Prism-Shadow/awesome-rsi - 观星指南 Stargazers.cn

Find your next RSI paper — Explore the Awesome RSI website

Our survey

From Existing Methods to New Research Ideas: Two Perspectives on Recursive Self-Improvement

Survey overview: a tree connects agent resources, the RSI taxonomy, feedback-driven improvement, and insights from traditional deep learning.

A nine-dimension taxonomy of RSI methods and insights from traditional deep learning to inspire new research.

Watch the walkthrough · 1 min

https://github.com/user-attachments/assets/70f488af-925c-4b93-ba03-5c84711b8dbf

Start here

Awesome RSI collects benchmarks, methods, and systems for Recursive Self-Improvement. We follow the loop: an agent performs tasks, learns from trajectories and feedback, updates its own state, and uses that updated state in later work. That state can be model parameters, harness code, context, memory, or skills.

107 method papers · 33 benchmark papers · 3 systems

Looking for…	Start with…
An introduction to RSI	Understanding RSI — an illustrated guide, available in English and Chinese.
A method to build on	Methods & Systems — filter by artifacts, topology, feedback, and more.
A way to measure improvement	Benchmarks — compare artifacts and online, offline, or hybrid protocols.
Connections between papers	Citation graphs — switch between methods and benchmarks, search for a node, zoom, and pan.
More background	Books, courses, and learning materials.

Paper map

Each list in this README is organized along one dimension: RSI artifact for methods and systems, and RSI mode for benchmarks. For more ways to explore the collection, visit the Awesome RSI website, where you can compare additional dimensions and combine filters to find work that matches your interests.

What does the agent improve? The tree below follows the RSI artifact dimension.

Left-to-right paper tree: RSI artifact splits into Parametric and Non-parametric. Parametric covers model parameters; Non-parametric covers Harness code, Context, Memory, Skill, and Other artifacts. Each branch shows example papers. Open the full-size map for a closer look.

Model parameters · Harness code · Context · Memory · Skill · Other artifacts · Benchmarks

The tree shows examples from the collection. The lists below use the website's existing labels; a work can appear under multiple artifacts. Inclusion covers both explicit self-modification and experience-driven improvement during long-running tasks.

Methods & Systems

Compare all dimensions on the website →

Grouped by RSI artifact and ordered by first publication or project release date, newest first. Conference labels reflect the venue recorded in the collection; projects link to their repositories.

Model parameters

The student's model parameters are updated to improve task performance. This includes a teacher using student performance feedback to refine successive training rounds, even when each round restarts from the initial model, as well as the updated student continuing to learn from later tasks.

Paper or project	Publication
ReSAIL: Mitigating Collapse in Iterative Agent Self-Distillation	arXiv preprint
Gödel Forest: Balancing Search Depth and Breadth for Data-Centric Recursive Self-Improvement	arXiv preprint
Recursive Self-Improvement via On-Policy Distillation for Reasoning	arXiv preprint
TISD: On-Policy Self-Distillation with Trajectory Intervention	arXiv preprint
Experience Funnel: A State-Policy Alternating Loop for Self-Evolving Agents	arXiv preprint
NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness	arXiv preprint
RISE: Recursive Improvement via Self-Extrapolating Policy Distillation	arXiv preprint
Reef: Continual Learning Infrastructure for Self-Improving Agents	Project · v0.0.2
EnvHarness: Awakening Static Worlds for Agent Learning	arXiv preprint
HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry	arXiv preprint
ExpGraph: Model-Agnostic Experience Learning with Graph-Structured Memory for LLM Agents	arXiv preprint
Continual Harness: Online Adaptation for Self-Improving Foundation Agents	arXiv preprint
G-Zero: Self-Play for Open-Ended Generation from Zero Data	arXiv preprint
P²O: Joint Policy and Prompt Optimization	arXiv preprint
MM-Zero: Self-Evolving Multi-Model Vision Language Models From Zero Data	EMNLP 2026
TTCS: Test-Time Curriculum Synthesis for Self-Evolving	arXiv preprint
Guided Self-Evolving LLMs with Minimal Human Supervision	arXiv preprint
VisPlay: Self-Evolving Vision-Language Models from Images	CVPR 2026
R-Zero: Self-Evolving Reasoning LLM from Zero Data	ICLR 2026
Self-Adapting Language Models	NeurIPS 2025

Harness code

Executable agent, harness, control-flow, self-improvement, or tool code is modified.

Paper or project	Publication
MESH-Harness: Self-Improving Agent Harnesses via Bandit-Guided Compositional Evolution	arXiv preprint
Learning from Research: Toward Lifelong Agent Harness Evolution	arXiv preprint
MoMHa: Multi-Objective Optimization of LLM Harnesses over Accuracy, Safety, and Tokens	NeurIPS 2026
SkillEvoReg: Regularizing Agent Skill Evolution Against Overfitting	arXiv preprint
HarnessPAI: An Evolving Harness for Physical AI	arXiv preprint
Grow the Harness, Not the Context: From Strategy-Free Scaffolds to Reusable Specialist Agents	arXiv preprint
Harness as a Language: A Minimalist Agent Framework With Maximal Expressivity	arXiv preprint
Recursive self-improvement of AI research agents	arXiv preprint
Harness-Zero: Harness Distillation via Agent-as-Harness	arXiv preprint
RRSI: Regularized Recursive Self-Improvement of Agent Harnesses	arXiv preprint
Self Improvement via Fast Tree-search	arXiv preprint
SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness	arXiv preprint
EvoOntology: A Self-Evolving Ontology Layer for Data Agents	arXiv preprint
ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement	arXiv preprint
Dream-RSI: Recursive Self-Improvement through Evolving Worlds	Preprint
Ecdysis: Efficient and Effective Training of Runtime Harnesses for LLM Agents	arXiv preprint
SimSkill: A Self-Evolving LLM Agent for Skill and Knowledge Accumulation in Traffic Simulation	arXiv preprint
Reef: Continual Learning Infrastructure for Self-Improving Agents	Project · v0.0.2
HarnessEvolve: Learning from Reference Trajectories for Reliable Agent Self-Evolution	arXiv preprint
Proteus: A Harness-Agnostic Self-Evolution Framework for AI Agents	Project · v0.3.0
ForeDreamer: A Self-Evolving Dual-Agent Memory Architecture for Future Event Prediction	Findings of EMNLP 2026
Mendel Gödel Machine: Recursive Self-Improving Coding Agents via Comparative Evolution	arXiv preprint
EvolveNet: Collaborative Harness Evolution for Agent Self-Improvement	arXiv preprint
DarwinX: Evolving Agent Harnesses Through Natural Selection	arXiv preprint
HarnessBank: Semantic Gene-Bank Search with Gated Verification for Agent-Harness Self-Evolution	arXiv preprint
The Red Queen Gödel Machine: Co-Evolving Agents and Their Evaluators	arXiv preprint
HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry	arXiv preprint
Self-Harness: Harnesses That Improve Themselves	arXiv preprint
From Failed Trajectories to Reliable LLM Agents: Diagnosing and Repairing Harness Flaws	arXiv preprint
OpenSkill: Open-World Self-Evolution for LLM Agents	arXiv preprint
SkillSmith: Co-Evolving Skills and Tools for Self-Improving Agent Systems	arXiv preprint
PANDO: Efficient Multimodal AI Agents via Online Skill Distillation	arXiv preprint
DemoEvolve: Overcoming Sparse Feedback in Agentic Harness Evolution with Demonstrations	arXiv preprint
MOSS: Self-Evolution through Source-Level Rewriting in Autonomous Agent Systems	arXiv preprint
Continual Harness: Online Adaptation for Self-Improving Foundation Agents	arXiv preprint
LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling	arXiv preprint
Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses	arXiv preprint
Escher-Loop: Mutual Evolution by Closed-Loop Self-Referential Optimization	arXiv preprint
Mem²Evolve: Towards Self-Evolving Agents via Co-Evolutionary Capability Expansion and Experience Distillation	ACL 2026
Meta-Harness: End-to-End Optimization of Model Harnesses	arXiv preprint
Hyperagents	arXiv preprint
Group-Evolving Agents: Open-Ended Self-Improvement via Experience Sharing	arXiv preprint
Meta Context Engineering via Agentic Skill Evolution	ICML 2026
Huxley-Gödel Machine: Human-Level Coding Agent Development by an Approximation of the Optimal Self-Improving Machine	ICLR 2026 Oral
Darwin Gödel Machine: Open-Ended Evolution of Self-Improving Agents	ICLR 2026
Gödel Agent: A Self-Referential Agent Framework for Recursive Self-Improvement	ACL 2025

Context

Prompts or working context are updated. Observations, feedback, and experience can accumulate or be reorganized during a continuous run to guide later actions or tasks.

Paper or project	Publication
Learning from Revision Consequences: Hindsight Meta-Experience Distillation for Self-Improving Agents	arXiv preprint
EviSkill: Grounding Skill Evolution in Replayable Evidence	arXiv preprint
MESH-Harness: Self-Improving Agent Harnesses via Bandit-Guided Compositional Evolution	arXiv preprint
Learning from Research: Toward Lifelong Agent Harness Evolution	arXiv preprint
NavHarness: Towards Lifelong Embodied Navigation	arXiv preprint
MoMHa: Multi-Objective Optimization of LLM Harnesses over Accuracy, Safety, and Tokens	NeurIPS 2026
SkillEvoReg: Regularizing Agent Skill Evolution Against Overfitting	arXiv preprint
SkillRefine: Cross-Source Skill Induction and Execution Validation for LLM Agents in Refinery Planning Software	arXiv preprint
A Wrong Turn Does Not Ruin the Journey: Deviation-Guided Skill Self-Evolution for LLM Agents	arXiv preprint
HarnessPAI: An Evolving Harness for Physical AI	arXiv preprint
SEEK: Skill-Routed Evaluation with Evolvable Knowledge for Industrial Search	arXiv preprint
Grow the Harness, Not the Context: From Strategy-Free Scaffolds to Reusable Specialist Agents	arXiv preprint
Harness as a Language: A Minimalist Agent Framework With Maximal Expressivity	arXiv preprint
Recursive self-improvement of AI research agents	arXiv preprint
Harness-Zero: Harness Distillation via Agent-as-Harness	arXiv preprint
RRSI: Regularized Recursive Self-Improvement of Agent Harnesses	arXiv preprint
TTSE: A Two-Track Online Self-Evolution Framework	arXiv preprint
Designer-RSI: Evolving Procedural Memory from User Traffic for Agentic Graphic Design	arXiv preprint
Self Improvement via Fast Tree-search	arXiv preprint
SkillAA: Attribution-Guided Skill-Graph Updating with Targeted Validation and Rollback	arXiv preprint
SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness	arXiv preprint
EvolveTrade: Experience-Driven Policy Refinement for Self-Evolving LLM Trading Agents	arXiv preprint
Reflect, Revise, Reuse: Training-Free Skill Evolution for GUI Agents	arXiv preprint
AlgoEvo: Self-Evolving Agentic Search for Automated Algorithm Discovery	arXiv preprint
AnchorGUI: Asymmetric Memory for Dual-Scale Learning in GUI Navigation	ECCV 2026
EvoOntology: A Self-Evolving Ontology Layer for Data Agents	arXiv preprint
ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement	arXiv preprint
RSIAgent: Autonomous Exploration for Recursive Self-improvement in New Environments	arXiv preprint
Dream-RSI: Recursive Self-Improvement through Evolving Worlds	Preprint
COBRA-Skills: Contextual Bandit-Guided Evolution for Agent Skill Optimization	arXiv preprint
Ecdysis: Efficient and Effective Training of Runtime Harnesses for LLM Agents	arXiv preprint
Experience Funnel: A State-Policy Alternating Loop for Self-Evolving Agents	arXiv preprint
Procedural Graphs: Self-Evolving Execution Structures for LLM Agents	arXiv preprint
SkillAdam: Stable and Efficient Skill Evolution for Agents	arXiv preprint
SimSkill: A Self-Evolving LLM Agent for Skill and Knowledge Accumulation in Traffic Simulation	arXiv preprint
CHIME: Credit-Aware Hierarchical Memory Evolution for Long-Horizon Agentic Planning	arXiv preprint
Reef: Continual Learning Infrastructure for Self-Improving Agents	Project · v0.0.2
SkillGLoW: Procedural-Family Skill Consolidation for Self-Improving Agents on Long-Horizon Task Streams	arXiv preprint
Harness-of-Harness: Multi-Day Autonomous Software Development with Continual Improvement	arXiv preprint
HarnessEvolve: Learning from Reference Trajectories for Reliable Agent Self-Evolution	arXiv preprint
PILOT in the Loop: Live Self-Improvement for Long-Horizon Agents	arXiv preprint
WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution	arXiv preprint
Recursive Experiential-Working Memory Evolution for Long-Horizon Agent Harnesses	arXiv preprint
MediSkill-Evo: Process-Constrained Self-Evolution for Evidence-Grounded Clinical Interaction	arXiv preprint
Prime Agent: A Self-Improving RLM Harness	arXiv preprint
Proteus: A Harness-Agnostic Self-Evolution Framework for AI Agents	Project · v0.3.0
TRACE: A Self-Evolving Skill Bank for Consistent, Limit-Aware LLM Agents	arXiv preprint
ForeDreamer: A Self-Evolving Dual-Agent Memory Architecture for Future Event Prediction	Findings of EMNLP 2026
EnvHarness: Awakening Static Worlds for Agent Learning	arXiv preprint
HyperSkill: Self-Evolving LLM Agents via Hypergraph-Structured Skill Memory	arXiv preprint
Evo-Harness: Context-to-Harness Skill Compilation for Self-Evolving Agents	arXiv preprint
DIVE: Unlocking Self-Improvement in Frozen Language Models Through Diversity-Driven Skill Evolution	arXiv preprint
Mendel Gödel Machine: Recursive Self-Improving Coding Agents via Comparative Evolution	arXiv preprint
SkillHEX: Improving Agent Skills via Hypothesis-Driven Autonomous Exploration and Exploitation	arXiv preprint
EvolveNet: Collaborative Harness Evolution for Agent Self-Improvement	arXiv preprint
DarwinX: Evolving Agent Harnesses Through Natural Selection	arXiv preprint
Knowledge-Centric Self-Improvement	arXiv preprint
Recursive Harness Self-Improvement	arXiv preprint
HarnessBank: Semantic Gene-Bank Search with Gated Verification for Agent-Harness Self-Evolution	arXiv preprint
SAGEAgent: A Self-Evolving Agent for Cost-Aware Modality Acquisition in Multimodal Survival Prediction	arXiv preprint
The Red Queen Gödel Machine: Co-Evolving Agents and Their Evaluators	arXiv preprint
When Rules Learn: A Self-Evolving Agent for Legal Case Retrieval	ACL 2026
HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry	arXiv preprint
Self-Harness: Harnesses That Improve Themselves	arXiv preprint
From Failed Trajectories to Reliable LLM Agents: Diagnosing and Repairing Harness Flaws	arXiv preprint
OpenSkill: Open-World Self-Evolution for LLM Agents	arXiv preprint
SePO: Self-Evolving Prompt Agent for System Prompt Optimization	arXiv preprint
SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision	Findings of EMNLP 2026
ExpGraph: Model-Agnostic Experience Learning with Graph-Structured Memory for LLM Agents	arXiv preprint
PANDO: Efficient Multimodal AI Agents via Online Skill Distillation	arXiv preprint
DemoEvolve: Overcoming Sparse Feedback in Agentic Harness Evolution with Demonstrations	arXiv preprint
Continual Harness: Online Adaptation for Self-Improving Foundation Agents	arXiv preprint
LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling	arXiv preprint
Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses	arXiv preprint
Mem²Evolve: Towards Self-Evolving Agents via Co-Evolutionary Capability Expansion and Experience Distillation	ACL 2026
Meta-Harness: End-to-End Optimization of Model Harnesses	arXiv preprint
P²O: Joint Policy and Prompt Optimization	arXiv preprint
Hyperagents	arXiv preprint
Group-Evolving Agents: Open-Ended Self-Improvement via Experience Sharing	arXiv preprint
Meta Context Engineering via Agentic Skill Evolution	ICML 2026
Huxley-Gödel Machine: Human-Level Coding Agent Development by an Approximation of the Optimal Self-Improving Machine	ICLR 2026 Oral
Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models	ICLR 2026
ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory	ICLR 2026
Memp: Exploring Agent Procedural Memory	Findings of ACL 2026
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning	ICLR 2026 Oral
Darwin Gödel Machine: Open-Ended Evolution of Self-Improving Agents	ICLR 2026
Dynamic Cheatsheet: Test-Time Learning with Adaptive Memory	EACL 2026
Gödel Agent: A Self-Referential Agent Framework for Recursive Self-Improvement	ACL 2025
Cradle: Empowering Foundation Agents Towards General Computer Control	ICML 2025

Memory

Information or experience is stored, updated, and retrieved across steps, trajectories, or tasks.

Paper or project	Publication
Learning from Revision Consequences: Hindsight Meta-Experience Distillation for Self-Improving Agents	arXiv preprint
EviSkill: Grounding Skill Evolution in Replayable Evidence	arXiv preprint
Learning from Research: Toward Lifelong Agent Harness Evolution	arXiv preprint
NavHarness: Towards Lifelong Embodied Navigation	arXiv preprint
SkillRefine: Cross-Source Skill Induction and Execution Validation for LLM Agents in Refinery Planning Software	arXiv preprint
HarnessPAI: An Evolving Harness for Physical AI	arXiv preprint
Harness as a Language: A Minimalist Agent Framework With Maximal Expressivity	arXiv preprint
Recursive self-improvement of AI research agents	arXiv preprint
Harness-Zero: Harness Distillation via Agent-as-Harness	arXiv preprint
RRSI: Regularized Recursive Self-Improvement of Agent Harnesses	arXiv preprint
TTSE: A Two-Track Online Self-Evolution Framework	arXiv preprint
Designer-RSI: Evolving Procedural Memory from User Traffic for Agentic Graphic Design	arXiv preprint
SkillAA: Attribution-Guided Skill-Graph Updating with Targeted Validation and Rollback	arXiv preprint
Reflect, Revise, Reuse: Training-Free Skill Evolution for GUI Agents	arXiv preprint
AlgoEvo: Self-Evolving Agentic Search for Automated Algorithm Discovery	arXiv preprint
AnchorGUI: Asymmetric Memory for Dual-Scale Learning in GUI Navigation	ECCV 2026
EvoOntology: A Self-Evolving Ontology Layer for Data Agents	arXiv preprint
ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement	arXiv preprint
ReMe: A Local-First, Self-Evolving Personal Knowledge Base for AI Agents	Project · v0.4.1.12
RSIAgent: Autonomous Exploration for Recursive Self-improvement in New Environments	arXiv preprint
Dream-RSI: Recursive Self-Improvement through Evolving Worlds	Preprint
Experience Funnel: A State-Policy Alternating Loop for Self-Evolving Agents	arXiv preprint
Procedural Graphs: Self-Evolving Execution Structures for LLM Agents	arXiv preprint
SkillAdam: Stable and Efficient Skill Evolution for Agents	arXiv preprint
SimSkill: A Self-Evolving LLM Agent for Skill and Knowledge Accumulation in Traffic Simulation	arXiv preprint
CHIME: Credit-Aware Hierarchical Memory Evolution for Long-Horizon Agentic Planning	arXiv preprint
SkillGLoW: Procedural-Family Skill Consolidation for Self-Improving Agents on Long-Horizon Task Streams	arXiv preprint
Harness-of-Harness: Multi-Day Autonomous Software Development with Continual Improvement	arXiv preprint
PILOT in the Loop: Live Self-Improvement for Long-Horizon Agents	arXiv preprint
WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution	arXiv preprint
Recursive Experiential-Working Memory Evolution for Long-Horizon Agent Harnesses	arXiv preprint
MediSkill-Evo: Process-Constrained Self-Evolution for Evidence-Grounded Clinical Interaction	arXiv preprint
Prime Agent: A Self-Improving RLM Harness	arXiv preprint
Proteus: A Harness-Agnostic Self-Evolution Framework for AI Agents	Project · v0.3.0
ForeDreamer: A Self-Evolving Dual-Agent Memory Architecture for Future Event Prediction	Findings of EMNLP 2026
EnvHarness: Awakening Static Worlds for Agent Learning	arXiv preprint
HyperSkill: Self-Evolving LLM Agents via Hypergraph-Structured Skill Memory	arXiv preprint
Knowledge-Centric Self-Improvement	arXiv preprint
SAGEAgent: A Self-Evolving Agent for Cost-Aware Modality Acquisition in Multimodal Survival Prediction	arXiv preprint
ISM: Self-Improving Strategy Memory for Continual Mathematical Reasoning	ICML 2026 AI for Math Workshop
HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry	arXiv preprint
Self-Harness: Harnesses That Improve Themselves	arXiv preprint
From Failed Trajectories to Reliable LLM Agents: Diagnosing and Repairing Harness Flaws	arXiv preprint
SkillSmith: Co-Evolving Skills and Tools for Self-Improving Agent Systems	arXiv preprint
ExpGraph: Model-Agnostic Experience Learning with Graph-Structured Memory for LLM Agents	arXiv preprint
PANDO: Efficient Multimodal AI Agents via Online Skill Distillation	arXiv preprint
Continual Harness: Online Adaptation for Self-Improving Foundation Agents	arXiv preprint
LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling	arXiv preprint
Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses	arXiv preprint
HeLa-Mem: Hebbian Learning and Associative Memory for LLM Agents	ACL 2026
Mem²Evolve: Towards Self-Evolving Agents via Co-Evolutionary Capability Expansion and Experience Distillation	ACL 2026
Meta-Harness: End-to-End Optimization of Model Harnesses	arXiv preprint
Hyperagents	arXiv preprint
Meta Context Engineering via Agentic Skill Evolution	ICML 2026
Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models	ICLR 2026
ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory	ICLR 2026
Memp: Exploring Agent Procedural Memory	Findings of ACL 2026
Dynamic Cheatsheet: Test-Time Learning with Adaptive Memory	EACL 2026
A-MEM: Agentic Memory for LLM Agents	NeurIPS 2025
Agent Workflow Memory	ICML 2025
Cradle: Empowering Foundation Agents Towards General Computer Control	ICML 2025

Skill

Reusable strategies, procedures, workflows, or skill resources are created and revised.

Paper or project	Publication
Learning from Revision Consequences: Hindsight Meta-Experience Distillation for Self-Improving Agents	arXiv preprint
EviSkill: Grounding Skill Evolution in Replayable Evidence	arXiv preprint
Learning from Research: Toward Lifelong Agent Harness Evolution	arXiv preprint
NavHarness: Towards Lifelong Embodied Navigation	arXiv preprint
SkillEvoReg: Regularizing Agent Skill Evolution Against Overfitting	arXiv preprint
SkillRefine: Cross-Source Skill Induction and Execution Validation for LLM Agents in Refinery Planning Software	arXiv preprint
A Wrong Turn Does Not Ruin the Journey: Deviation-Guided Skill Self-Evolution for LLM Agents	arXiv preprint
HarnessPAI: An Evolving Harness for Physical AI	arXiv preprint
SEEK: Skill-Routed Evaluation with Evolvable Knowledge for Industrial Search	arXiv preprint
Harness as a Language: A Minimalist Agent Framework With Maximal Expressivity	arXiv preprint
Harness-Zero: Harness Distillation via Agent-as-Harness	arXiv preprint
RRSI: Regularized Recursive Self-Improvement of Agent Harnesses	arXiv preprint
TTSE: A Two-Track Online Self-Evolution Framework	arXiv preprint
Designer-RSI: Evolving Procedural Memory from User Traffic for Agentic Graphic Design	arXiv preprint
SkillAA: Attribution-Guided Skill-Graph Updating with Targeted Validation and Rollback	arXiv preprint
EvolveTrade: Experience-Driven Policy Refinement for Self-Evolving LLM Trading Agents	arXiv preprint
Reflect, Revise, Reuse: Training-Free Skill Evolution for GUI Agents	arXiv preprint
AlgoEvo: Self-Evolving Agentic Search for Automated Algorithm Discovery	arXiv preprint
AnchorGUI: Asymmetric Memory for Dual-Scale Learning in GUI Navigation	ECCV 2026
ReMe: A Local-First, Self-Evolving Personal Knowledge Base for AI Agents	Project · v0.4.1.12
RSIAgent: Autonomous Exploration for Recursive Self-improvement in New Environments	arXiv preprint
COBRA-Skills: Contextual Bandit-Guided Evolution for Agent Skill Optimization	arXiv preprint
Experience Funnel: A State-Policy Alternating Loop for Self-Evolving Agents	arXiv preprint
Procedural Graphs: Self-Evolving Execution Structures for LLM Agents	arXiv preprint
SkillAdam: Stable and Efficient Skill Evolution for Agents	arXiv preprint
SimSkill: A Self-Evolving LLM Agent for Skill and Knowledge Accumulation in Traffic Simulation	arXiv preprint
Reef: Continual Learning Infrastructure for Self-Improving Agents	Project · v0.0.2
SkillGLoW: Procedural-Family Skill Consolidation for Self-Improving Agents on Long-Horizon Task Streams	arXiv preprint
HarnessEvolve: Learning from Reference Trajectories for Reliable Agent Self-Evolution	arXiv preprint
PILOT in the Loop: Live Self-Improvement for Long-Horizon Agents	arXiv preprint
WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution	arXiv preprint
Recursive Experiential-Working Memory Evolution for Long-Horizon Agent Harnesses	arXiv preprint
MediSkill-Evo: Process-Constrained Self-Evolution for Evidence-Grounded Clinical Interaction	arXiv preprint
Prime Agent: A Self-Improving RLM Harness	arXiv preprint
Proteus: A Harness-Agnostic Self-Evolution Framework for AI Agents	Project · v0.3.0
TRACE: A Self-Evolving Skill Bank for Consistent, Limit-Aware LLM Agents	arXiv preprint
ForeDreamer: A Self-Evolving Dual-Agent Memory Architecture for Future Event Prediction	Findings of EMNLP 2026
EnvHarness: Awakening Static Worlds for Agent Learning	arXiv preprint
HyperSkill: Self-Evolving LLM Agents via Hypergraph-Structured Skill Memory	arXiv preprint
Evo-Harness: Context-to-Harness Skill Compilation for Self-Evolving Agents	arXiv preprint
DIVE: Unlocking Self-Improvement in Frozen Language Models Through Diversity-Driven Skill Evolution	arXiv preprint
SkillHEX: Improving Agent Skills via Hypothesis-Driven Autonomous Exploration and Exploitation	arXiv preprint
DarwinX: Evolving Agent Harnesses Through Natural Selection	arXiv preprint
SAGEAgent: A Self-Evolving Agent for Cost-Aware Modality Acquisition in Multimodal Survival Prediction	arXiv preprint
ISM: Self-Improving Strategy Memory for Continual Mathematical Reasoning	ICML 2026 AI for Math Workshop
When Rules Learn: A Self-Evolving Agent for Legal Case Retrieval	ACL 2026
OpenSkill: Open-World Self-Evolution for LLM Agents	arXiv preprint
SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision	Findings of EMNLP 2026
SkillSmith: Co-Evolving Skills and Tools for Self-Improving Agent Systems	arXiv preprint
ExpGraph: Model-Agnostic Experience Learning with Graph-Structured Memory for LLM Agents	arXiv preprint
PANDO: Efficient Multimodal AI Agents via Online Skill Distillation	arXiv preprint
Continual Harness: Online Adaptation for Self-Improving Foundation Agents	arXiv preprint
Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses	arXiv preprint
Mem²Evolve: Towards Self-Evolving Agents via Co-Evolutionary Capability Expansion and Experience Distillation	ACL 2026
Meta Context Engineering via Agentic Skill Evolution	ICML 2026
Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models	ICLR 2026
Memp: Exploring Agent Procedural Memory	Findings of ACL 2026
Dynamic Cheatsheet: Test-Time Learning with Adaptive Memory	EACL 2026
Agent Workflow Memory	ICML 2025
Cradle: Empowering Foundation Agents Towards General Computer Control	ICML 2025

Other artifacts

Other artifacts evolve, such as data strategies, experiment configurations, or task solutions.

Paper or project	Publication
Harness-of-Harness: Multi-Day Autonomous Software Development with Continual Improvement	arXiv preprint
EnvHarness: Awakening Static Worlds for Agent Learning	arXiv preprint

Benchmarks

Compare benchmark dimensions on the website →

Grouped by RSI mode, newest first. Benchmarks that support multiple protocols appear in each relevant group. Artifact labels describe what evolves in the evaluated workflow.

Online · Offline · Offline → Online

Online

Experience accumulates during the task stream or repeated interaction, and later work can use it.

Benchmark paper	Year	RSI artifact
RSIGym: A Flexible Environment for Recursive Self-Improvement	2026	Model parameters · Harness code · Context · Other artifacts
Agent Plasticity: Measuring Self-Improvement Through Experience	2026	Harness code · Context · Memory · Skill
Aspire: Can Models Self-Evolve from Vague Goals?	2026	Model parameters · Harness code · Context · Memory
FinEvo-Bench: A Longitudinal Benchmark for Self-Evolving Agents in Professional Financial Workflows	2026	Memory · Skill
ContinualSkillBench: Can LLM Agents Truly Evolve Their Capabilities?	2026	Context · Skill
PAST-Bench: Benchmarking the Foundations of Recursive Self-Improvement in Personal Agents	2026	Memory · Skill
PATH-Bench: Path-Dependent Evaluation of Lifelong Agents	2026	Context · Memory · Skill
AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks?	2026	Context · Memory · Skill
RSIBench-Data: Benchmarking Data-Centric Research for Recursive Self-Improvement	2026	Context · Other artifacts
EdgeBench: Unveiling Scaling Laws of Learning from Real-World Environments	2026	Context · Other artifacts
Continual Learning Bench: Evaluating Frontier AI Systems in Real-World Stateful Environments	2026	Context · Memory · Other artifacts
AutoLab: Can Frontier Models Solve Long-Horizon Auto Research and Engineering Tasks?	2026	Context · Other artifacts
Can Generalist Agents Automate Data Curation?	2026	Context · Other artifacts
EvoMemBench: Benchmarking Agent Memory from a Self-Evolving Perspective	2026	Context · Memory
MLS-Bench: A Holistic and Rigorous Assessment of AI Systems on Building Better AI	2026	Context · Other artifacts
SkillLearnBench: Benchmarking Continual Learning Methods for Agent Skill Generation on Real-World Tasks	2026	Skill
SkillFlow: Benchmarking Lifelong Skill Discovery and Evolution for Autonomous Agents	2026	Context · Skill
Agent² RL-Bench: Can LLM Agents Engineer Agentic RL Post-Training?	2026	Context · Other artifacts
PostTrainBench: Can LLM Agents Automate LLM Post-Training?	2026	Context · Other artifacts
Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory	2025	Context · Memory
Building Self-Evolving Agents via Experience-Driven Lifelong Learning: A Framework and Benchmark	2025	Context · Memory · Skill
LifelongAgentBench: Evaluating LLM Agents as Lifelong Learners	2025	Context · Memory

Offline

Evolution precedes a separate held-out evaluation.

Benchmark paper	Year	RSI artifact
Agent Plasticity: Measuring Self-Improvement Through Experience	2026	Harness code · Context · Memory · Skill
HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness?	2026	Harness code · Context
Aspire: Can Models Self-Evolve from Vague Goals?	2026	Model parameters · Harness code · Context · Memory
S3Gym: Can LLMs Turn Self-Testing and Self-Judging into Self-Improvement?	2026	Model parameters · Context · Memory
Evo-Bench: Can Language Models Improve Agent Harness?	2026	Harness code · Context
HarnessOpt-Bench: Evaluating LLMs at Harness Optimization	2026	Harness code · Context
GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks	2026	Skill
EvoAgentBench: Benchmarking Agent Self-Evolution via Ability Transfer	2026	Skill
SEAGym: An Evaluation Environment for Self-Evolving LLM Agents	2026	Harness code · Context · Memory · Skill
The Meta-Agent Challenge: Are Current Agents Capable of Autonomous Agent Development?	2026	Harness code · Context
SkillFlow: Benchmarking Lifelong Skill Discovery and Evolution for Autonomous Agents	2026	Context · Skill
VeRO: A Harness for Agents to Optimize Agents	2026	Harness code · Context
MemoryBench: A Benchmark for Memory and Continual Learning in LLM Systems	2025	Memory
Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions	2025	Context · Memory

Offline to online

An artifact is built offline and continues to evolve during online use.

Benchmark paper	Year	RSI artifact
SkillFlow: Benchmarking Lifelong Skill Discovery and Evolution for Autonomous Agents	2026	Context · Skill

Use the explorer

Choose a collection: Benchmark papers or Methods & Systems.
Narrow the question: select multiple tags within a row, then combine dimensions across rows. For example, look for methods that update Skill, run Online, and use Environment feedback.
Read and compare: search titles, sort by recency or citations, and expand abstracts and taxonomy profiles.
Follow the connections: open Citation graph, choose methods or benchmarks, and search for a paper. Drag and zoom to explore its neighborhood.

The site supports English and Chinese, with the language switch in the upper-right corner.

Citation

If this collection is useful in your work, please cite it:

@misc{awesomersi2026,
  title        = {Awesome RSI: A Curated Collection of Recursive Self-Improvement Benchmarks and Methods},
  author       = {Prism-Shadow},
  year         = {2026},
  howpublished = {\url{https://github.com/Prism-Shadow/awesome-rsi}},
}

WeChat Group

Scan the QR code to join the Awesome RSI discussion group.