Continual Harness automates online self-improvement for foundation-model embodied agents by refining prompts, sub-agents, skills, and memory within one run, cutting button-press costs on Pokemon Red and Emerald and closing much of the gap to expert harnesses.
super hub Canonical reference
Voyager: An Open-Ended Embodied Agent with Large Language Models
Canonical reference. 94% of citing Pith papers cite this work as background.
355
Pith papers citing it
Background
94% of classified citations
abstract
We introduce Voyager, the first LLM-powered embodied lifelong learning agent in Minecraft that continuously explores the world, acquires diverse skills, and makes novel discoveries without human intervention. Voyager consists of three key components: 1) an automatic curriculum that maximizes exploration, 2) an ever-growing skill library of executable code for storing and retrieving complex behaviors, and 3) a new iterative prompting mechanism that incorporates environment feedback, execution errors, and self-verification for program improvement. Voyager interacts with GPT-4 via blackbox queries, which bypasses the need for model parameter fine-tuning. The skills developed by Voyager are temporally extended, interpretable, and compositional, which compounds the agent's abilities rapidly and alleviates catastrophic forgetting. Empirically, Voyager shows strong in-context lifelong learning capability and exhibits exceptional proficiency in playing Minecraft. It obtains 3.3x more unique items, travels 2.3x longer distances, and unlocks key tech tree milestones up to 15.3x faster than prior SOTA. Voyager is able to utilize the learned skill library in a new Minecraft world to solve novel tasks from scratch, while other techniques struggle to generalize. We open-source our full codebase and prompts at https://voyager.minedojo.org/.
hub tools
citation-role summary
background 59
method 2
dataset 1
other 1
citation-polarity summary
claims ledger
- abstract We introduce Voyager, the first LLM-powered embodied lifelong learning agent in Minecraft that continuously explores the world, acquires diverse skills, and makes novel discoveries without human intervention. Voyager consists of three key components: 1) an automatic curriculum that maximizes exploration, 2) an ever-growing skill library of executable code for storing and retrieving complex behaviors, and 3) a new iterative prompting mechanism that incorporates environment feedback, execution errors, and self-verification for program improvement. Voyager interacts with GPT-4 via blackbox querie
authors
co-cited works
representative citing papers
Flame3D enables zero-shot compositional 3D scene reasoning by representing scenes as editable visual-textual memories exposed to agentic MLLMs through composable and synthesizable spatial tools.
ShadowMerge exploits relation-channel conflicts to poison graph-based agent memory, achieving 93.8% average attack success rate on Mem0 and real-world datasets while bypassing existing defenses.
The khipu problem frames a governance failure in distributed AI where interpretive continuity is lost even when traces remain, requiring infrastructure to preserve reading practices rather than only data retention.
SEVerA uses Formally Guarded Generative Models and a three-stage Search-Verification-Learning process to synthesize self-evolving agents that satisfy hard formal constraints while improving task performance.
ExCyTIn-Bench is the first benchmark of 7542 questions from Microsoft Sentinel threat investigation graphs, where the best LLM agent achieves a reward of 0.606.
Introduces bounded-memory testbed for LLM agents in Slay the Spire 2 where typed retrieval replaces accumulating context, with released trajectories showing skill layer raises wins from 3/10 to 6/10.
SOLAR is a learning-augmented policy for semantic cache replacement that achieves constant competitive ratio 3 and 5-75% gains over FIFO on retrieval workloads.
SkillComposer performs task-conditioned skill sequence prediction with a constrained autoregressive decoder to jointly output skill subset, count, and order, raising pass rates by 23.1 and 18.2 percentage points on two production coding agents over no-skill baselines.
Multi-agent LLM system Agora under Sealed Joint Search conditions produces +1.87 holdout Sharpe on CSI 1000 over a 91-day sealed period, exceeding the best baseline at +1.334 under favorable seed.
LLM agents often fail to abstain at the right time in uncertain multi-turn tasks, and the CONVOLVE context engineering method raises timely abstention rates on WebShop from 26.7 to 57.4 without parameter updates.
GILP trains a parameterized backbone for valid actions and state predictions, then uses a consistency gate with LLM drafts to reduce hallucinated-state rate from 0.176 to 0.035 on GPT-4o-mini while raising success from 0.668 to 0.838.
PreAct compiles successful agent executions into verifiable state-machine programs for 8.5-13x faster replay on repeated tasks, with an independent evaluator check before storing each program.
daVinci-kernel is a multi-agent RL system that co-evolves skill selection, policy generation, and summarization via shared LLM and REINFORCE to optimize GPU kernels, reporting higher KernelBench scores than prior RL models.
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.
PhysAgent is a simulator-in-the-loop multi-agent system that automates physically grounded 4D synthesis from multimodal prompts by using trajectory feedback from vision models and LLM reasoning to optimize force fields.
PACE is a training-free anytime-valid commit gate using testing-by-betting e-processes that controls per-candidate false-commit probability for self-evolving agents and reduces spurious edits compared to greedy acceptance.
Rosetta Memory trains two profile-conditioned operators with a minimum-gain sampling curriculum and performance-gap reward to enable memory transfer between LLMs, showing gains on multi-hop QA benchmarks and robustness to unseen models.
LatentSkill uses a hypernetwork to generate LoRA adapters from textual skills, enabling weight-space storage that cuts prefill tokens and boosts agent success rates on ALFWorld and Search-QA.
VASO is a verification-guided self-evolution framework for LLM robot skill contracts that reaches 97.2% formal-specification compliance on Jackal and quadcopter tasks using under 100 samples.
Introduces APB benchmark with 4209 cases across 22 domains to diagnose planning in 12 MLLMs and shows it improves downstream execution when used for refinement.
AIP models skills as graphs of discrete steps connected by typed I/O edges under a validated schema, raising agent mean reward from 0.60 to 0.71 and pass rate from 53% to 67% on 27 SkillsBench tasks while enabling node-level fixes.
PersonaTree is a new hierarchical memory framework for persistent LLM agents that structures evidence into persona claims via support paths and outperforms baselines on six person-understanding benchmarks.
citing papers explorer
-
AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents
Introduces bounded-memory testbed for LLM agents in Slay the Spire 2 where typed retrieval replaces accumulating context, with released trajectories showing skill layer raises wins from 3/10 to 6/10.
-
AI Trading's Alpha Singularity: Emergent Market Reasoning through Agent-to-Agent Self-Evolution
Multi-agent LLM system Agora under Sealed Joint Search conditions produces +1.87 holdout Sharpe on CSI 1000 over a 91-day sealed period, exceeding the best baseline at +1.334 under favorable seed.
-
Agentic Abstention: Do Agents Know When to Stop Instead of Act?
LLM agents often fail to abstain at the right time in uncertain multi-turn tasks, and the CONVOLVE context engineering method raises timely abstention rates on WebShop from 26.7 to 57.4 without parameter updates.
-
Grounded Iterative Language Planning: How Parameterized World Models Reduce Hallucination Propagation in LLM Agents
GILP trains a parameterized backbone for valid actions and state predictions, then uses a consistency gate with LLM drafts to reduce hallucinated-state rate from 0.176 to 0.035 on GPT-4o-mini while raising success from 0.668 to 0.838.
-
PreAct: Computer-Using Agents that Get Faster on Repeated Tasks
PreAct compiles successful agent executions into verifiable state-machine programs for 8.5-13x faster replay on repeated tasks, with an independent evaluator check before storing each program.
-
Experience Makes Skillful: Enabling Generalizable Medical Agent Reasoning via Self-Evolving Skill Memory
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.
-
PACE: Anytime-Valid Acceptance Tests for Self-Evolving Agents
PACE is a training-free anytime-valid commit gate using testing-by-betting e-processes that controls per-candidate false-commit probability for self-evolving agents and reduces spurious edits compared to greedy acceptance.
-
AIP: A Graph Representation for Learning and Governing Agent Skills
AIP models skills as graphs of discrete steps connected by typed I/O edges under a validated schema, raising agent mean reward from 0.60 to 0.71 and pass rate from 53% to 67% on 27 SkillsBench tasks while enabling node-level fixes.
-
SMAC-Talk: A Natural Language Extension of the StarCraft Multi-Agent Challenge for Large Language Models
SMAC-Talk is a new benchmark that adds natural language messaging and deceptive-agent scenarios to SMAC for testing LLM coordination in multi-agent environments.
-
Handoff Debt: The Rediscovery Cost When Coding Agents Take Over Interrupted Tasks
An empirical protocol measures rediscovery costs when coding agents resume interrupted tasks and finds that context-bearing handoffs cut agent events 20-59% and tokens 42-63% versus repository-only handoffs across three models.
-
Model-Native Computing Architecture: Envisioning Future System Architecture Through the Lens of Computer Architecture
Proposes the Intelligent Computing Architecture (ICA) as a six-layer framework with dual probabilistic-deterministic planes and three Amdahl-style heuristics to unify design of LLM-based systems.
-
CORE: Contrastive Reflection Enables Rapid Improvements in Reasoning
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.
-
VitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User Interactions
VitaBench 2.0 introduces a benchmark for long-term personalized and proactive agent behavior, with results indicating substantial gaps in current frontier LLMs.
-
AGORA: Adapter-Grounded Observation-Action Retention for Inference-Free Prompt Compression in LLM Agents
AGORA is an inference-free step-level compressor for LLM agent prompts that retains at least 75% of uncompressed performance in most tested settings where token-level methods collapse due to action-grammar destruction.
-
PANDO: Efficient Multimodal AI Agents via Online Skill Distillation
PANDO introduces an online skill-distillation method with a structured library, reflection, demotion, routing, compression, and cache-aware prompting that reaches 58.3% success on 910 VisualWebArena tasks using 58-61% fewer tokens than prior methods.
-
Formal Skill: Programmable Runtime Skills for Efficient and Accurate LLM Agents
Proposes Formal Skill as a programmable runtime abstraction for LLM agents, implemented in open-source FairyClaw, achieving competitive Harness-Bench scores with substantially fewer tokens.
-
Library Drift: Diagnosing and Fixing a Silent Failure Mode in Self-Evolving LLM Skill Libraries
The paper diagnoses library drift in self-evolving LLM skill libraries and demonstrates a governance recipe raising pass@1 from 0.258 to 0.584 on MBPP+ hard-100.
-
DecisionBench: A Benchmark for Emergent Delegation in Long-Horizon Agentic Workflows
DecisionBench supplies a fixed task suite, model pool, delegation interface, and multi-axis metrics to evaluate emergent delegation, showing similar quality across awareness conditions but 15-31 point headroom under perfect delegation.
-
EXG: Self-Evolving Agents with Experience Graphs
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.
-
Baba in Wonderland: Online Self-Supervised Dynamics Discovery for Executable World Models
Alice uses preservation conflicts from failed candidate updates to create class-stratified hypotheses and guide exploration, improving executable world-model learning under prior misalignment.
-
X-SYNTH: Beyond Retrieval -- Enterprise Context Synthesis from Observed Digital Human Attention
X-SYNTH synthesizes enterprise context from digital human attention using Digital Twin Signatures and seven attention filters, raising true lead rate from 9.5% to 61.9% while cutting false lead rate to 18.8%.
-
RS-Claw: Progressive Active Tool Exploration via Hierarchical Skill Trees for Remote Sensing Agents
RS-Claw enables remote sensing agents to actively explore tools via hierarchical skill trees, achieving up to 86% token compression and outperforming flat registration and RAG baselines on Earth-Bench.
-
State-Centric Decision Process
SDP constructs a task-induced state space from raw text by having agents commit to and certify natural-language predicates as states, enabling structured planning and analysis in unstructured language environments.
-
SkillSmith: Compiling Agent Skills into Boundary-Guided Runtime Interfaces
SkillSmith is a boundary-first compiler-runtime system that turns skill packages into minimal executable interfaces, cutting token usage 57%, thinking iterations 43%, and solve time 51% versus raw skill injection on SkillsBench.
-
Do Vision-Language-Models show human-like logical problem-solving capability in point and click puzzle games?
VLATIM benchmark reveals large VLMs excel at high-level planning in physics puzzles but struggle with precise visual grounding and mouse control, so they lack human-like problem-solving capabilities.
-
MAGE: Multi-Agent Self-Evolution with Co-Evolutionary Knowledge Graphs
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.
-
TimeClaw: A Time-Series AI Agent with Exploratory Execution Learning
TimeClaw is an exploratory execution learning system that turns multiple valid tool-use paths into hierarchical distilled experience for improved time-series reasoning without test-time adaptation.
-
EquiMem: Calibrating Shared Memory in Multi-Agent Debate via Game-Theoretic Equilibrium
EquiMem calibrates shared memory in multi-agent debate by computing a game-theoretic equilibrium from agent queries and paths, outperforming heuristics and LLM validators across benchmarks while remaining robust to adversarial agents.
-
FORTIS: Benchmarking Over-Privilege in Agent Skills
FORTIS benchmark shows over-privilege is the norm in LLM agent skill selection and execution, with models reaching for higher-privilege skills and tools than required across ten frontier models and three domains.
-
RewardHarness: Self-Evolving Agentic Post-Training
RewardHarness self-evolves a tool-and-skill library from 100 preference examples to reach 47.4% accuracy on image-edit evaluation, beating GPT-5, and yields stronger RL-tuned models.
-
Tools as Continuous Flow for Evolving Agentic Reasoning
FlowAgent models tool chaining as continuous latent trajectory generation with conditional flow matching to deliver global planning, formal utility bounds, and better robustness on long-horizon tasks, plus a new plan-level benchmark.
-
When Stored Evidence Stops Being Usable: Scale-Conditioned Evaluation of Agent Memory
A new evaluation protocol shows agent memory reliability degrades variably with added irrelevant sessions depending on agent, memory interface, and scale.
-
Towards Autonomous Business Intelligence via Data-to-Insight Discovery Agent
AIDA is the first end-to-end autonomous agent that combines a domain-specific language with Pareto-guided reinforcement learning to discover insights from complex business data.
-
Agentick: A Unified Benchmark for General Sequential Decision-Making Agents
Agentick is a new benchmark for sequential decision-making agents that evaluates RL, LLM, VLM, hybrid, and human approaches across 37 tasks and finds no single method dominates.
-
SkillRet: A Large-Scale Benchmark for Skill Retrieval in LLM Agents
SkillRet benchmark shows fine-tuned retrievers improve NDCG@10 by 13+ points over prior models on large-scale skill retrieval for LLM agents.
-
More Is Not Always Better: Cross-Component Interference in LLM Agent Scaffolding
Full factorial testing of five LLM agent components reveals that the complete 'All-In' combination is consistently outperformed by smaller subsets due to cross-component interference, with optimal subsets being task- and scale-dependent.
-
Inference-Time Budget Control for LLM Search Agents
A VOI-based controller for dual inference budgets improves multi-hop QA performance by prioritizing search actions and selectively finalizing answers.
-
Belief Memory: Agent Memory Under Partial Observability
BeliefMem is a probabilistic memory architecture for LLM agents that retains multiple candidate conclusions with probabilities updated by Noisy-OR, achieving superior average performance over deterministic baselines on LoCoMo and ALFWorld.
-
Co-Evolving LLM Decision and Skill Bank Agents for Long-Horizon Tasks
COSPLAY co-evolves an LLM decision agent with a skill bank agent to improve long-horizon game performance, reporting over 25.1% average reward gains versus frontier LLM baselines on single-player benchmarks.
-
AI scientists produce results without reasoning scientifically
LLM agents execute scientific tasks but fail to follow core scientific reasoning norms such as evidence consideration and belief revision based on refutations.
-
Exploration and Exploitation Errors Are Measurable for Language Model Agents
A policy-agnostic metric and controllable 2D grid environments with task DAGs enable measurement of exploration and exploitation errors in language model agents from observed actions.
-
ROZA Graphs: Self-Improving Near-Deterministic RAG through Evidence-Centric Feedback
ROZA graphs enable self-improving RAG by storing evidence-specific reasoning chains, yielding up to 10.6pp accuracy gains and 46% lower cost through graph traversal feedback.
-
GUIDE: Interpretable GUI Agent Evaluation via Hierarchical Diagnosis
GUIDE decomposes GUI agent evaluation into trajectory segmentation, subtask diagnosis, and overall summary to deliver higher accuracy and structured error reports than holistic baselines.
-
SKILLFOUNDRY: Building Self-Evolving Agent Skill Libraries from Heterogeneous Scientific Resources
SkillFoundry mines heterogeneous scientific resources into a self-evolving library of validated agent skills, with 71.1% novelty versus prior libraries and measurable gains on coding benchmarks plus two genomics tasks.
-
C-TRAIL: A Commonsense World Framework for Trajectory Planning in Autonomous Driving
C-TRAIL combines LLM commonsense with a dual-trust mechanism and Dirichlet-weighted Monte Carlo Tree Search to improve trajectory planning accuracy and safety in autonomous driving.
-
Episodic-to-Semantic Consolidation Without Identity Drift
A deterministic episodic-to-semantic consolidation function with a structural lemma proving identity invariance, demonstrated in synthetic experiments on an embodied service agent.
-
Repair the Amplifier, Not the Symptom: Stable World-Model Correction for Agent Rollouts
WM-SAR identifies and repairs causal subgraphs that amplify errors in agent planning graphs, outperforming symptom-scanning LLM correctors under token constraints.
-
COMFYCLAW: Self-Evolving Skill Harnesses for Image Generation Workflows
COMFYCLAW introduces skill evolution via graph editing, automatic reversion, VLM verification, and distillation of runs into reusable Agent Skills, achieving higher average scores than a verifier-only baseline across benchmarks.
-
OPINE-World: Programmatic World Modeling with Ontology-error-Prioritized Interactive Exploration
OPINE-World learns programmatic world models from interaction using dual LLM agents and ontology-error exploration, solving 20 of 25 ARC-AGI-3 games without per-game training.
-
AutoMem: Automated Learning of Memory as a Cognitive Skill
AutoMem automates memory structure revision and proficiency training in LLMs, delivering 2x-4x performance gains on long-horizon games without altering task-action behavior.