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. 93% of citing Pith papers cite this work as background.
232
Pith papers citing it
Background
93% 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 57
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.
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.
MobiBench is the first modular multi-path offline benchmark for mobile GUI agents, achieving 94.72% agreement with human evaluators while allowing component-level analysis.
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.
Boiling the Frog is a new stateful multi-turn benchmark that finds an aggregate 44.4% strict attack success rate for incremental safety violations across nine AI models, with rates ranging from 20.5% to 92.9%.
GraphFlow uses a unified wGraph to dynamically instantiate workflows and manage KV caches for LLM agents, reporting 4.95 pp average gains and 4x memory reduction on five benchmarks.
MemGym unifies agent gyms into a memory benchmark with isolated scoring across tool-use, research, coding, and computer-use regimes plus a lightweight reward model for tractable coding evaluation.
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.
Identifies library drift as a failure mode in self-evolving LLM skill libraries and shows a governance recipe improves pass@1 from 0.258 to 0.584 on MBPP+ hard-100.
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 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.
LLM societies in Nomic show non-monotonic collective adaptation peaking at mid-scales, with smaller models rule-inert and larger ones restrictive.
MasFACT transfers historical topology priors across tasks via Fused Gromov-Wasserstein optimal transport and PAC-Bayes conservative adaptation to reduce topology forgetting in continual multi-agent settings.
SkillTTA synthesizes temporary task-specific skills from retrieved training trajectories to boost LLM agent Pass@1 scores on SpreadsheetBench and BigCodeBench without parameter updates.
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 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%.
MemDocAgent generates consistent hierarchical repository-level code documentation by combining dependency-aware traversal with memory-guided agent interactions that accumulate work traces.
ASH reaches 11.2/12 milestones in Pokemon Emerald and 9.9/12 in Zelda by self-improving via an IDM trained on its own trajectories to label internet video, while baselines plateau at roughly 6/12.
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.
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 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.
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.
citing papers explorer
-
Continual Harness: Online Adaptation for Self-Improving Foundation Agents
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.
-
Flame3D: Zero-shot Compositional Reasoning of 3D Scenes with Agentic Language Models
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: A Novel Poisoning Attack on Graph-Based Agent Memory via Relation-Channel Conflicts
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.
-
SEVerA: Verified Synthesis of Self-Evolving Agents
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.
-
MobiBench: Multi-Branch, Modular Benchmark for Mobile GUI Agents
MobiBench is the first modular multi-path offline benchmark for mobile GUI agents, achieving 94.72% agreement with human evaluators while allowing component-level analysis.
-
ExCyTIn-Bench: Evaluating LLM agents on Cyber Threat Investigation
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.
-
Boiling the Frog: A Multi-Turn Benchmark for Agentic Safety
Boiling the Frog is a new stateful multi-turn benchmark that finds an aggregate 44.4% strict attack success rate for incremental safety violations across nine AI models, with rates ranging from 20.5% to 92.9%.
-
GraphFlow: A Graph-Based Workflow Management for Efficient LLM-Agent Serving
GraphFlow uses a unified wGraph to dynamically instantiate workflows and manage KV caches for LLM agents, reporting 4.95 pp average gains and 4x memory reduction on five benchmarks.
-
MemGym: a Long-Horizon Memory Environment for LLM Agents
MemGym unifies agent gyms into a memory benchmark with isolated scoring across tool-use, research, coding, and computer-use regimes plus a lightweight reward model for tractable coding evaluation.
-
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
Identifies library drift as a failure mode in self-evolving LLM skill libraries and shows a governance recipe improves 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.
-
Scale-Dependent Collective Adaptation in Self-Amending LLM Societies: A Cross-Family Study of Emergent Governance
LLM societies in Nomic show non-monotonic collective adaptation peaking at mid-scales, with smaller models rule-inert and larger ones restrictive.
-
\textsc{MasFACT}: Continual Multi-Agent Topology Learning via Geometry-Aware Posterior Transfer
MasFACT transfers historical topology priors across tasks via Fused Gromov-Wasserstein optimal transport and PAC-Bayes conservative adaptation to reduce topology forgetting in continual multi-agent settings.
-
Skills on the Fly: Test-Time Adaptive Skill Synthesis for LLM Agents
SkillTTA synthesizes temporary task-specific skills from retrieved training trajectories to boost LLM agent Pass@1 scores on SpreadsheetBench and BigCodeBench without parameter updates.
-
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%.
-
Remember Your Trace: Memory-Guided Long-Horizon Agentic Framework for Consistent and Hierarchical Repository-Level Code Documentation
MemDocAgent generates consistent hierarchical repository-level code documentation by combining dependency-aware traversal with memory-guided agent interactions that accumulate work traces.
-
ASH: Agents that Self-Hone via Embodied Learning
ASH reaches 11.2/12 milestones in Pokemon Emerald and 9.9/12 in Zelda by self-improving via an IDM trained on its own trajectories to label internet video, while baselines plateau at roughly 6/12.
-
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.
-
Skill Drift Is Contract Violation: Proactive Maintenance for LLM Agent Skill Libraries
SkillGuard extracts executable environment contracts from LLM skill documents to detect only relevant drifts, reporting zero false positives on 599 cases, 100% precision in known-drift tests, and raising one-round repair success from 10% to 78%.
-
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.
-
MemCompiler: Compile, Don't Inject -- State-Conditioned Memory for Embodied Agents
MemCompiler reframes memory use as state-conditioned compilation, delivering relevant guidance via text and latent channels to improve embodied agent performance up to 129% and cut latency 60% versus static injection.
-
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.
-
ReaComp: Compiling LLM Reasoning into Symbolic Solvers for Efficient Program Synthesis
LLM reasoning traces can be compiled into reusable symbolic solvers that achieve high accuracy on program synthesis benchmarks at zero inference cost and transfer to other domains.
-
SADE: Symptom-Aware Diagnostic Escalation for LLM-Based Network Troubleshooting
SADE encodes a Cisco-style phase-gated diagnostic policy into LLM agents, delivering a 37-point root-cause F1 gain on the NIKA benchmark with 22 points attributable to the policy itself.
-
Theory Under Construction: Orchestrating Language Models for Research Software Where the Specification Evolves
Comet-H orchestrates LLMs via deficit-scoring prompt selection and half-life task tracking to co-evolve research software components, demonstrated by a static analysis tool reaching F1=0.768 versus a 0.364 baseline.
-
Atomic-Probe Governance for Skill Updates in Compositional Robot Policies
A cross-version swap protocol reveals dominant skills that swing composition success by up to 50 percentage points, and an atomic probe with selective revalidation governs updates at lower cost than always re-testing full compositions.
-
Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses
AHE automates coding-agent harness evolution via component, experience, and decision observability, raising Terminal-Bench 2 pass@1 from 69.7% to 77.0% with cross-benchmark and cross-model transfer.
-
Cutscene Agent: An LLM Agent Framework for Automated 3D Cutscene Generation
Cutscene Agent uses a multi-agent LLM system and a new toolkit for game engine control to automate end-to-end 3D cutscene generation, evaluated on the introduced CutsceneBench.
-
Skill Retrieval Augmentation for Agentic AI
Introduces the SRA paradigm and SRA-Bench benchmark showing retrieval-based skill augmentation improves agent performance but skill incorporation remains a bottleneck regardless of retrieval quality.
-
Measuring the Unmeasurable: Markov Chain Reliability for LLM Agents
TraceToChain models LLM agent traces as absorbing DTMCs using automatic clustering and smoothed MLE, with KS and AIC validation, to reconcile pass@k, pass^k, and RDC as projections of a single first-passage success-time distribution.
-
A Systematic Survey of Security Threats and Defenses in LLM-Based AI Agents: A Layered Attack Surface Framework
A new 7x4 taxonomy organizes agentic AI security threats by architectural layer and persistence timescale, revealing under-explored upper layers and missing defenses after surveying 116 papers.
-
AEL: Agent Evolving Learning for Open-Ended Environments
AEL uses a fast-timescale bandit for memory policy selection and slow-timescale LLM reflection for causal insights, achieving a Sharpe ratio of 2.13 on a 208-episode portfolio benchmark while showing that added mechanisms degrade performance.
-
The Platform Is Mostly Not a Platform: Token Economies and Agent Discourse on Moltbook
Moltbook operates as two largely separate layers: a dominant transactional token economy using protocols like MBC-20 and a thinner discursive conversation layer with only 3.6% agent overlap.