Process Reward Model (RL-PRM). This is triggered during user-inactive windows by the Opportunistic Meta-Learning Scheduler (OMLS), which monitors system inactivity and calendar data. These mechanisms are mutually reinforcing: a refined policy generates better trajectories for skill synthesis, while richer skills provide higher-quality data for policy optimization. To prevent data contamination, a versioning mechanism separates support and query data. Built on a proxy-based architecture, MetaClaw scales to production-size LLMs without local GPUs. Experiments on MetaClaw-Bench and AutoResearchClaw show that skill-driven adaptation improves accuracy by up to 32% relative. The full pipeline advances Kimi-K2.5 accuracy from 21.4% to 40.6% and increases composite robustness by 18.3%. Code is available at https://github.com/aiming-lab/MetaClaw.

Peng Xia, Jianwen Chen, Xinyu Yang +10

UNC-Chapel Hill · Carnegie Mellon University · UC Santa Cruz +1

Continual Learning for LLM AgentsLLM Agent Skill LearningMeta-Learning
AskPDF
Mar 13, 2026

VERDICT: Verifiable Evolving Reasoning with Directive-Informed Collegial Teams for Legal Judgment Prediction

Legal Judgment Prediction (LJP) predicts applicable law articles, charges, and penalty terms from case facts. Beyond accuracy, LJP calls for intrinsically interpretable and legally grounded reasoning that can reconcile statutory rules with precedent-informed standards. However, existing methods often behave as static, one-shot predictors, providing limited procedural support for verifiable reasoning and little capability to adapt as jurisprudential practice evolves. We propose VERDICT, a self-refining collaborative multi-agent framework that simulates a virtual collegial panel. VERDICT assigns specialized agents to complementary roles (e.g., fact structuring, legal retrieval, opinion drafting, and supervisory verification) and coordinates them in a traceable draft--verify--revise workflow with explicit Pass/Reject feedback, producing verifiable reasoning traces and revision rationales. To capture evolving case experience, we further introduce a Hybrid Jurisprudential Memory (HJM) grounded in the Micro-Directive Paradigm, which stores precedent standards and continually distills validated multi-agent verification trajectories into updated Micro-Directives for continual learning across cases. We evaluate VERDICT on CAIL2018 and a newly constructed CJO2025 dataset with a strict future time-split for temporal generalization. VERDICT achieves state-of-the-art performance on CAIL2018 and demonstrates strong generalization on CJO2025. To facilitate reproducibility and further research, we release our code and the dataset at https://anonymous.4open.science/r/ARR-4437.

Hui Liao, Chuan Qin, Yongwen Ren +4

University of Science and Technology of China · Chinese Academy of Sciences · iFLYTEK AI Research

Legal Judgment PredictionLegal ReasoningMulti-Agent LLM SystemsContinual Learning for LLM AgentsLLM Self-Refinement
AskPDF
Mar 12, 2026

Can RL Improve Generalization of LLM Agents? An Empirical Study

Reinforcement fine-tuning (RFT) has shown promise for training LLM agents to perform multi-turn decision-making based on environment feedback. However, most existing evaluations remain largely in-domain: training and testing are conducted in the same environment or even on the same tasks. In real-world deployment, agents may operate in unseen environments with different background knowledge, observation spaces, and action interfaces. To characterize the generalization profile of RFT under such shifts, we conduct a systematic study along three axes: (1) within-environment generalization across task difficulty, (2) cross-environment transfer to unseen environments, and (3) sequential multi-environment training to quantify transfer and forgetting. Our results show that RFT generalizes well across task difficulty within an environment, but exhibits weaker transfer to unseen environments, which correlates with shifts in both semantic priors and observation/action interfaces. In contrast, sequential training yields promising downstream gains with minimal upstream forgetting, and mixture training across environments improves the overall balance. We further provide detailed analyses and deeper insights, and hope our work helps the community develop and deploy generalizable LLM agents.

Zhiheng Xi, Xin Guo, Jiaqi Liu +11

Fudan University · Shanghai Artificial Intelligence Laboratory · Meituan

LLM AgentsRL for LLM AgentsRL Fine-TuningGeneralization in RLContinual Learning for LLM AgentsMulti-Task RL
AskPDF
Mar 12, 2026

Compiled Memory: Not More Information, but More Precise Instructions for Language Agents

Existing memory systems for language agents address memory management: how to retrieve and page more information within a context budget. We address a complementary problem -- memory utility: what experience is worth keeping, and how it should change agent behavior. We present Atlas, a memory kernel that compiles accumulated task experience into an agent's instruction structure -- without fine-tuning, RAG, or human intervention. Memory is distillation, not storage; delivery is instruction rewriting, not context injection. Facts extracted from agent failures and successes are verified through a three-step promotion gate and delivered by rewriting the agent's system prompt with learned sub-bullets. On CUAD contract analysis, the evolved prompt improves GPT-4o token-level F1 by +8.7+8.7pp and precision by +12.5+12.5pp. On HotpotQA multi-hop QA, joint F1 improves +3.16+3.16pp. An ablation isolates the mechanism's defining property -- the training signal constraint: the evolved prompt learns exactly what it is taught, and nothing more. Applied to Claude Sonnet~4.5 using the same evolved prompt -- compiled from GPT-4o errors, unchanged -- joint F1 improves +2.31+2.31pp, with gains concentrating where Claude's stronger baseline leaves the most room -- confirming that the compiled knowledge is task-shaped, not model-shaped.

James Rhodes, George Kang

AlphaBitCore, Inc.

LLM Agent MemoryMemory-Augmented Language Model AgentsContinual Learning for LLM Agents
AskPDF
Mar 11, 2026

Towards Cold-Start Drafting and Continual Refining: A Value-Driven Memory Approach with Application to NPU Kernel Synthesis

Deploying Large Language Models to data-scarce programming domains poses significant challenges, particularly for kernel synthesis on emerging Domain-Specific Architectures where a "Data Wall" limits available training data. While models excel on data-rich platforms like CUDA, they suffer catastrophic performance drops on data-scarce ecosystems such as NPU programming. To overcome this cold-start barrier without expensive fine-tuning, we introduce EvoKernel, a self-evolving agentic framework that automates the lifecycle of kernel synthesis from initial drafting to continual refining. EvoKernel addresses this by formulating the synthesis process as a memory-based reinforcement learning task. Through a novel value-driven retrieval mechanism, it learns stage-specific Q-values that prioritize experiences based on their contribution to the current objective, whether bootstrapping a feasible draft or iteratively refining latency. Furthermore, by enabling cross-task memory sharing, the agent generalizes insights from simple to complex operators. By building an NPU variant of KernelBench and evaluating on it, EvoKernel improves frontier models' correctness from 11.0% to 83.0% and achieves a median speedup of 3.60x over initial drafts through iterative refinement. This demonstrates that value-guided experience accumulation allows general-purpose models to master the kernel synthesis task on niche hardware ecosystems. Our official page is available at https://evokernel.zhuo.li.

Yujie Zheng, Zhuo Li, Shengtao Zhang +8

Shanghai Jiao Tong University · Shanghai Artificial Intelligence Laboratory · Independent Researcher +1

Memory-Augmented Language Model AgentsRL for Code GenerationLarge Language Model-Guided OptimizationContinual Learning for LLM Agents
AskPDF
Mar 11, 2026

Reflection-Driven Self-Improving Language Model Agents for Adaptive RAN Slicing

Adaptive control in AI-native networks remains challenging because tasks such as dynamic Radio Access Network (RAN) slicing require persistent trade-off decisions among spectrum efficiency, service quality, and reconfiguration stability. Conventional Reinforcement Learning (RL) compresses these competing objectives into handcrafted scalar rewards, requiring exhaustive tuning for a balanced trade-off. Language model (LM) agents provide a new path toward adaptive control because they can semantically represent complex preference relations, but prompt-based adaptation struggles to retain long-horizon interaction history due to finite context limits. We propose a Reflection-Driven Self-Improvement (ReDSI) framework that replaces scalar rewards with semantic feedback for continuous policy adaptation. This framework is built upon a Small Language Model (SLM) agent for fast decision-making, coupled with a bi-perspective reflection to transform interaction history into preference data, subsequently distilling long-horizon decision experience into the SLM parameters through preference-based fine-tuning. Evaluated on a dynamic RAN slicing task, our method achieves an optimal trade-off across multiple competing objectives, outperforming standard RL baselines and existing LM-based agents by demonstrating substantially greater sample efficiency. These results highlight a viable paradigm of self-improving LM agents for reward-free multi-objective continuous control in AI-native networks.

Yuanhao Li, Haozhe Wang, Geyong Min +2

Department of Computer Science, Faculty of Environment, Science and Economy, University of Exeter, Exeter, EX4 4QF, UK. · British Telecom, UK.

Self-Improving AgentsLanguage Model-Based ControlContinual Learning for LLM AgentsFine-Tuning
AskPDF
Mar 9, 2026

RetroAgent: From Solving to Evolving via Retrospective Dual Intrinsic Feedback

Standard reinforcement learning (RL) for large language model (LLM) agents primarily optimizes extrinsic task rewards, often favoring isolated task completion over continual adaptation. This paradigm can cause premature convergence to suboptimal policies and leaves useful experience only implicitly encoded in model parameters, limiting its retrieval and reuse for future decisions. We introduce RetroAgent, an online RL framework that trains agents to master interactive environments not merely by solving tasks, but by evolving across episodes. Inspired by human retrospective self-improvement, RetroAgent augments extrinsic rewards with hindsight-generated dual intrinsic feedback: (1) Intrinsic Numerical Feedback, which rewards beneficial exploration by measuring incremental subtask progress relative to prior attempts; and (2) Intrinsic Language Feedback which distills successes and failures into reusable textual lessons for explicit experience reuse. To leverage these lessons effectively, we propose Similarity & Utility-Aware Upper Confidence Bound (SimUtil-UCB), a retrieval strategy that balances semantic relevance, historical utility, and exploration. Across four challenging agentic benchmarks, RetroAgent achieves new state-of-the-art performance, outperforming GRPO by +18.3% on ALFWorld, +15.4% on WebShop, +27.1% on Sokoban, and +8.9% on MineSweeper, while demonstrating strong test-time adaptation and out-of-distribution generalization.

Xiaoying Zhang, Zichen Liu, Yipeng Zhang +2

Shanghai AI Lab · National University of Singapore · Independent Researcher

Reinforcement LearningRL for LLM AgentsContinual Learning for LLM AgentsMemory-Augmented Language Model Agents
AskPDF
Mar 9, 2026

Adaptive Collaboration with Humans: Metacognitive Policy Optimization for Multi-Agent LLMs with Continual Learning

While scaling individual Large Language Models (LLMs) has delivered remarkable progress, the next frontier lies in scaling collaboration through multi-agent systems (MAS). However, purely autonomous MAS remain ''closed-world'' systems, constrained by the static knowledge horizon of pre-trained models. This limitation makes them brittle on tasks requiring knowledge beyond training data, often leading to collective failure under novel challenges. To address this, we propose the Human-In-the-Loop Multi-Agent Collaboration (HILA) framework, a principled paradigm for human--agent collaboration. HILA trains agents to learn a metacognitive policy that governs when to solve problems autonomously and when to defer to a human expert. To operationalize this policy, we introduce Dual-Loop Policy Optimization, which disentangles immediate decision-making from long-term capability growth. The inner loop applies Group Relative Policy Optimization (GRPO) with a cost-aware reward to optimize deferral decisions, while the outer loop implements continual learning, transforming expert feedback into high-quality supervised signals that strengthen the agent's reasoning ability. Experiments on challenging mathematical and problem-solving benchmarks show that HILA, equipped with Dual-Loop Policy Optimization, consistently outperforms advanced MAS, establishing a principled foundation for collaborative and continually improving agentic systems.

Wei Yang, Defu Cao, Jiacheng Pang +2

University of Southern California

Human-in-the-Loop AIMulti-Agent LLM SystemsLearning to DeferRL for LLM AgentsContinual Learning for LLM Agents
AskPDF
Mar 6, 2026

Lifelong Embodied Navigation Learning

Embodied navigation agents powered by large language models have shown strong performance on individual tasks but struggle to continually acquire new navigation skills, which suffer from catastrophic forgetting. We formalize this challenge as lifelong embodied navigation learning (LENL), where an agent is required to adapt to a sequence of navigation tasks spanning multiple scenes and diverse user instruction styles, while retaining previously learned knowledge. To tackle this problem, we propose Uni-Walker, a lifelong embodied navigation framework that decouples navigation knowledge into task-shared and task-specific components with Decoder Extension LoRA (DE-LoRA). To learn the shared knowledge, we design a knowledge inheritance strategy and an experts co-activation strategy to facilitate shared knowledge transfer and refinement across multiple navigation tasks. To learn the specific knowledge, we propose an expert subspace orthogonality constraint together and a navigation-specific chain-of-thought reasoning mechanism to capture specific knowledge and enhance instruction-style understanding. Extensive experiments demonstrate the superiority of Uni-Walker for building universal navigation agents with lifelong learning.

Xudong Wang, Jiahua Dong, Baichen Liu +3

State Key Laboratory of Robotics and Intelligent Systems, Shenyang Institute of Automation, Chinese Academy of Sciences · University of Chinese Academy of Sciences · Mohamed bin Zayed University of Artificial Intelligence

Embodied NavigationContinual Learning for LLM AgentsVision-Language NavigationLow-Rank Adaptation
AskPDF
Mar 3, 2026

CGL: Advancing Continual GUI Learning via Reinforcement Fine-Tuning

Graphical User Interface (GUI) Agents, benefiting from recent advances in multimodal large language models (MLLM), have achieved significant development. However, due to the frequent updates of GUI applications, adapting to new tasks without forgetting old tasks in GUI continual learning remains an open problem. In this work, we reveal that while Supervised Fine-Tuning (SFT) facilitates fast adaptation, it often triggers knowledge overwriting, whereas Reinforcement Learning (RL) demonstrates an inherent resilience that shields prior interaction logic from erasure. Based on this insight, we propose a Continual GUI Learning (CGL) framework that dynamically balances adaptation efficiency and skill retention by enhancing the synergy between SFT and RL. Specifically, we introduce an SFT proportion adjustment mechanism guided by policy entropy to dynamically control the weight allocation between the SFT and RL training phases. To resolve explicit gradient interference, we further develop a specialized gradient surgery strategy. By projecting exploratory SFT gradients onto GRPO-based anchor gradients, our method explicitly clips the components of SFT gradients that conflict with GRPO. On top of that, we establish an AndroidControl-CL benchmark, which divides GUI applications into distinct task groups to effectively simulate and evaluate the performance of continual GUI learning. Experimental results demonstrate the effectiveness of our proposed CGL framework across continual learning scenarios. The benchmark, code, and model will be made publicly available.

Zhenquan Yao, Zitong Huang, Yihan Zeng +5

Harbin Institute of Technology · Huawei Noah’s Ark Lab · University College Dublin +1

Continual Learning for LLM AgentsRL for GUI AgentsRL Fine-Tuning
AskPDF
Mar 3, 2026

AOI: Turning Failed Trajectories into Training Signals for Autonomous Cloud Diagnosis

Large language model (LLM) agents offer a promising data-driven approach to automating Site Reliability Engineering (SRE), yet their enterprise deployment is constrained by three challenges: restricted access to proprietary data, unsafe action execution under permission-governed environments, and the inability of closed systems to improve from failures. We present AOI (Autonomous Operations Intelligence), a trainable multi-agent framework formulating automated operations as a structured trajectory learning problem under security constraints. Our approach integrates three key components. First, a trainable diagnostic system applies Group Relative Policy Optimization (GRPO) to distill expert-level knowledge into locally deployed open-source models, enabling preference-based learning without exposing sensitive data. Second, a read-write separated execution architecture decomposes operational trajectories into observation, reasoning, and action phases, allowing safe learning while preventing unauthorized state mutation. Third, a Failure Trajectory Closed-Loop Evolver mines unsuccessful trajectories and converts them into corrective supervision signals, enabling continual data augmentation. Evaluated on the AIOpsLab benchmark, our contributions yield cumulative gains. (1) The AOI runtime alone achieves 66.3% best@5 success on all 86 tasks, outperforming the prior state-of-the-art (41.9%) by 24.4 points. (2) Adding Observer GRPO training, a locally deployed 14B model reaches 42.9% avg@1 on 63 held-out tasks with unseen fault types, surpassing Claude Sonnet 4.5. (3) The Evolver converts 37 failed trajectories into diagnostic guidance, improving end-to-end avg@5 by 4.8 points while reducing variance by 35%.

Pei Yang, Wanyi Chen, Asuka Yuxi Zheng +13

Gradient · Soochow University · UC Santa Cruz +4

LLM Agent TrainingAI Agent ReliabilityContinual Learning for LLM AgentsAI Agent Security
AskPDF
Mar 2, 2026

Position: Modular Memory is the Key to Continual Learning Agents

Foundation models have transformed machine learning through large-scale pretraining and increased test-time compute. Despite surpassing human performance in several domains, these models remain fundamentally limited in continuous operation, experience accumulation, and personalization, capabilities that are central to adaptive intelligence. While continual learning research has long targeted these goals, its historical focus on in-weight learning (IWL), i.e., updating a single model's parameters to absorb new knowledge, has rendered catastrophic forgetting a persistent challenge. Our position is that combining the strengths of In-Weight Learning (IWL) and the newly emerged capabilities of In-Context Learning (ICL) through the design of modular memory is the missing piece for continual adaptation at scale. We outline a conceptual framework for modular memory-centric architectures that leverage ICL for rapid adaptation and knowledge accumulation, and IWL for stable updates to model capabilities, charting a practical roadmap toward continually learning agents.

Vaggelis Dorovatas, Malte Schwerin, Andrew D. Bagdanov +21

Toyota Motor Europe · University of Bremen · University of Florence +17

Continual Learning for LLM AgentsMemory-Augmented Agents
AskPDF
Feb 25, 2026

Help Without Being Asked: A Deployed Proactive Agent System for On-Call Support with Continuous Self-Improvement

In large-scale cloud service platforms, thousands of customer tickets are generated daily and are typically handled through on-call dialogues. This high volume of on-call interactions imposes a substantial workload on human support analysts. Recent studies have explored reactive agents that leverage large language models as a first line of support to interact with customers directly and resolve issues. However, when issues remain unresolved and are escalated to human support, these agents are typically disengaged. As a result, they cannot assist with follow-up inquiries, track resolution progress, or learn from the cases they fail to address. In this paper, we introduce Vigil, a novel proactive agent system designed to operate throughout the entire on-call life-cycle. Unlike reactive agents, Vigil focuses on providing assistance during the phase in which human support is already involved. It integrates into the dialogue between the customer and the analyst, proactively offering assistance without explicit user invocation. Moreover, Vigil incorporates a continuous self-improvement mechanism that extracts knowledge from human-resolved cases to autonomously update its capabilities. Vigil has been deployed on Volcano Engine, ByteDance's cloud platform, for over ten months, and comprehensive evaluations based on this deployment demonstrate its effectiveness and practicality. The open source version of this work is publicly available at https://github.com/volcengine/veaiops.

Fengrui Liu, Xiao He, Tieying Zhang

ByteDance Beijing, China · ByteDance Hangzhou, China · ByteDance San Jose, United States

Proactive AssistanceCustomer Support AutomationLLM Agent Self-ImprovementContinual Learning for LLM Agents
AskPDF
Feb 25, 2026

Your Code Agent Can Grow Alongside You with Structured Memory

While "Intent-oriented programming" (or "Vibe Coding") redefines software engineering, existing code agents remain tethered to static code snapshots. Consequently, they struggle to model the critical information embedded in the temporal evolution of projects, failing to leverage the "reasoning trajectories" implicit in past successful practices. This limitation results in rigid behavioral logic and a lack of autonomous adaptability, ultimately hindering their ability to tackle complex, repository-level problems. To bridge this static-dynamic mismatch, we propose MemCoder, a framework designed to enable continual human-AI co-evolution. MemCoder first structures historical human experience to distill latent intent-to-code mappings from past commits. It then employs a self-refinement mechanism driven by verification feedback to correct agent behavior in real-time. Crucially, an experience self-internalization mechanism is introduced to crystallize human-validated solutions into long-term knowledge, thereby supporting sustained evolution. Experimental results on SWE-bench Verified demonstrate that MemCoder not only achieves State-of-the-Art (SOTA) performance but also delivers a 9.4% improvement in resolved rate over the general foundation model DeepSeek-V3.2. These findings indicate that equipping agents with the capability to co-evolve with humans via project history and real-time feedback effectively unlocks the potential of general models in complex software engineering tasks.

Yi-Xuan Deng, Xiaoqin Liu, Yi Zhang +2

Tsinghua University · Intern at Proxseer Inc · Proxseer Inc.

Software Engineering AgentsMemory-Augmented AgentsSelf-Improving AgentsContinual Learning for LLM Agents
AskPDF
Jan 26, 2026

Just-In-Time Reinforcement Learning: Continual Learning in LLM Agents Without Gradient Updates

While Large Language Model (LLM) agents excel at general tasks, they inherently struggle with continual adaptation due to the frozen weights after deployment. Conventional reinforcement learning (RL) offers a solution but incurs prohibitive computational costs and the risk of catastrophic forgetting. We introduce Just-In-Time Reinforcement Learning (JitRL), a training-free framework that enables test-time policy optimization without any gradient updates. JitRL maintains a dynamic, non-parametric memory of experiences and retrieves relevant trajectories to estimate action advantages on-the-fly. These estimates are then used to directly modulate the LLM's output logits. We theoretically prove that this additive update rule is the exact closed-form solution to the KL-constrained policy optimization objective. Extensive experiments on WebArena and Jericho demonstrate that JitRL establishes a new state-of-the-art among training-free methods. Crucially, JitRL outperforms the performance of computationally expensive fine-tuning methods (e.g., WebRL) while reducing monetary costs by over 30 times, offering a scalable path for continual learning agents. The code is available at https://github.com/liushiliushi/JitRL.

Yibo Li, Zijie Lin, Ailin Deng +5

National University of Singapore, Singapore.

Continual Learning for LLM AgentsReinforcement LearningTest-Time RLPolicy LearningRL for LLM AgentsContinual RL+1
AskPDF
Jan 18, 2026

A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agents

Reasoning is a fundamental cognitive process underlying inference, problem-solving, and decision-making. While large language models (LLMs) demonstrate strong reasoning capabilities in closed-world settings, they struggle in open-ended and dynamic environments. Agentic reasoning marks a paradigm shift by reframing LLMs as autonomous agents that plan, act, and learn through continual interaction. In this survey, we organize agentic reasoning along three complementary dimensions. First, we characterize environmental dynamics through three layers: foundational agentic reasoning, which establishes core single-agent capabilities including planning, tool use, and search in stable environments; self-evolving agentic reasoning, which studies how agents refine these capabilities through feedback, memory, and adaptation; and collective multi-agent reasoning, which extends intelligence to collaborative settings involving coordination, knowledge sharing, and shared goals. Across these layers, we distinguish in-context reasoning, which scales test-time interaction through structured orchestration, from post-training reasoning, which optimizes behaviors via reinforcement learning and supervised fine-tuning. We further review representative agentic reasoning frameworks across real-world applications and benchmarks, including science, robotics, healthcare, autonomous research, and mathematics. This survey synthesizes agentic reasoning methods into a unified roadmap bridging thought and action, and outlines open challenges and future directions, including personalization, long-horizon interaction, world modeling, scalable multi-agent training, and governance for real-world deployment.

Tianxin Wei, Ting-Wei Li, Zhining Liu +26

University of Illinois Urbana-Champaign · Meta · UCSD +2

Continual Learning for LLM AgentsMulti-Agent ReasoningAgentic AI
AskPDF
Jan 7, 2026

Evolving Programmatic Skill Networks

We study continual skill acquisition in open-ended embodied environments where an agent must construct, refine, and reuse an expanding library of executable skills. We introduce the Programmatic Skill Network (PSN), a framework in which skills are executable symbolic programs forming a compositional network that evolves through experience. PSN defines three core mechanisms instantiated via large language models: (1)~\opreflect for structured fault localization over skill compositions, (2)~progressive optimization with maturity-aware update gating that stabilizes reliable skills while maintaining plasticity for uncertain ones, and (3)~canonical structural refactoring under rollback validation that maintains network compactness. We further show that PSN's learning dynamics exhibit structural parallels to neural network training. Experiments on MineDojo and Crafter demonstrate robust skill reuse, rapid adaptation, and strong generalization across open-ended task distributions.

Haochen Shi, Xingdi Yuan, Bang Liu

DIRO & Institut Courtois, Université de Montréal · Mila – Québec AI Institute · Microsoft Research +1

Continual Learning for LLM AgentsLLM-Based Program SynthesisAgent Skill Learning
AskPDF
Feb 3, 2025

Memento No More: Coaching AI Agents to Master Multiple Tasks via Hints Internalization

As the general capabilities of artificial intelligence (AI) agents continue to evolve, their ability to learn to master multiple complex tasks through experience remains a key challenge. Current LLM agents, particularly those based on proprietary language models, typically rely on prompts to incorporate knowledge about the target tasks. This approach does not allow the agent to internalize this information and instead relies on ever-expanding prompts to sustain its functionality in diverse scenarios. This resembles a system of notes used by a person affected by anterograde amnesia, the inability to form new memories. In this paper, we propose a novel method to train AI agents to incorporate knowledge and skills for multiple tasks without the need for either cumbersome note systems or prior high-quality demonstration data. Our approach employs an iterative process where the agent collects new experiences, receives corrective feedback from humans in the form of hints, and integrates this feedback into its weights via a context distillation training procedure. We demonstrate the efficacy of our approach by implementing it in a Llama-3-based agent that, after only a few rounds of feedback, outperforms advanced models GPT-4o and DeepSeek-V3 in tasksets requiring correct sequencing of information retrieval, tool use, and question answering.

Minttu Alakuijala, Ya Gao, Georgy Ananov +4

Department of Computer Science, Aalto University · Department of Computer Science, University of Manchester · System 2 AI

Continual Learning for LLM AgentsLLM Agent Skill LearningContext Distillation
AskPDF