REVIEW 29 cited by
LifelongAgentBench: Evaluating LLM Agents as Lifelong Learners
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
LifelongAgentBench: Evaluating LLM Agents as Lifelong Learners
read the original abstract
Lifelong learning is essential for intelligent agents operating in dynamic environments. Current large language model (LLM)-based agents, however, remain stateless and unable to accumulate or transfer knowledge over time. Existing benchmarks treat agents as static systems and fail to evaluate lifelong learning capabilities. We present LifelongAgentBench, the first unified benchmark designed to systematically assess the lifelong learning ability of LLM agents. It provides skill-grounded, interdependent tasks across three interactive environments, Database, Operating System, and Knowledge Graph, with automatic label verification, reproducibility, and modular extensibility. Extensive experiments reveal that conventional experience replay has limited effectiveness for LLM agents due to irrelevant information and context length constraints. We further introduce a group self-consistency mechanism that significantly improves lifelong learning performance. We hope LifelongAgentBench will advance the development of adaptive, memory-capable LLM agents.
Forward citations
Cited by 29 Pith papers
-
Continual Learning Bench: Evaluating Frontier AI Systems in Real-World Stateful Environments
CL-Bench is the first expert-validated benchmark for continual learning in frontier LLMs across six real-world domains, showing limited gains and that naive in-context learning outperforms dedicated memory systems.
-
EdgeBench: Unveiling Scaling Laws of Learning from Real-World Environments
Across ~38,000 hours on 134 ultra-long real-world tasks, aggregate agent performance follows a log-sigmoid of interaction time, and measured learning speed doubles about every three months.
-
GateMem: Benchmarking Memory Governance in Multi-Principal Shared-Memory Agents
GateMem benchmark shows no existing memory method for LLM agents achieves strong utility, access control, and reliable forgetting simultaneously in multi-principal shared settings.
-
M$^3$Eval: Multi-Modal Memory Evaluation through Cognitively-Grounded Video Tasks
M³Eval is a new cognitively-grounded benchmark that evaluates memory dimensions in multi-modal video models and reports consistent model weaknesses in disentanglement, interference, spatial-temporal grounding, and sym...
-
Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory
Evo-Memory is a new benchmark for self-evolving memory in LLM agents across task streams, with baseline ExpRAG and proposed ReMem method that integrates reasoning, actions, and memory updates for continual improvement.
-
Progressive Multimodal Alignment for Continual Instruction Tuning
Adding distribution-shift-triggered projector experts, mixed by a router and anchored by the frozen pretrained projector, improves multimodal continual instruction tuning accuracy and reduces forgetting.
-
SkillRise: Agentic Reinforcement Learning for Cross-Task Skill Evolution
A single RL policy alternating task solving and skill-document curation, with decoupled cross-task credit, improves Pass@1 and cross-task test-time scaling on ALFWorld, WebShop, and ScienceWorld.
-
Are We Ready For An Agent-Native Memory System?
A four-module framework is used to benchmark 12 agent memory systems, showing no architecture dominates and that workload alignment plus localized maintenance drive performance and cost.
-
From Player to Master: Enhancing Test-Time Learning of LLM Agents via Reinforcement Learning over Memory
MemoPilot trains memory updates for LLM agents via multi-turn GRPO on RPS and poker, achieving top Elo scores and outperforming baselines including DeepSeek-V3.2.
-
Bayesian-Agent: Posterior-Guided Skill Evolution for LLM Agent Harnesses
Bayesian-Agent maintains feature-conditioned categorical posteriors over skills/SOPs from verified trajectories and maps them to actions that improve benchmark scores on SOP-Bench, Lifelong AgentBench, and RealFin-Bench.
-
Learning While Acting: A Skill-Enhanced Test-Time Co-Evolution Framework for Online Lifelong Learning Agents
LifeSkill is a verifier-guided skill learning plus online internalization framework that raises average performance by 7 points over lifelong agent baselines on LifelongAgentBench.
-
Mem-$\pi$: Adaptive Memory through Learning When and What to Generate
Mem-π is a framework using a dedicated model and decision-content decoupled RL to generate context-specific guidance on demand for LLM agents, outperforming retrieval baselines by over 30% on web navigation.
-
GenericAgent: A Token-Efficient Self-Evolving LLM Agent via Contextual Information Density Maximization (V1.0)
GenericAgent outperforms other LLM agents on long-horizon tasks by maximizing context information density with fewer tokens via minimal tools, on-demand memory, trajectory-to-SOP evolution, and compression.
-
LLMs Corrupt Your Documents When You Delegate
LLMs corrupt an average of 25% of document content during long delegated editing workflows across 52 domains, even frontier models, and agentic tools do not mitigate the issue.
-
Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory
Evo-Memory is a new streaming benchmark and evaluation framework for self-evolving memory in LLM agents, unifying over ten memory modules and introducing the ReMem pipeline for continual improvement on multi-turn and ...
-
MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation
A skill-lifecycle agent (create, memory, manage, evaluate, refine) beats Hermes, Codex, and Claude Code on SkillsBench/SkillLearnBench and transfers skills better.
-
Progressive Multimodal Alignment for Continual Instruction Tuning
Progressive Multimodal Alignment expands projector experts only when multimodal distribution shifts are detected, reducing projector-level forgetting and boosting MCIT baselines with sub-linear growth.
-
Rethinking Self-Evolution: A Constrained Exploration-Exploitation Process for Mitigating Skill Overfitting
SkillBoost reduces skill overfitting in self-evolving LLM agents by combining failure-localized editing, multi-candidate generation, and an anti-regression acceptance gate.
-
Always-OnAgents:A Survey of Persistent Memory, State, and Governance in LLMAgents
Survey mapping persistent state in LLM agents along six axes and proposing the AOEP-v0 protocol to evaluate governance and recovery obligations.
-
Tree-of-Experience: A Structured Experience-Management Solution for Self-Evolving Agents under Low-Repetition and Implicit-Reward Environments
Introduces FinEvolveBench and Tree-of-Experience showing structured experience management improves LLM agent performance over baselines in low-repetition implicit-reward settings.
-
AgentCL: Toward Rigorous Evaluation of Continual Learning in Language Agents
AgentCL constructs controlled task streams with intentional reusability and introduces MemProbe to evaluate non-parametric memory designs for continual learning in language agents across coding, research, and reasoning tasks.
-
MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation
MUSE-Autoskill introduces a skill-centric framework for self-evolving LLM agents through a unified lifecycle of skill creation, memory, management, evaluation, and refinement.
-
AlphaMemo: Structured Search-Process Memory for Self-Evolving Alpha Mining Agents
AlphaMemo equips LLM alpha-mining agents with AST-diff motif memory, residual learning, and asymmetric veto control to improve out-of-sample factor discovery on CSI 500 and S&P 500.
-
MINTEval: Evaluating Memory under Multi-Target Interference in Long-Horizon Agent Systems
MINTEval benchmark shows current memory-augmented systems average 27.9% accuracy on long-horizon interference tasks, limited by retrieval and memory construction with degradation from intervening updates.
-
Learning CLI Agents with Structured Action Credit under Selective Observation
CLI agents trained with RL benefit from selective observation via σ-Reveal and structured credit assignment via A³ that leverages AST action sub-chains and trajectory margins.
-
From Agent Loops to Deterministic Graphs: Execution Lineage for Reproducible AI-Native Work
Execution lineage models AI-native work as a DAG of computations with explicit dependencies, achieving perfect state preservation in controlled update tasks where loop-based agents introduce churn and contamination.
-
Scaling Teams or Scaling Time? Memory Enabled Lifelong Learning in LLM Multi-Agent Systems
LLMA-Mem improves long-horizon performance in LLM multi-agent systems over baselines while reducing cost and shows non-monotonic scaling where memory-enabled smaller teams can beat larger ones.
-
Evaluation of ML Resource Utilization Requires Model Life Cycle Assessment
The paper calls for life cycle assessment to capture embodied hardware costs and full pipeline operational costs in AI development and deployment.
-
A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence
The paper delivers the first systematic review of self-evolving agents, structured around what components evolve, when adaptation occurs, and how it is implemented.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.