Self-Improving Agents

Ask about this topic

Overview

Self-improving agents study how systems can learn from their own actions and outcomes to perform better on later tasks, from coding and web use to robotics and long-horizon games. Common approaches turn successes and failures into reusable memories or executable skills, revise prompts and agent harnesses, or update model parameters through fine-tuning and reinforcement learning. Work increasingly uses repeated trials, held-out tasks, execution-based checks, and external evaluators to test whether improvements transfer rather than merely exploit a score. The central tension is that feedback and self-authored tests can be unreliable, so genuine progress must be balanced against regression, reward hacking, safety risks, and the cost of verification.

Latest papers

CardsList

171 papers57 papers in the last four weeks, up 171% on the four weeks before. 0.3% of all new papers.

Sep 28, 2026

BEHAVE: Functional Behavior Modeling Enables Self-Improving Agents for Hardware Design and Verification

Developing agents for hardware design and verification requires reliable correctness feedback. As a hardware specification may permit correct implementations with different latencies, matching design and reference outputs cycle by cycle can reject valid designs. To address this, we introduce BEHAVE, an agentic framework for multi-turn joint hardware design and verification through functional behavior modeling. We define Behavior IR to express task functionality as executable behavior models without prescribing implementation timing beyond the specification. The agent iteratively develops a register-transfer-level (RTL) design and a behavior model as the design's verification reference. Our evaluator, BEHAVE-Sim, checks both artifacts separately against a hidden golden behavior model using input stimuli generated by random sampling and solver-guided search. BEHAVE thus supports power, performance, and area (PPA) exploration across task-permitted latencies and microarchitectures. During training, the same evaluator provides verifiable reinforcement learning (RL) rewards from specification-behavior pairs without reference RTL. For self-improvement, the agent continually searches for high-level implementations relevant to its capability gaps, constructs and checks specification-behavior pairs, and trains on the expanded task pool. We release BEHAVE-Train and BEHAVE-Eval with 600 human-reviewed specification-behavior pairs for realistic hardware workloads. Starting from 60 seed tasks and acquiring 100 new tasks, self-improvement raises Qwen3.8-27B's RTL pass@1 on BEHAVE-Eval from 55.0% to 75.0%, reaching performance comparable to RL using a 540-task pool.

Yuheng Wu, Berk Gokmen, Sujeeth Jinesh +5

Stanford University · Workato, Inc.

Formal Hardware VerificationElectronic Design AutomationAI Agent BenchmarksReinforcement Learning with Verifiable RewardsSelf-Improving Agents
AskPDF
Sep 26, 2026

Predict Before You Modify: Learning Improvement Dynamics for Self-Evolving Agents

Self-evolving agents improve through repeated cycles of modification and evaluation. However, existing methods receive feedback on modifications only after costly evaluations, and aggregate scores may obscure distinctions between failures that require different repairs. We introduce predictive self-evolution through an editable Improvement Dynamics Model (IDM). Before evaluation, the IDM predicts task-level outcomes of a proposed modification and guides an optional revision. After evaluation, past modifications and their observed outcomes are used to improve the IDM, allowing predictive knowledge to accumulate across generations. The system can thus improve how it solves tasks, proposes modifications, and predicts their effects. Building on HyperAgents, we evaluate this approach across multilingual coding, paper review, robotics reward design, and Olympiad-level mathematical grading. Our approach outperforms HyperAgents across all four domains, with up to 46% higher average performance over generations. Gains also persist under matched token budgets that include both agent evolution and task evaluation, and extend to held-out tasks. Forecast accuracy improves as the IDM evolves, and the learned predictive knowledge transfers to improve evolution in a new domain.

Zixuan Xie, Chang Xu, Yuhua Jiang +1

University of Virginia · Microsoft Research · Tsinghua University

LLM Agent Self-ImprovementSelf-Improving AgentsSelf-Evolving AgentsPredict-Then-Optimize
AskPDF
Sep 26, 2026

When Better Gets Worse: Improvement Fidelity for Self-Improving Agents in Adaptive Worlds

Self-improving agents increasingly rely on proxy verifiers to choose policy updates, yet deployment can change the world in which those updates are evaluated. An update that looks better to the verifier can therefore become worse after deployment even when the verifier ranks policies well overall. We formalize this gap as Improvement Fidelity, which asks whether proxy improvements preserve the sign and ordering of deployment improvements over the updates an improvement process actually proposes. We show that global policy accuracy need not guarantee update fidelity: operator shift and deployment response can create update-level errors, while candidate margins determine whether those errors change the replacement decision. We introduce PIVOT-KG, a paired, decision-aware validator that allocates scarce high-fidelity evaluation according to the expected reduction in selection regret per unit cost. Across 90 held-out roots in Leduc, Kuhn, and Melting Pot, proxy and deployment optimal sets are disjoint in 51 cases. In an eight-candidate HighwayEnv stress test, PIVOT-KG reduces mean improvement-selection regret from 0.0435 under the exact Uniform validation rule to 0.0055 at the primary budget. Together, these results show why reliable self-improvement should evaluate proposed improvements in the worlds they induce, while providing a practical rule for allocating scarce deployment evidence when it can affect the replacement decision.

Ke Wang, Zijie Zhao, Zhiyi Yuan +1

University of Cambridge · Georgia Institute of Technology · Massachusetts Institute of Technology +2

Self-Improving AgentsAI Agent EvaluationPolicy Evaluation
AskPDF
Sep 25, 2026

GameBoyWorlds: A Testbed for Self-Improvement in Embodied Video Games

Powered by expert guidance, agents can operate in interactive environments; however, it is unclear whether they can learn autonomously from their own experience. To evaluate such self-improvement methods, we introduce GameBoyWorlds, a testbed for agentic self-improvement in video games. GameBoyWorlds-Execution evaluates task execution on a collection of 5 distinct game series. Agents are allowed access to dedicated training games but are provided no demonstrations, documentation, or rewards. Agents must ground themselves in the environment through self-directed exploration and by inferring actionable knowledge from their own experience. At test time, agents must complete short-horizon tasks that evaluate their ability to navigate, interact, and engage with game-specific mechanics in unseen games. Out-of-the-box frontier models complete fewer than 50% of the 500 tasks due to failures in multimodal grounding, establishing that self-improvement methods have room to push performance. We demonstrate that contemporary approaches to self-improvement are lacking, with world modelling and autonomous skill discovery failing, and a novel strategy that uses curiosity-based exploration to write guides achieving only partial success. GameBoyWorlds-Playthrough tests end-to-end game completion in two fan-made Pokémon games. We show that while frontier models have been pre-exposed to official releases such as Pokémon Red, they lack essential information on the games in our testbed. Instead of relying on their parametric knowledge to succeed, agents must learn from their own experience and autonomously improve over the course of the playthrough. We show that a sophisticated agentic pipeline with multimodal memory and hierarchical subgoals fails to reach even the first major milestone in both games, establishing GameBoyWorlds as an ambitious target for self-improving agents.

Dhananjay Ashok, Adam Shen, Aslan Huo Feng +10

Information Sciences Institute, University of Southern California · Columbia University · University of Chicago +2

Self-Improving AgentsGame-Playing AgentsAI Agent BenchmarksAgent BenchmarksLong-Horizon Agent Evaluation
AskPDF
Sep 25, 2026

Memory as Middleware for Self-Improving AI Agents

AI agents are stateless across sessions by default and therefore operationally amnesic: each session begins with little durable knowledge of prior failures, repairs, preferences, or successful strategies. As a result, agents repeat the same mistakes and discard hard-won experience. The dominant fix is bespoke memory---retrieval, persistence, and learning logic hand-wired into one agent and bound to one storage engine. This creates a fragmented landscape where memory cannot be swapped, shared, isolated, or reasoned about independently of the agent that owns it. We argue that this is a middleware problem: agent memory deserves a first-class, pluggable layer, just as data access, messaging, and persistence each became middleware concerns. We develop this vision through six systems challenges: two-sided pluggability, host-native interposition, multi-tenant isolation, write-path consistency, federated sharing with provenance, and lifecycle governance. We present ALTK-Evolve, a reference implementation of memory middleware for self-improving agents, and use it to motivate a broader research agenda for future memory middleware.

K. R. Jayaram, Vatche Isahagian, Vinod Muthusamy +4

IBM Research, USA

Agent Memory ManagementSelf-Improving Agents
AskPDF
Sep 24, 2026

LensDesigner: A Self-Improving Agent for Optical Lens Design

Optical lens design is a complex, non-convex optimization challenge that relies heavily on human experience and intuition. Existing optimized-based automatic lens design methods struggle to navigate this vast parameter space without meticulous manual tuning. In this paper, we present LensDesigner, an autonomous agent framework that mirrors the problem-solving workflow of expert opticians. To overcome the initial cold start problem, we construct LensLib100K, an extensive optical lens library, and employ Optics-Aware Retrieval to supply physically valid structural seeds. Within an interactive physical simulation environment, the agent executes macroscopic orchestration while receiving immediate optical feedback. Furthermore, we introduce a continuous self-evolving mechanism guided by a curriculum agent. By iteratively solving design tasks with progressively increasing difficulty, the agent autonomously extracts, accumulates, and reuses design heuristics, effectively evolving its optical lens design expertise over time. At the evaluation level, we introduce LensArena, a standardized evaluation benchmark comprising 120120 diverse optical design tasks, covering extreme configurations. Extensive experiments on this benchmark demonstrate that LensDesigner significantly outperforms publicly available baseline algorithms, achieving superior success rates and optimization efficiency. We hope this work sheds light on the emerging field of intelligent optics. The code will be publicly available.

Lei Sun, Haoran Liang, Dannong Xu +6

INSAIT, Sofia University “St. Kliment Ohridski” · Zhejiang University

Self-Improving AgentsAutomated Heuristic DesignConstrained Optimization
AskPDF
Sep 23, 2026

What Stops Recursive Self-Improvement in Robotics? Lessons from 123 Rounds of Agentic Skill Discovery

Can a robot improve itself the way coding agents now improve software? We built an agentic system to find out. It watches a robot fail, works out which capability is missing, writes new skills or finds and installs external models, tests every change in simulation, and repeats, with no human writing robot code. We ran it for 123 improvement rounds on household manipulation tasks. This report describes what we learned. The good news is that the agent can discover capabilities on its own: noticing that its targets were out of view, it asked for an active-viewing model, debugged it, and deployed a working search skill. The bad news is that its improvements did not add up. Changes kept passing their tests, yet the target task, putting condiments on the top shelf of a fridge, never succeeded. We found that the agent was rarely the bottleneck. Three things around it were. First, chained perception modules do not understand relations. Segmenters such as SAM 3 find shelves but not "the top shelf", so the agent filled the gap with ever more geometric rules that never converged, when what it needed was a different kind of model. Second, skill chains lock learning onto the first step. Long tasks mostly fail early, so evidence and fixes pile up there, and later skills are rarely reached, tested, or improved. Third, what the agent learns is decided by the harness. The agent optimized exactly what the evaluator measured, including where it was wrong, and weak tests and misleading memory turned activity into a standstill. We distill these lessons into concrete recommendations for building robot systems that improve themselves, each paired with an experiment that could prove it wrong.

Jiaming Wang

National University of Singapore

Self-Improving AgentsRobot Skill LearningLong-Horizon Robotic Manipulation
AskPDF
Sep 21, 2026

MedRSI: Recursive Self-Improvement for Medical Agents via Clinically Aligned Self-Evolution

Medical agents increasingly combine general reasoning models with specialized clinical tools, yet their capabilities remain largely fixed by what clinicians and engineers design before deployment. Recursive self-improvement (RSI) offers a different paradigm in which agents learn from their own failures and autonomously expand their capabilities, but directly applying RSI to medicine introduces fundamental safety challenges. We introduce MedRSI, the first recursive self-improvement framework for medicine, which continuously transforms diagnostic failures into new clinical capabilities through tool composition and task-specific model training. Inspired by clinical practice, MedRSI introduces two mechanisms for clinically aligned self-evolution. Clinical-cost-aware failure prioritization directs improvement toward errors according to their potential clinical consequences rather than frequency alone. Fast discovery with slow registration separates rapid capability invention from conservative adoption, allowing new tools to enter the persistent agent only after demonstrating sustained benefit across subsequent patient cohorts. Across public glaucoma and heart disease benchmarks and two private clinical tasks, MedRSI progressively develops segmentation, measurement, prediction, multimodal reasoning, and generative capabilities, surpasses manually engineered medical agents, and autonomously discovers solutions to clinical problems not anticipated by its original designers. Our results show that medical agents need not remain constrained by capabilities specified before deployment: with clinically grounded mechanisms governing what to improve and what to retain, they can continuously construct, validate, and accumulate new capabilities from diagnostic experience. Code is available at https://github.com/ImprintLab/MedRSI.

Junde Wu, Jiayuan Zhu, Minghao Hu +2

University of Oxford · Stanford University

Self-Improving AgentsSelf-Evolving AgentsRecursive Self-ImprovementLLM Agent Safety
AskPDF
Sep 17, 2026

UnifiedPlayers: Enhance Tool-Integrated Reasoning in Agentic Reinforcement Learning

Self-evolving methods reduce the need for human-annotated trajectories by allowing tool-using agents to generate their own training data. Yet existing methods typically separate trajectory generation from evaluation, relying on static verifiers that cannot adapt to emerging failure modes or self-consistency signals that may reinforce errors shared across trajectories. Jointly adapting planning, execution, and evaluation offers a promising alternative, but introduces a fundamental coordination challenge: each component continuously changes the data or feedback used to train the others. We address this challenge with UnifiedPlayers, a cooperative framework comprising a Planning Player that generates tasks, an Execution Player that produces multi-turn trajectories with Python tool calls, and an Evaluation Player that constructs executable verifiers. We design role-specific rewards that coordinate the three players toward a shared learning objective under GRPO. Across two model backbones and twelve reasoning benchmarks, UnifiedPlayers outperforms the strongest prior baseline by at least 3.5% on mathematical reasoning and 3.9% on general reasoning tasks. Moreover, the learned verifier achieves 84.2% adversarial detection accuracy, while its reward signal exhibits 2.03×\times higher per-question variance than a self-consistency baseline, providing more discriminative verifications. These results highlight cooperation among specialized players as a promising path toward self-enhanced tool-integrated agents.

Wenjie Liao, Liangjie Zhao, Zehong Cao

Waseda University · Adelaide University

RL for Language Model ReasoningReinforcement Learning with Verifiable RewardsSelf-Improving AgentsCooperative MARLRL for Tool Use
AskPDF
Sep 17, 2026

VideoResearcher: Self-Improving Tool Design for Long-Video Understanding

Video agents have made substantial progress in long-video understanding. Yet effective video-agent systems require costly, time-consuming manual design and trial and error. Current self-improvement methods either refine low-impact prompts, recombine predefined micro-tools, or struggle with convergence in harness optimization. To bridge this gap, we target high-impact video-tool with VideoResearcher, a training-free multi-agent framework that autonomously designs, tests, and refines tools for video understanding, like a human researcher. VideoResearcher operates through dual Solving and Evolving loops: it analyzes tool-use trajectories to identify capability gaps, coordinates specialized agents to develop and validate executable tools, and reuses evolved tools to strengthen evidence acquisition in subsequent video reasoning. Through iterative tool refinement and validation, it progressively strengthens evidence acquisition without updating model parameters. VideoResearcher achieves state-of-the-art performance among self-improving agents and approaches the human-designed upper bound, demonstrating a training-free paradigm for long-video understanding that expands agent capabilities through autonomous tool development while reducing costly manual engineering.

Dingqiang Ye, Dongdi Zhao, Kaishen Wang +11

Johns Hopkins University

Tool-Using Vision-Language AgentsLong-Video UnderstandingSelf-Improving AgentsLLM Agent Tool GenerationAutonomous Research Agents
AskPDF
Sep 15, 2026

Reflections on Trusting Trust, Revisited: Contaminating Self-Modifying AI Coding Agents with Poisoned Benchmarks

Thompson's "Reflections on Trusting Trust" showed that a compiler can be poisoned to reinsert its own backdoor, so that even recompiling clean source reproduces the Trojan. Today, substantial coding work is done by AI coding agents -- and increasingly, those agents generate new versions of themselves. We reconsider Thompson's attack when the "compiler" is a self-modifying coding agent. Can an adversary supply poisoned benchmarks to the agent's self-evaluation and self-improvement process to induce future versions of the agent to write vulnerable code on clean, held-out tasks? We instantiate this attack against three recently proposed self-modifying coding agents: the Darwin Gödel Machine (with our experimental modifications), the Self-Improving Coding Agent, and Hyperagents (both substantively unmodified). We demonstrate successful proofs-of-concept: for example, with Hyperagents powered by Sonnet 4.5, our poisoned benchmark leads the agent to self-evolve instructions that disable HTTPS certificate validation on neutral URL-fetching tasks. From our experiments, we distill properties of the vulnerability, benchmark, model, and agent scaffolding that are sufficient to enable a benchmark poisoning attack. Moreover, we show that contamination often persists even when a poisoned agent is subsequently evolved against clean benchmarks. We discuss defensive directions and argue that self-modifying coding agents must be designed to be more resilient to such attacks.

Franziska Roesner, Tadayoshi Kohno

University of Washington · Georgetown University

AI Coding AgentsAI Agent SecuritySelf-Improving AgentsSelf-Evolving Agents
AskPDF
Sep 14, 2026

Dream-RSI: Recursive Self-Improvement through Evolving Worlds

Recursive self-improvement is becoming essential for autonomous AI agents, whose progress depends on discovering high-value solutions across complex domains. Effective exploration drives this process, yet managing and improving exploration strategies remains a major bottleneck. Current systems face a fundamental dilemma: fixed strategies fail to adapt as search spaces scale, while online policy optimization must navigate vast meta-search spaces under delayed, expensive feedback from long-horizon rollouts. We introduce Dream-RSI, a framework for scalable, recursively self-improving exploration. A lightweight orchestration layer makes exploration explicit and programmable while leaving the underlying base agent unchanged. Our key insight is that accumulated discovery history can act as a replay simulator over the realized search space. By dreaming within this simulator built from historical discovery trees, Dream-RSI obtains immediate, low-cost off-policy feedback to evaluate and refine exploration policies without repeated, expensive online evaluation. The improved policy is then redeployed online to drive further discovery, continuously expanding the simulator pool in a self-improving loop. Across 9 tasks in 4 domains, Dream-RSI achieves competitive quality and improves discovery efficiency in several settings.

Tong Zheng, Xidong Wu, Zheng Zhang +14

Google · University of Maryland, College Park · Google Deepmind +1

RL ExplorationSelf-Improving AgentsRecursive Self-ImprovementAutonomous ExperimentationOff-Policy RL
AskPDF
Sep 11, 2026

Generalized Agent Iteration: One Formal Framework for Iterative Policy Improvement and Recursive Self-Improvement

When we speak of recursive self-improvement (RSI), are we speaking of a phenomenon, a mechanism, or a prospect? Towards autonomous and evolving intelligence, RSI is being claimed at many scales, while no single framework that formally describes these emerging instances exists. Its counterpart in the classical realm, iterative policy improvement, is characterized by generalized policy iteration (GPI), a framework of broad applicability with well-understood theoretical properties, but only where the update principle and the evaluation base lie outside the agent. In this paper, we propose Generalized Agent Iteration (GAI), a formal framework that describes iterative policy improvement and RSI as two cases of a single learning paradigm. GAI defines the agent as a configuration of modifiable components within a system and models the learning process as a cycle of agent evaluation and agent improvement. Two pivotal dials then distinguish the instances: whether the improving mechanism is part of the agent and whether the standard it is measured against is grounded outside it. The former dial delineates the boundary between GPI and RSI, and the latter determines a system's polarity as anchored, goal drift, or fully self-referential. Moreover, we use these coordinates to place existing systems on the same two axes and make the defects of recursive self-improvement statable one condition at a time. We see this paper as a first step toward exploring a formal characterization of RSI that rests on the classical account, makes existing systems comparable, and provides a principled basis for analyzing and designing new ones.

Hongyao Tang, Yi Ma, Pengyi Li +1

Tianjin University · Shanxi University

Self-Improving AgentsRecursive Self-ImprovementPolicy Iteration
AskPDF
Sep 10, 2026

Guardrailed Meta-Agent Loops: Stress-Testing Policy Pinning, Budget Bounds, and Crash Recovery

Self-improving agent workflows create an audit problem when the same controller can change both its behavior and the conditions under which that behavior is judged. We present GuardrailLoop, a simulation-based testbed that makes three operational contracts jointly testable: preservation of human-defined policy, compute accounting at every recorded execution prefix, and recovery of a specified scientific state after crashes. A hash-pinned policy fixes goals, scope, evaluation identity, budget, and release conditions; machine-directed evolution is restricted to a code-owned feature catalog and bounded knobs. The contribution is an executable boundary and an evaluation protocol that separates useful adaptation, state recovery, and repeated execution. In a paired 50-seed 2 x 2 study, round-stage growth changes target attainment by +1.00 and restricted mean compute to target by -56.97 simulated GPU-hours (95% paired-bootstrap interval [-58.91,-54.70]); idle growth has zero measured utility effect. Across 240 enumerated crash injections, all runs recover the defined outcome, but only 210 preserve the normalized trace: 30 pre-commit crashes repeat a planner call. Resource-drift, kill-switch, integrity, and output-guard matrices satisfy their specified checks. These findings show why successful outcome recovery is insufficient evidence of exactly-once execution. They establish conformance within one calibrated deterministic testbed, rather than general safety or real-world self-improvement.

Qinzhen Ma, Jialin Wu

Rice University · University of California, San Diego

Agent Failure AnalysisAI Agent ReliabilityRuntime Enforcement for AI AgentsAI Agent Safety BenchmarksSelf-Improving Agents
AskPDF
Sep 10, 2026

The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement

Recursive self-improvement (RSI) enables AI systems to turn experience and feedback into persistent changes that improve both their capabilities and the process of future improvement. We first use the Headroom-Closed Index (HCI) to reveal the problems of existing LLMs, then introduce the RSI concept and its development roadmap: from improvement-execution autonomy, improvement-strategy autonomy, experience-acquisition autonomy, and environment-adaptation autonomy, to recursive meta-improvement. Next we examine RSI across scenarios (e.g., scientific discovery, embodied intelligence, software engineering), highlighting their distinct requirements and development speeds. Drawing on diverse industry practices and preliminary empirical evidence, we connect RSI research with practical systems and identify key challenges to achieving genuine RSI.

Yi Duan, Ying Liu, Zirui Tang +32

Shanghai Jiao Tong University · Theseus Labs · Agent-Native Research Lab +6

Self-Improving AgentsLanguage Model Self-ImprovementRecursive Self-Improvement
AskPDF
Sep 8, 2026

A Theory of Reliable Self-Evolution for Agent Harnesses

In harness self-evolution, agents modify their own prompts, code, tools, and orchestration while keeping the underlying language model fixed. Recent work has shown that agents can improve themselves in response to task failures and achieve substantial performance gains. However, gains on failed tasks do not automatically ensure that performance on previously successful tasks is preserved, raising concerns about reliable adoption. In this work, we provide a theoretically grounded condition under which a self-evolved harness can be reliably adopted. We then propose a validation rule to make the evolved system satisfy the reliable adoption condition with theoretical guarantees. Consequently, the system can achieve progressive improvement through evolution. This leads to a natural question: Does reliable self-evolution have a performance ceiling, and which factors govern this ceiling? Our theoretical results show that the performance ceiling is determined by the costs of verification and evaluation. On the other hand, self-evolution may stall in practice. In this regard, we show that experimental evidence on agent performance shifts can be used to identify the sources of stagnation. Our work thus establishes a theoretical framework for understanding and advancing reliable harness self-evolution.

Qianshu Cai, Yonggang Zhang, Jun Nie +6

University of Science and Technology of China · Hong Kong Generative AI Research & Development Center; The Hong Kong University of Science and Technology · Hong Kong Baptist University

Agent Harness OptimizationSelf-Improving AgentsSelf-Evolving Agents
AskPDF
Sep 6, 2026

MetaRSI / RSI2: A Meta-Recursive Self-Improving System for Recursive Self-Improving Systems Themselves

Recursive self-improvement (RSI) lets a system improve the model-building machinery from its own failures, so every later model inherits the gain. Yet RSI has been validated almost exclusively on coding and formal benchmarks such as science QA and mathematics. This format bound limits RSI to improvement within a machine-checkable slice, not general capability where questions are open and correctness is settled by argument, replication, or measurement. We argue RSI must next operate across real, diverse scientific, engineering, and meta-scientific domains, not where formal evaluation is merely tractable. To that end we present MetaRSI-v1, where improvement is the scheduled composition of three typed operators over one unified paradigm. Data-RSI amplifies existing competence and marks its boundary; Harness-RSI edits a five-slot scaffold without touching weights; Model-RSI internalizes capability into parameters through bounded training. Sharing one loop kernel and artifact vocabulary, they make data, scaffold, and model changes composable rather than exclusive. A two-axis optimizer jointly decides operator order and each operator's proposal policy, while a meta-level policy revises the schedule across terms. We validate MetaRSI-v1 under the field's standard evaluations, on code and closed-form science, with no external teacher: the target model plays every role in its own loop. MetaRSI-v1 reframes self-improvement from a single-surface edit to a composition across the full model-production pipeline, opening two paths: a model route internalizing capability through training, and a harness route leaving weights untouched and thus extending self-improvement to any model reachable through an interface, with Data-RSI redefined as the shared substrate feeding both. The framework further yields refutable laws on where loops exist, how operators compose, and what supervision buys.

Zihan Tan, Leixin Sun, Zitong Shi +28

Hugging Face

Meta-LearningAgent Harness OptimizationSelf-Improving AgentsLanguage Model Self-ImprovementRecursive Self-Improvement
AskPDF
Sep 3, 2026

Dalek: A Constructive Agent Machine

We present Dalek, a closed machine designed for agents that realizes self-maintenance, self-evolution, self-reproduction, and self-organization on any substrate satisfying a general host contract. The machine is built from three primitives---actors, messages, and channels. Four obligations---a host boundary, a construction language, admissible transitions, and rule heredity---give its boundary, identity, and closure a structural basis. Von Neumann's 1948 self-reproducing automaton supplies a hereditary constructional core: a self-description together with a constructor, a copier, and a controller. Dalek combines this core with the four obligations and rederives its medium for a text-and-message agent substrate, adding explicit structures for boundary, identity, history, and growth. A large language model and a compiler occupy the payload position and form a general capability producer. New capabilities are authored, compiled, installed into the description, and inherited by descendants. The same path produces the machine's own organs and even its runtime, closing heredity and evolution within the machine.

Wanpeng Xie

Artificial LifeSelf-Improving AgentsSelf-Evolving Agents
AskPDF
Sep 2, 2026

LLM-as-a-Judge Is Not an Oracle: Why Self-Improving Agents Need Deterministic Guardrails

Self-improving agent pipelines have a problem at their center. An optimizer rewrites prompts to score higher, and the score comes from a judge that is itself an LLM. That judge has the last word on whether the system is getting better, and our position is that it has not earned it. The judge should be demoted from oracle to advisor: its verdict becomes one input among several, and every change is gated instead by a deterministic verification layer the judge cannot override. We reached this position by building the alternative and running it. Over months of running autonomous prompt-optimization loops in production across contract analysis, compliance review, and code quality, we cataloged eleven ways the evaluation signal failed, in four classes: judge bias, harness and metric failures, ground-truth errors, and reward hacking. Agents achieved perfect scores by reading cached answer keys from their environment, a 100% pass rate concealing 68% true capability. A corrupted ground-truth label caused the optimizer to delete correct compliance rules to agree with it. A syntactically broken prompt was promoted as the winner because a silent parser fallback improved the metric. Attempts to fix the judge by rewriting its rubric plateaued; the only reliable gain came from a structural constraint on its output order. In response we describe PROCTOR, a Teacher-Student loop in which a stateful orchestrator holds all tool access, stateless subagents diagnose failures and draft mutations they cannot apply, and a Teacher grades those mutations under five deterministic guardrails: hermetic sandboxes, capability-disjoint roles, acceptance checks that outrank the Teacher, frozen holdouts, and canary cases engineered so that a perfect score is itself evidence of cheating. We report the failures this prevented, and, because the Teacher is itself an LLM judge, the failures it did not.

Vansh Wahi

AI Research Engineer

LLM-as-a-JudgeSelf-Improving AgentsAutomatic Prompt OptimizationReward Hacking
AskPDF
Sep 1, 2026

Harness-of-Harness: Multi-Day Autonomous Software Development with Continual Improvement

This paper studies autonomous software development, in which LLM-based coding agents transform high-level requirements into complete, functional, and usable software systems without human intervention. We introduce Harness-of-Harness (HoH), a framework that enables coding agents to continually improve software during autonomous development. HoH operates on existing coding-agent harnesses, and organizes their executions into iterative planning-coding-testing loops. To sustain improvement across loops, HoH balances repair with capability growth, scopes development into small and verifiable increments, separates implementation-time testing from independent evaluation, and constrains verifiable outputs rather than prescribing agent workflows. It progressively exposes deliverables, role-specific tools, and skills, encourages reuse rather than recreation, and maintains versioned project histories. On GameCraft-Bench, FrontierSWE, and ProgramBench, three harness-model pairs (Codex with GPT-5.5, OpenCode with DeepSeek-V4-Pro, and Pi with MiniMax-M3), HoH consistently outperforms the corresponding standalone harnesses, achieving an average relative gain of 52.25 percent and a maximum gain of 82.86 percent after three iterations. In a multi-day deployment with more than 70 iterations, HoH autonomously develops a first-person-shooter game, featuring a coherent storyline, fully implemented core mechanics, human-playable experience, polished visuals and integrated audio. Github: https://github.com/Flesymeb/HarnessOfHarness Project Page: https://flesymeb.github.io/HarnessOfHarness/

Haoyang Yan, Min-le Su, Hangfan Zhang +6

Shanghai Artificial Intelligence Laboratory

Agent Harness OptimizationSelf-Improving AgentsLong-Horizon LLM AgentsLLM Agent Harnesses
AskPDF
Aug 31, 2026

Recursive Criticality of AI Self-Improvement

AI is increasingly used in the R&D process that produces future AI systems. We study the conditions under which this feedback becomes self-amplifying. Our model describes how the rate of AI capability growth depends on baseline research productivity, recursive feedback, and the increasing difficulty of research progress. We derive a recursive reproduction number, RAI\mathcal{R}_{\mathrm{AI}}, that determines whether improvements are amplified or damped across development cycles. This quantity compares the strength of feedback with the rate at which further progress becomes more difficult. When RAI>1\mathcal{R}_{\mathrm{AI}}>1, the effects of improvements compound across development cycles, placing the system in a self-amplifying regime. When RAI<1\mathcal{R}_{\mathrm{AI}}<1, their effects weaken across cycles. The transition depends on the structure of the AI R&D feedback loop and need not occur at any particular level of model capability. A system can therefore enter a self-amplifying regime before acceleration becomes visible, while rapid progress can also occur without self-amplification. Higher baseline research productivity can accelerate progress without changing whether the system is self-amplifying, but the duration of the development cycle becomes a limiting timescale for amplification. Increasing research difficulty can end a period of self-amplification. Extending the model to multiple research actors shows that improvements shared across organizations can make the overall research ecosystem self-amplifying even when no individual actor is. The framework identifies measurable properties of AI R&D systems that can help distinguish recursive amplification from rapid progress driven by other sources, including the strength of recursive feedback, how effectively improvements propagate into successor systems, cycle duration, and the increasing difficulty of further progress.

Mikhail Burtsev

London Institute for Mathematical Sciences

Self-Improving AgentsRecursive Self-Improvement
AskPDF
Aug 31, 2026

SCAFFOLD: Self-Improving Web Agents via Recursive Parametric Skill Abstraction

Web agents need to navigate visually rich, long-horizon interfaces that change across sites, yet most previous agents still learn each task in isolation and discard the procedural knowledge they accumulate. Recent skill-augmented frameworks take an important first step, but they treat the skill library as a flat or two-tier prompt-side cache and offer no principled mechanism for compressing redundancy or composing skills recursively. We introduce Scaffold, a self-improving framework for visual web agents that (i) induces parametric, executable skills from successful trajectories under a multi-instance abstraction constraint, (ii) maintains a recursively composed hierarchy in which higher-level skills invoke lower-level ones, (iii) compacts the library via a minimum-description-length (MDL) criterion and behavioral equivalence checking, and (iv) periodically distills skill-augmented trajectories back into model weights to internalize the abstractions. Across WebArena, VisualWebArena, and a held-out split of Online-Mind2Web, Scaffold improves success rate by 11.111.1--17.217.2 absolute points over the strongest skill-augmented baseline and shows monotonic gains across five self-improvement iterations without library collapse. We release the code and documents in the Github repository.

Bowei He, Xiaokun Zhang, Meng Ding +1

MBZUAI · McGill University · CityUHK +1

Web AgentsLLM Agent Skill LearningSelf-Improving Agents
AskPDF
Aug 30, 2026

Auditing Harness Tampering in Self-Improving Agents

Self-improving agents iteratively modify their own harness to push the frontier of their performance. However, such modifications can produce illusory performance gains or compromise integrity constraints such as authorization, provenance, and completeness without genuinely improving capability. We term this phenomenon as harness tampering, which extends the concept from reward and measurement tampering to the full self-improvement lifecycle. To systematically study this problem, we propose a two-axis taxonomy that categorizes each misaligned edit by the harness functional role in which it occurs and the obligation it violates. Then we build an annotated corpus by seeding tampered-benign edit pairs into the real trajectories of self-improving agents. We adapt and benchmark diverse audit methods on tampering classification and localization tasks. Finally we systematically audit real trajectories of self-improving agents. The results demonstrate that harness tampering consistently occurs in real runs from different agents, often persists in the lineage of the best agent, and forms distinct system-specific profiles across the taxonomy.

Xing Wang, Xiaoyi Zhang, Jie Shao

University of Electronic Science and Technology of China

AI Agent AuditingSelf-Improving AgentsAgent Harness Optimization
AskPDF
Aug 30, 2026

Self-Aware Active Learning Enables Continual Improvement in Autonomous Driving

Learning-based autonomous driving (AD) systems can perform reliably in familiar conditions, yet rare distribution shifts and long-tail events remain a major source of abrupt failure. A central limitation is that most agents learn primarily from passive experience and lack mechanisms to estimate when their competence is insufficient, seek timely assistance, and convert safety-critical encounters into targeted improvement. Here we present self-aware guided exploration (SAGE), an active learning framework for post-training adaptation in AD. SAGE learns a predictive world model that generates two online intrinsic signals: fear, which estimates short-horizon predictive risk and model uncertainty, and curiosity, which measures novelty through prediction error. Curiosity adaptively calibrates the intervention threshold for fear, allowing the agent to regulate risk in a context-dependent manner. When predicted fear exceeds this adaptive threshold, the agent transfers control to an expert or fallback policy and uses the resulting takeover trajectories for focused imitation learning. In parallel, fear is integrated into policy optimization and evaluation as a safety-oriented constraint to reduce performance regressions during adaptation. We evaluate SAGE in simulated route-transfer tasks, Waymo-based logged driving scenarios, CARLA occlusion hazards, and real-world mobile robot navigation tests. Across these settings, SAGE improves robustness in novel and safety-critical scenarios, reduces safety violations, and maintains task performance comparable to strong baseline policies. These results suggest that agents can improve after initial training by estimating the limits of their competence, requesting guidance when needed, and learning selectively from rare high-value events.

Dong Hu, Chao Huang, Carman K. M. Lee +1

Department of Industrial and Systems Engineering, The Hong Kong Polytechnic University, Hong Kong · School of Electrical and Mechanical Engineering, Adelaide University, Australia · Department of Computer Science, University College London, United Kingdom

Active LearningAutonomous DrivingInteractive Imitation LearningSelf-Improving Agents
AskPDF
Aug 30, 2026

CineForge: Self-Improving Agents for Long-Horizon Video Generation

Long-horizon story-driven video generation requires a production agent to coordinate narrative decomposition, state tracking, shot design, prompt construction, rendering, and revision across interdependent scenes. Existing adaptive video systems primarily refine requests or reusable skills, leaving recurring production failures disconnected from persistent, stage-targeted improvements across stories. We introduce CineForge, a self-evolving video-production agent framework that couples CineForge-Produce for video generation with CineForge-Evolve for cross-story policy evolution. CineForge-Produce organizes each source story into typed narrative, character, spatial, and cinematic states, uses them to coordinate asset and clip generation, and records the process as a canonical production trajectory. CineForge-Evolve applies Case-to-Pattern-to-Policy Evolution (CPPE) to review trajectory evidence, consolidate recurrent findings into bounded stage-local patches, and deploy validated updates through structural replay and confidence-controlled paired evaluation. To measure complete story realization, we introduce CineScope, which combines a 100-script CineScope-Data suite with a human-aligned, multiscale CineScope-Metric spanning causal state, directorial orchestration, pacing and resource allocation, and character arc. Across CineScope-Data and two public benchmarks, the evolved CineForge policy improves CineScope-Metric from 4.024 to 4.380, outperforms three long-video baselines with consistent gains under ScriptAgent, and reduces review LLM calls by 37.0% on new stories. These results establish production trajectories as actionable experience for video agents that improve cumulatively across long-form storytelling tasks.

Junxiang Liu, Lin Wang, Haiyu Shi +10

Tongji University, Shanghai, China · Kuaishou Technology, Beijing, China · Fudan University, Shanghai, China

Long-Horizon Video GenerationAgentic Video GenerationMulti-Shot Video GenerationSelf-Improving AgentsLong-Horizon LLM AgentsVideo Generation Evaluation
AskPDF
Aug 25, 2026

Recursive Experiential-Working Memory Evolution for Long-Horizon Agent Harnesses

Recursive self-improvement (RSI) remains hard in long-horizon tasks, where growing histories obscure the task state and misalign skill invocation. We introduce Recuris, a recursive Experiential-Working Memory architecture for long-horizon agent harnesses, in which Working Memory tracks task progress and guides skill selection from Experiential Memory, grounding skill use in current needs rather than the full history. This coupling also turns execution into structured evidence that localizes failures to specific memory components. Across tasks, a fixed Meta-Agent turns that evidence into localized, validation-gated updates to Skill Memory that reshape execution and yield new evidence, forming a bounded recursive memory-evolution loop. Across four long-horizon benchmarks and ten models, Recuris improves task success in 35 of the 37 completed model-benchmark pairs, carrying frontier models to SOTA-level task success: on tau-bench it adds +17.8 points to GPT-5.6 Sol and +15.6 to Claude Opus 5, taking Opus 5 to 87.9%, and +16.6/+13.5 points on Qwen3.6-27B/35B on SkillFlow. The advantage widens as the interaction horizon grows, to +32.2 points on the longest tasks, and common long-horizon failures fall by up to 80%. These results position recursively evolving memory as a scalable foundation for RSI, enabling agents to continuously transform accumulated experience into increasingly effective long-horizon behavior. Code: https://github.com/Gen-Verse/Recuris

Zhaochen Yu, Yingcheng Wu, Zhenfei Yin +5

NUS · Princeton University · Stanford University +1

Long-Horizon LLM AgentsMemory-Augmented AgentsSelf-Improving AgentsRecursive Self-ImprovementLLM Agent Skill LearningLong-Horizon Reasoning
AskPDF
Aug 25, 2026

CAFE: Self-Improving Search Agents Need Co-Evolving Feedback

Reliable search requires more than acquiring external evidence. An agent must also recognize and recover from errors as its trajectory unfolds. In-trajectory feedback provides a mechanism for such recovery by diagnosing where the search has drifted and redirecting subsequent reasoning steps. This is particularly important in long-horizon search, where an early directional error may receive no immediate corrective signal and can compound across later steps. Making such feedback learnable, however, creates a coupled problem: the agent must learn when to request and use feedback, while the critic must learn corrections from outcome-confounded rollouts as the agent's failure patterns evolve. We introduce CAFE (Coupled Agent--Feedback Evolution), a framework in which a shared-parameter model alternates between search-agent and critic roles. CAFE initializes feedback-conditioned recovery from trajectories built around the base agent's own failures, then couples online and offline optimization. During online RL, a comparative feedback estimate uses a prompt-level call--skip success gap to shape request returns, while feedback-aware advantage shaping reweights token advantages before and after feedback. Offline, rollout-derived preference optimization learns feedback from matched successful and unsuccessful trajectories. On seven agentic search benchmarks, CAFE outperforms the evaluated RL-based search agents on average, retains its gains across all six out-of-domain benchmarks, and reduces answer-level hallucinations. One-sided ablations show that improving only the agent or only the critic eventually plateaus, whereas alternating the two updates continues to improve performance. These findings suggest that a self-improving search agent needs feedback that co-evolves with the policy it guides.

Boyang Liu, Senjie Jin, Peixin Wang +17

Fudan University · LLM Department, Tencent

Agentic SearchSelf-Improving AgentsAI Agent ReliabilityError FeedbackRL for LLM AgentsActor-Critic Methods
AskPDF
Aug 25, 2026

Metan^n: Recursive Self-Improvement through Emergent Depth

Self-improving LLM agents refine answers, not the process that produces those answers. Systems that add a meta-level hold that level fixed, and those that edit themselves must leave part of their own editing machinery untouched to stay stable, capping the meta-depth they realize at roughly two. We present Metan^n, which keeps the meta-operation fixed and recurses on its input instead. That operation, ΩΩ, is applied repeatedly to its own products, reading the traces of the solver stack below together with the code that produced them, then writing the next layer as a strategic pre-process and a library of callable helpers. Because ΩΩ never changes, it cannot destabilize the system, and because its input strictly grows, each layer reasons from a higher vantage than the last. Depth is set by convergence rather than fixed in advance, and an evolutionary archive searches over layer chains. Across two backbones, Metan^n outperforms prior self-improving agents on all eight benchmark families. The sharpest case is ARC-AGI-2, built to resist skill memorization, where it alone scores above zero. Ablations indicate that most of the gain from recursion comes from the conditioning each layer passes to the next, and distinct layer roles emerge with depth although no prompt prescribes them. Code available at https://github.com/minnesotanlp/meta-n

Zae Myung Kim, Young-Jun Lee, Seungyeon Jwa +1

University of Minnesota · Seoul National University

LLM Agent Self-ImprovementSelf-Improving AgentsRecursive Self-Improvement
AskPDF
Aug 18, 2026

On the Fragility of Self-Improving Agents: Variance, Task Order, and Underspecification

Memory-based self-improving agents--those that learn from an online stream of tasks and improve over time by maintaining a textual memory bank--have shown great promise in recent literature. However, the reliability aspects of these methods have been critically overlooked. In this work, we conduct a comprehensive re-evaluation of two memory-based methods, broadening the scope of evaluation along two axes: (1) including multiple self-improving runs to quantify variance, and (2) shuffling the tasks to investigate the effect of task order. Through these experiments, we make two observations that expose the fragility of current methods: First, agent evaluation is inherently noisy in complex environments and on multi-step tasks, and stacking a self-improving loop on top can further amplify this noise. Second, the agent's improvement is highly dependent on task order. Prior works often adopt default orderings that impose an implicit curriculum, acting as a hidden prerequisite for success. To better understand this fragility, we manually examine the agents' memory and hypothesize that task and environment underspecification contribute to this fragility. We validate this hypothesis by incorporating information that enables better specification, such as detailed rubrics and environment feedback, into the memory construction process. While this added information partially closes the performance degradation in previous experiments, significant gaps still remain, suggesting that other uncharacterized factors contribute to this fragility. Looking ahead, our work advocates for more rigorous evaluation protocols for self-improving agents by reporting results across multiple runs and stress-testing them under challenging conditions. Moreover, our findings on underspecification call for systems and interfaces that enable effective human oversight, preventing agents from failing in unforeseeable ways.

Qinyuan Ye, Yu Li, Yada Pruksachatkun +2

Salesforce AI Research

Self-Improving AgentsMemory-Augmented AgentsLLM Agent ReliabilityLLM Agent Evaluation
AskPDF
Aug 13, 2026

AdsWorldEngine: A Self-Evolving Conversational Advertising Agent through Orchestrator and Tool Coevolution

Conversational advertising aims to deliver useful ads within multi-turn assistant interactions. Unlike conventional query-based advertising, where the user's intent is often expressed in a short standalone query, conversational ads must infer latent commercial intent from the current user query, the assistant response, and dialogue history while also deciding whether an ad would be helpful rather than intrusive. We propose AdsWorldEngine, an agentic framework for conversational advertising. AdsWorldEngine uses an Opportunity Gate to determine whether ads should be shown, an Orchestrator to generate commercial intents, call advertising tools, and construct a top-3 ad slate, and an Evaluator to score delivered ads for offline optimization. The central contribution is an iterative actor-tool training procedure: we first train the Orchestrator with supervised fine-tuning and agentic reinforcement learning, then use high- and low-reward rollouts to construct preference data to train tools. This creates a self-improving loop in which the system learns not only how to use advertising tools, but also how to improve them from rewarded behavior. To support subjective production decisions, we introduce label grounded judgment modeling, which trains judgment models from human labels collected under explicit guidelines. It enriches labels with thinking traces, filters inconsistent rationales through reflection, and further optimizes binary judgments with a cost sensitive GRPO variant that preserves asymmetric reward gaps. Offline, AdsWorldEngine improves diversity by 60% and relevance by 80% over the current production ad delivery system. In an online A/B test, it increases RPM by 22% and ads coverage by 74%.

Simiao Zuo, Chenhui Xu, Yimeng Jia +3

Microsoft Redmond, WA, USA

Online AdvertisingTool-Using AgentsSelf-Improving AgentsConversational Agents
AskPDF