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

198 papers31 papers in the last four weeks, down 47% on the four weeks before. 0.2% of all new papers.

Nov 17, 2026

Do LLM Agents Still Need to Be Told How to Self-Improve?

LLM agents increasingly drive their own learning. Self-improvement methods delegate various components of model optimization to the models themselves. As models become more capable, this motivates a basic question: do these increasingly capable models still need us to specify how they should self-improve? In this paper we study an autonomous paradigm in which, given basic primitives, resources, and a general goal for self-improvement, agents construct their own self-learning algorithm for context-based optimization. Using the setting of gameplay as a testbed, a frozen LLM agent is given a compute budget and tools for collecting experience and updating text documents, and allowed to freely experiment without an externally imposed loop or access to real-world data. We find that sufficiently capable models do self-improve under these conditions, demonstrating strategies that align with classic cognitive frameworks for self-regulated learning and constructs from machine learning literature on self-generated curricula. Furthermore, we study the extent to which the learned text artifacts transfer to external benchmarks, observing improvement across different game horizons, mechanics, and 3D navigation.
Nov 17, 2026

The Resolution Hypothesis: Agent Evolution's Key Is Identifying Improvements

Agent evolution follows a simple loop: a proposer writes candidate artifacts (prompts, skills, memories) and selection accepts those that score higher. This loop has shown promise, yet practitioners face a puzzle: methods trade wins across papers, and evolution often fails to bootstrap on certain tasks. We trace this puzzle to the Resolution Hypothesis: agent evolution stalls not because methods fail to propose better artifacts, but because noisy evaluations cannot reliably identify them. Across seven evolution methods and six models (over 10M LLM calls), we find support for the hypothesis at both levels where evaluation scores are used. At the candidate level (choosing artifacts), helpful candidate artifacts exist, but selection is no better than random at telling them from harmful ones, so errors accumulate across rounds. At the method level (ranking methods), typical margins of a few percentage points are smaller than the difference between two independent runs of the same method, so published rankings often rest on luck. Together, these findings indicate that agent evolution is often bottlenecked by reliably identifying improvements. This calls for a shift in how we develop and evaluate self-improving agents, from designing ever more candidate improvement systems to making true improvements detectable and accumulable.
Nov 17, 2026

Values Shape What Self-Improving Coding Agents Build

Self-improving agents are typically optimized for the results they produce, with less attention to how they produce them. Their instructions give designers limited ways to shape how they work, especially when the task is open-ended. This paper studies whether a short value statement in an agent's persistent instruction file changes not only how well the agent performs but also what it builds. Four higher-order value types in Schwartz's theory of basic human values were evaluated: openness to change, conservation, self-enhancement, and self-transcendence. Across diverse coding tasks, the values were held fixed within each run over multiple iterations of self-improvement. Three findings emerged: (1) Values matter for performance across a diverse set of tasks. The openness values increase performance on held-out data, whereas the opposite conservation values result in scores below those of an agent given no values. (2) Values change what agents build, producing solution algorithms that differ in size, complexity and approach. (3) Human oversight is still needed for designing values. Allowing the agent to revise its own values narrows the differences between sets of values, and values distilled from the AI literature provide no detectable gain over having no values. Properly designed values can thus influence what a self-improving coding agent builds and, where the task permits, how well it performs.
Nov 17, 2026

Harnesses That Improve Themselves: A Unifying Framework for Self-Improving Agent Harnesses

Whether a foundation model succeeds as an autonomous agent depends as much on its runtime software as on its weights. This runtime, the agent harness, manages context and memory, steers multi-turn control, executes tool actions in sandboxes, and verifies work before stopping. Because models differ in how they use tools and how they fail, a static harness tuned for one model or task often stalls, wastes tokens, or regresses on another. This bottleneck has driven a shift from prompt tuning to self-improving agent harnesses: systems that inspect their own execution traces, separate runtime bugs from model limits, and rewrite their own code. We present a unifying architectural and design framework for self-improving agent harnesses. The framework pairs four editable runtime components (context and state, agent control, action interfaces, and verification and recovery) with a four-stage loop that diagnoses failures, proposes code patches, validates candidates, and deploys updates. Using this framework, we show how optimizers trace errors across long trajectories and discover reusable runtime mechanisms such as pre-stop verifiers, loop breakers, and persistent memory. We further show why full-harness rewrites overfit or break across modules, and how modular updates with validation gates generalize across models while bounding token cost. To keep self-modification safe, we establish practical defenses against recurring failure modes including prompt bloat, benchmark gaming, and evaluator tampering. Finally, experiments on SWE-bench Lite validate this framework, showing that gated modular evolution outperforms prompt reflection and full-harness rewrites across models and repositories at a fraction of the token cost.
Nov 16, 2026

Evaluation-Free Recursive Self-Improvement for Coding Agents

Recent self-improving coding agents have achieved strong benchmark performance by iteratively modifying their own executable implementations. A common pattern uses downstream task-derived evidence to decide which candidates or lineages continue evolving, which we term evaluate-and-select. Obtaining this signal requires repeatedly executing evolved agents on downstream tasks, so broader exploration incurs increasing evaluation cost, while repeated optimization against a fixed evaluation distribution may encourage benchmark-specific adaptation. We ask: can coding agents self-improve without downstream task evaluation inside the evolution loop? We introduce Explore-then-Integrate (ELITE), which integrates implementation mechanisms rather than selecting a single exploratory child to continue the lineage. At each generation, ELITE proposes diverse focused improvements, implements them independently from the same parent, and inspects the resulting programs to identify complementary, redundant, and conflicting mechanisms before reimplementing a compatible subset as one coherent descendant. No downstream task outcomes or task-solving trajectories of evolved candidates are used to guide evolution; only deterministic checks of structural and operational validity are used inside the loop. On SWE-bench Pro, ELITE improves the initial agent from 60.0% to 85.6%, compared with 86.7% for the Darwin Godel Machine (DGM) and 88.3% for the Huxley-Godel Machine (HGM), while using zero candidate task evaluations and reducing observed wall-clock evolution time by 8.8x and 3.2x, respectively, under the evaluated configurations. In cross-benchmark transfer without further adaptation, ELITE averages 73.3% on SWE-bench Verified and 69.3% on Polyglot. Together, these results demonstrate the feasibility of coding-agent self-improvement without downstream candidate task evaluation in our setting.
Nov 16, 2026

From Recursion to Convolution: Parallel Self-Improvement for Multi-Agent Systems

Multi-agent self-improvement enables agents to improve through interaction and feedback. However, sequential dependencies across agents and refinement rounds can propagate errors, increase computational costs, and limit parallelism. Moreover, refining individual features or agents in isolation can overlook their dependencies and restrict collective coordination. To address these challenges, we propose ConvRSI, a framework for parallelizing multi-agent self-improvement through convolution. ConvRSI couples intra-agent convolution, which jointly refines related agent features, with inter-agent graph convolution, which aggregates messages according to the collaboration topology. Both stages operate in latent space, enabling parallel updates without repeatedly decoding and re-encoding intermediate messages. Experiments on MATH-500 show that ConvRSI achieves 5.04% performance improvement while reducing 17.27% inference cost, and 45.11% latency compared with RecursiveMAS. It also supports diverse collaboration patterns by representing their topologies as adjacency matrices. These results demonstrate the potential of convolutional co-evolution for efficient multi-agent self-improvement. Our code and datasets are provided in https://github.com/LYA2333/ConvRSI.
Nov 14, 2026

CompoundingKernel: Self-Improving from Zero to First

We present CompoundingKernel, a self-improving agent system that writes GPU kernels by search. As of 2026-11-11, its generated kernels rank #1 on the public L1, L2 and Quantization boards of SOL-ExecBench (NVIDIA B200). They have held #1 on L1 since 2026-10-27, albeit a short loss on 2026-11-07. All 235 problems have a site-verified correct kernel; on the 209 public-board problems they are 4.40x faster than the benchmark's reference baseline. The search starts from zero: agents get each problem's PyTorch definition but no reference kernels or official scores. A per-problem archive outside the model holds every correct kernel and its lineage. An LLM controller reads it, picks a parent or a new design, and gives each parallel child agent one direction. Checks outside the model decide correctness. At equal wall time, it beat a coded UCB style tree on 35 of 38 problems by making 2.4x as many correct attempts. Over a thousand agents ran at once, and one warm restart fix raised their evaluation rate 3.6x. We find that the rate of reliable measurements, not the number of agents, limits how far such a search scales. Our code and kernels are available on URL.
Nov 13, 2026

ESI: An Embodied Self-Improvement Flywheel for LLM-VLA Agents

Independently pretrained language models and vision-language-action (VLA) policies provide complementary building blocks for embodied agents, but connecting them does not automatically produce coordinated behavior. The VLA may generate actions that diverge from the LLM's intended subtask and, upon regaining control after a correction, undo the promising state restored by the LLM. We introduce ESI (Embodied Self-Improvement), an automated flywheel that uses environmental interaction to align reasoning and action. ESI treats the modular agent as the unit of post-training, repeatedly refining the prompts that guide the LLM, the shared skill interface that expresses its intent, and the VLA parameters that realize that intent, then redeploying these components together. Our key insight is that collaboration itself can supply supervision for improving this interface. The LLM's subtask decisions provide semantic supervision for what the policy should execute, while its effective corrections and subsequent student continuations provide action-level supervision for recovery and handoff. The student also learns from its own effective execution, allowing locally useful experience to contribute even when the overall episode fails. On ten selected RoboDojo tasks, ESI achieves a mean Score of 62.03 and a mean success rate of 49.41% using an LLM-VLA agent without generating task-specific control code. On both metrics, it outperforms the published reference results of all hybrid embodied agents, including the Agent+WAM system GO-3 Nano Preview (47.27 Score and 36.60% success), as well as all compared code-based methods.
Nov 13, 2026

RecurIR: Learning When and How to Revise Restoration Policies via Recursive Self-Improvement

Agent-based image restoration has achieved promising performance by coordinating restoration tools to handle heterogeneous and coupled degradations. However, existing agents often improve their decisions through accumulated successful and failed executions, without explicitly identifying the conditions under which learned restoration strategies remain effective. Consequently, changes in degradation severity, spatial coverage, or interactions may invalidate previous decisions, while providing limited guidance on how these decisions should be revised. In this paper, we propose RecurIR, a recursive self-improvement framework that enables restoration agents to learn when and how to revise their decision rules. Specifically, we introduce a policy-hypothesis discovery mechanism to identify testable, condition-dependent rules through matched tool executions. We then design a rule-falsification-driven task evolution mechanism to generate targeted degradation variations, examine the validity of learned rules, and identify their applicability boundaries. Based on the resulting evidence, we develop a change-conditioned policy revision mechanism that learns how variations in degradation conditions should modify tool selection, execution order, operation strength, and processing regions. We further incorporate independent verification to retain effective revisions and use the resulting feedback to guide subsequent hypothesis discovery and task evolution. Through this recursive process, RecurIR progressively refines its restoration policies as degradation conditions change. Extensive experiments demonstrate the effectiveness of the proposed framework.
Nov 13, 2026

AutoRL: A Multi-Agent System towards Autonomous Reinforcement Learning

Recursive self-improvement (RSI) is one of the most promising paths toward an AI singularity for superintelligence. Achieving this vision requires AI systems to undertake the full training pipeline for iterative improvement. Reinforcement learning (RL) plays an essential role in this cycle to improve model capabilities and generalization, yet automating RL remains difficult due to unstable training dynamics and the need for sustained supervision. We introduce AutoRL, a multi-agent system for automating RL training, as a cornerstone for future RSI. Different from conducting research by end-to-end complete experiments, AutoRL monitors the evolving training state and integrates process-level supervision and research into an ongoing RL training, following the practical workflow of an RL researcher. Specifically, AutoRL consists of three RL-specific agentic roles. Perceptors track training dynamics, rollouts, evaluation, and efficiency, triggering deliberation when they detect anomalies, degradation, or stagnation. Three complementary Proposers diagnose problems and refine candidate interventions through shared evidence and checks. The Orchestrator reviews their recommendation and applies approved changes through online hot updates or checkpoint-based resumption. Experiments on Qwen3 and LongCat-Flash-Lite demonstrate the superiority of AutoRL over static RL recipes and a general agent. The research records show that existing agents can handle unattended RL supervision and dynamic adjustment. The difficulty for future RSI lies in developing fundamental methods that are valuable for resource-consuming validation.
Nov 11, 2026

Reward-Driven Collider Physics Challenges for Self-Improving Agentic AI via Reinforcement Learning

Recent advances in agentic AI have demonstrated the potential to automate complex high-energy physics (HEP) workflows. We focus on the regime of HEP tasks where frontier models still struggle to provide correct and complete solutions, and introduce an open-ended optimization task format with continuous, automatically evaluated rewards. Unlike conventional benchmarks focused on task completion, these tasks target reinforcement learning (RL) environments to generate agentic improvement on state- of-the-art HEP challenges. We benchmark frontier reasoning models on several HEP tasks and demonstrate an initial proof of concept in which a small language model improves through RL using automated feedback without human intervention. By connecting challenging HEP problems with verifiable scientific rewards and RL, we aim to advance agentic AI from reproducing established workflows to autonomously discovering better scientific solutions, paving the way toward self-improving scientific agents.
Nov 11, 2026

Verify by Doing: Co-Evolving Agent Execution and Evaluation without External Feedback

Agent self-improvement requires feedback about task success, yet external feedback may be unavailable at test time. Agents must then infer success from observable evidence, and incomplete verification can misguide subsequent updates. We introduce Verify by Doing (VbD), a method that co-evolves Actor and Evaluator harnesses within a single task while keeping model weights fixed. The Evaluator actively inspects artifacts and environment state with tools; its findings ground an internal signal for output selection and guide updates to both execution and verification procedures. Proposed Evaluators undergo comparative review on common candidates, while Actor updates require support from their own fresh outputs. Across AutomationBench, τ3τ^3 Banking, and selected GDPval tasks, VbD achieves the highest overall scores among the compared methods operating without external feedback, with gains of 3.3, 4.1, and 2.3 percentage points over the strongest baselines on the main backbone. Ablations support the contributions of active verification and Evaluator evolution, and selection from fixed candidate pools shows that improved verification can recover successful outputs without generating new ones.
Nov 10, 2026

Toward Autonomous RTL and Synthesis Optimization: Benchmarking and Self-Improving Agents

Recent advances in large language models (LLMs) and autonomous agents are creating new opportunities for hardware design optimization. This paper examines three connected directions toward autonomous RTL and synthesis optimization: (1) Realistic benchmarking. We discuss reference-based and open-ended RTL optimization benchmarks that evaluate optimization opportunities under realistic EDA workflows. (2) Tool-grounded RTL optimization. We present Dr. RTL, a multi-agent framework that automates critical-path analysis, RTL rewriting, and implementation-level evaluation, while continuously improving through reusable optimization skills. Evaluated on 20 real-world RTL designs, Dr.~RTL achieves average WNS/TNS improvements of 21%/17% with a 6% area reduction over commercial synthesis. (3) Design-specific synthesis optimization. We explore agent-driven synthesis script tuning and the discovery of executable synthesis algorithms across intermediate representations, technology-independent optimization, and technology mapping. Finally, we envision AI-native design automation that jointly explores architectural, RTL, and EDA algorithm design spaces, guided by verification constraints and implementation feedback.
Nov 9, 2026

RoboACE: Adversarial Co-Evolution for Robot Self-Improvement

Robot agents can improve reusable skills, planning procedures, and recovery strategies from execution feedback, yet a fixed practice source leaves the search for new weaknesses unchanged. Useful practice depends on the agent's current capabilities, so the procedure that chooses practice must also be revisable. We present RoboACE (Robot Adversarial Co-Evolution), a framework that jointly evolves curriculum and execution harnesses around frozen foundation models. The curriculum harness uses accumulated capability evidence to propose informative challenges, while the execution harness responds with reusable revisions that expand execution capabilities. Alternating updates hold one side fixed as the other changes, and admitted challenges form fixed snapshots for comparing execution revisions. Starting from a compact set of LIBERO practice conditions, the resulting frozen deployment outperforms the evaluated controllers and agent systems across four LIBERO-family panels. On LIBERO-PRO, it reaches 74.0% success, exceeding the initial deployment by 15.0 percentage points and direct execution by its VLA controller by 13.5 points. Case studies document changes to evidence-guided practice selection, drawer-skill grounding, and controller intervention.
Nov 7, 2026

ReSkill: Selective Self-Improvement for Robot Manipulation

Self-improvement on compositional manipulation tasks requires deciding what to reuse, where to improve, and which changes to retain. We present ReSkill, a selective self-improvement framework that concentrates revision on capability gaps. A coding agent constructs an object-centric task graph from an instruction and a skill library, then uses node-level execution records to locate failures. At the task level, it revises stage organization, hand-off conditions, and recovery routes; at the skill level, it strengthens perception, motion, manipulation, and verification capabilities that repeatedly fail. Candidate revisions undergo full-task evaluation and paired comparisons before adoption, allowing local changes to accumulate into validated skills and an independently executable policy. The agent participates only during development; the deployed policy calls the retained skills without invoking the agent at run time. On the same development set, average success across ten RoboDojo tasks rises from 30.0% for the initial versions to 86.2% for the final adopted programs; retained programs achieve 83.6% in recorded robustness and model-selection evaluations. Across eight real-world tasks, ReSkill succeeds in 72 of 80 rebuilt-simulation trials and 62 of 80 real-robot trials (77.5%). The median revision changes only three functions, approximately 0.5% of a program, while 39% of task-specific functions in later-added tasks directly reuse existing implementations. These results show how locating local deficiencies, validating candidate changes, and accumulating reusable skills can improve execution of compositional manipulation tasks.
Nov 6, 2026

Recursively Self-Improving Electromagnetic Spectrum Agents: Architecture and Operation

Electromagnetic spectrum agents (ESAs) must contend with changing environments and task requirements during sustained autonomous operation, yet their existing capabilities may not remain suitable for new operating conditions. This article proposes recursively self-improving electromagnetic spectrum agents (RSI-ESAs) that use operational feedback to update their capabilities and build on prior improvements. We present their architecture and editable components, and describe a self-improvement process encompassing problem diagnosis, candidate generation, validation, and inheritance. By retaining effective task versions and using modification records and diagnostic knowledge to guide subsequent updates, RSI-ESAs can accumulate task capabilities and improvement experience across successive rounds. A shared-spectrum scheduling case study illustrates improved task performance and capability accumulation over multiple improvement rounds under the tested conditions. Finally, we discuss open challenges for broader tasks and long-term operation, outlining research directions for the continued capability development of ESAs.
Nov 6, 2026

A Controlled Study of Models, Skills, Feedback, and Curriculum in Agentic Robotics

Agentic robotics asks coding agents to implement and iteratively improve robot policies from simulated and real-world physical interactions. We study the self-learning loop of agentic robotics through a controlled simulation study spanning nine manipulation tasks, 631 different experiment configurations, and 28K coding agent rollouts, systematically varying model capability, skill priors, feedback structure, and curriculum. The experiment data suggests that the bottleneck is often not the access to sufficient information, but interpreting it into the right policy update. Across these factors, a successful self-learning loop depends on how effectively agents attribute failures, reason task-relevant spatial and geometric structure, and selectively restructure code to improve policies.
Nov 6, 2026

Flex-RSI: Benchmarking Recursive Self-Improvement of Frontier Agents

Frontier language models are increasingly deployed as agents, and how well an agent performs depends not only on its model but also on its harness: the prompts, tools, memory, and control loop through which the model acts. When an agent is applied to a new problem, a natural question is whether it can use the feedback of the task to improve the way it works, and not merely its answer. Most existing benchmarks keep the agent's harness fixed and score the solution it produces, or target large-scale model training. We introduce Flex-RSI, a benchmark for the recursive self-improvement of agents on vision and robotics tasks under a fixed budget. In each round, an executor improves the task solution, which is kept only if it scores higher on held-out validation data, and an improver then revises the harness, including the executor and itself. Every run starts from the same general-purpose harness, and the final solution is scored on hidden test data. Evaluating closed-source and open-weight models on tasks spanning perception, reasoning, robot action, 3D reconstruction, visual creation, and infrastructure, we find that self-improvement helps most when the agent builds its own solution, that feedback recording only success or failure holds back open-weight models, and that open-weight models fall furthest behind where outputs must pass strict checks of physical stability or exact correctness. Paired runs further show that editing the harness itself contributes to the gains.
Nov 5, 2026

Learning the Task or Learning the Verifier? Rethinking Criteria Exposure in Embodied Self-Improvement

Self-improving embodied agents are increasingly being developed and compared on robot simulation benchmarks. Several recent works expose the benchmark's success criteria to the learning agent, a practice we call Criteria Exposure (CE). These criteria, originally written to verify policies trained by imitation learning, often demand more than the corresponding language instructions, so a score from such a verifier may not faithfully reflect whether the instructed task was completed, especially for robot-control programs written by an agent. As embodied coding agents report ever higher benchmark scores, a natural question arises: when a coding agent is exposed to the benchmark's criteria, does it generate code that better performs the instructed task, or code that simply overfits to the verification criteria? We conduct controlled experiments with a self-improving agent with and without CE, and find that with CE the agent quickly produces code with a higher success rate under the given criteria, but this advantage disappears when the criteria are changed slightly without departing from the original instructions. More importantly, the skills the agent develops under CE transfer poorly across tasks. We further propose instruction-faithful criteria and show that they better reflect the performance of agent-generated programs.
Nov 2, 2026

CUA-Master: Scaling Computer-use Agents through Open-World Recursive Improvements

Despite recent advances in CUAs, their development remains constrained by the limited diversity, controllability, and reliability of interaction data. Moreover, conventional optimization pipelines lack iterative feedback, while existing recursive improvement approaches often rely on self-generated experiences, limiting ability expansion and yielding diminishing returns. To address these challenges, we introduce CUA-Master, a nested double-loop recursive improvement framework. At the system level, an outer world-data-model flywheel continuously incorporates open-world corpus and leverages evolving model weaknesses to guide subsequent data construction and optimization iterations. At the data level, an inner flywheel couples open-world seeding and autocatalytic propagation. The former mines authentic workflows as seed tasks from instructional videos, and employs visual-semantic dual-path trajectory reconstruction; The latter transforms these seeds into reusable primitives for controllable synthesis of diverse, complex, and verifiable tasks. To enable efficient and reliable trajectory collection, we further introduce a feedback-guided snapshot-rollback retry mechanism in various real environments. Extensive experiments demonstrate that CUA-Master-27B achieves competitive performance across GUI-only and GUI-CLI hybrid benchmarks, scoring 80.2 on OSWorld Verified, 36.9 on OSWorld 2.0, 43.9 on WeaveBench, and 25.0 on Agents' Last Exam. Our framework also substantially improves the quality and efficiency of data synthesis, and exhibits continuous gains across recursive iterations.
Nov 2, 2026

Reimagining computational quantum research with AI scientists

AI scientists are expanding automated research across scientific domains, yet their ability to turn the scientific record into a foundation for autonomous discovery remains elusive. Here we uncover a fundamental barrier to this transition and demonstrate a route to overcome it in computational quantum science, where advances shape both what we can learn from complex quantum systems and what quantum computing can ultimately deliver. To identify this barrier, we introduce OmniQ, an expert-audited virtual research environment that converts published studies into executable reproduction tasks. Across 59 papers spanning classical simulation, quantum algorithms and quantum-property characterization, we systematically evaluate five agentic systems powered by large language models and six third-party agent harnesses. Our findings reveal that current AI scientists often fail to reproduce published results, exposing a fundamental mismatch between what scientific papers communicate and what autonomous agents require. By contrast, human expert intervention can turn these failures into successful reproductions, showing that the missing information can be identified and converted into reusable research experience. Guided by this observation, we develop Residual Agents (RA), a quantum-tailored self-improving AI scientist that distils externally verified workflow repairs into such experience. RA substantially improves research performance under fixed base models and limited adaptation budgets. For example, RA raises DeepSeek V4.1 Flash performance from 68% to 85%, matching Claude Code with Opus 5 at a third of its cost despite using a weaker base model. We integrate all reproduced results into an extensible platform built on the model context protocol, making verified research workflows directly accessible to AI scientists and allowing new scientific papers to be continuously incorporated.
Nov 2, 2026

SelfImprove-Bench: Evaluating Generalization in Self-Improving Agents

Recursively self-improving (RSI) systems are increasingly viewed as a promising means of accelerating progress toward artificial general intelligence. They aim to autonomously improve their capabilities by refining their working pipelines and recursively improving the strategies that guide subsequent refinements, with gains generalizing to unseen scenarios.However, existing evaluations lack reliable metrics to distinguish capability gains from scenario fitting, sustainable and extensible protocols for unseen tasks and difficulties, and fine-grained attribution of improvement to evolution traces. To this end, we propose SelfImprove-Bench,an RSI evaluation framework that organizes tasks into three primary capabilities (i.e., Exploring, Planning, Reasoning) as scenarios for guiding model evolution. We instantiated the tasks on games for controllability and reproducibility, and pairs them with scalable generation and orchestration driven by task templates and difficulty coefficients. Beyond task-level scores, SelfImprove-Bench organizes evaluation into generalization ladder levels G0 to G4 that measure how far gains transfer from training conditions. Experiments reveal that the evolutionary gains of existing RSI methods are inconsistent across generalization levels.
Nov 1, 2026

Recursive Self-Improvement of Exoskeleton Assistance Policies through Human-in-the-Loop Feedback

To reduce reliance on manual design and extensive parameter tuning, a framework for the autonomous evolution of exoskeleton assistance policies through human feedback is proposed. Assistance policies are autonomously generated as executable control code by an intelligent agent and evaluated in experiments with human participants. Subjective user feedback, movement performance, and muscle activation measurements are incorporated into policy assessment. Based on these assessments, policy deficiencies are autonomously identified and the control code is revised by the agent for subsequent trials. A closed loop of policy generation, human feedback, evaluation, and autonomous refinement is thereby established. The framework is evaluated using GPT, DeepSeek, GLM, and Kimi, and initial assistance performance and refinement outcomes are compared across models. Despite differences in initial performance, effective assistance is achieved with all four models after a single autonomous refinement iteration under the tested conditions. Across three tasks, biceps and triceps muscle activation levels are reduced by 29.4% and 35.2%, respectively, compared with those measured without an exoskeleton. However, limited adaptability to unexpected situations is observed, indicating that further improvements in robustness and safety are required.
Oct 29, 2026

KARMA: Training-Free Knowledge-Atomic Harness Evolution for Industrial Advertising Agents

Industrial advertising agents must continually adapt their decision knowledge to changing product offerings, traffic patterns, and operating policies. We present KARMA (Knowledge-Atomic, Regression-Gated Modular Adaptation), a training-free framework that evolves six typed knowledge modules while keeping model weights and executable harness code frozen. During our evolution, a deterministic Trace Verifier maps observed errors to candidate modules, and a Critic compares successful and failed trajectories to guide a tool-constrained Evolver. The Evolver applies atomic knowledge edits, which a fixed validation gate retains only when their measured gain reaches a threshold; otherwise, the previous knowledge state is restored. We evaluate KARMA with three LLM families on cases sampled from a corpus of approximately half a million real-world operation logs across six e-commerce domains. Across 18 domain--model settings, KARMA raises the average hold-out score from 30.19 to 39.15 (+8.96 points, +29.7%). Ablations show that removing either successful or failed trajectories more than halves the average hold-out gain. Evolved knowledge also transfers across domains without further adaptation, yielding an average hold-out gain of 8.54 points across all source--target pairs. By linking retained patches to their diagnostic evidence and validation outcomes, KARMA supports inspectable, reversible knowledge adaptation for agents in Web marketplaces.
Oct 29, 2026

MoLRSI: A Recursive Self-Improving AI agent for Molecular Discovery

Molecular discovery requires navigating vast combinatorial search spaces while balancing competing biological objectives. AI agents can automate expert-defined molecular design protocols, but automation alone does not address how to optimize workflows for new tasks or improve their development through experience. Here we introduce MoLRSI, an AI agent that combines systematic optimization of workflows and model architectures with persistent cross-task memory to recursively improve its search policy for molecular discovery. Workflow performance, refinement outcomes, and execution feedback guide subsequent searches, allowing the agent to improve both its workflows and its strategy for developing them. We evaluate MoLRSI in two challenging molecular discovery settings that require balancing competing properties. In antibiotic discovery, MoLRSI developed a screening workflow balancing antibacterial activity, cytotoxicity and structural novelty, achieving an experimental hit rate of 15.9%, compared with 8.7% for a previous expert-led workflow using the same training data and screening library. In de novo peptide-MHC binder design, MoLRSI developed workflows that jointly consider target binding and specificity, producing eight experimentally validated hits against MART-1 and SARS-CoV-1 pMHCs with preferential binding over tested off-targets while Claude Science completely failed. These findings demonstrate how experience-guided workflow optimization can address competing discovery objectives while improving the search strategies used in subsequent campaigns.
Oct 29, 2026

VEvo-Harness: Causally-Guarded Self-Evolving Harness for Agentic Image Generation

The central bottleneck in visual generation and editing has migrated from achieving pixel-level fidelity to satisfying densely constrained user specifications through increasingly agentic workflows. Prevailing agentic generation pipelines remain shallow generate-verify-rewrite loops treating VLM judgments as coarse visual feedback, either discarding repair experience or admitting ungated updates that poison skill library. With memorize and govern periods left open, they degrade into ungoverned iterators of repeated trial-and-error rather than continual self-evolving harness. Towards this issue, we present VEvo-Harness, the first causally-guarded continual self-evolving harness system for agentic visual generation. VEvo-Harness introduces four coupled innovations: (1) a visual traceback that densifies sparse judgments into root-cause attributions with a hierarchical verification tree; (2) a visual continual governance that admits only causally valid skill patches through counterfactual dual-arm image generation replay; (3) a lifecycle-managed harness state that hierarchically distills root-cause-anchored episodes across working, experience, and pattern tiers into a persistent skill library of routable and causally verified capabilities; (4) a heterogeneous sandbox policy that orchestrates a diverse action space of repair primitives, dynamically routing cost-aware interventions based on root causes to select the most effective strategy. VEvo-Harness surpasses state-of-the-art agentic methods and rivals proprietary generators (e.g., GPT-Image, Nano-Pro) while maintaining the continual harness evolution and generalization.
Oct 28, 2026

Recursive Self-Improvement in Physical AI: Mechanisms, Evidence, and Evaluation

Embodied systems can update policies, world models, skills, and executable programs from deployment experience, allowing one interaction to benefit later tasks. When a system also revises and reuses its data-acquisition, feedback, or learning procedures, experience changes the process that produces capability, introducing recursive self-improvement. This paper surveys research in physical AI through the connection between persistent capability and its improvement process. We first explain the functional distinction between learner updates and improvers, then compare policy learning, imagined experience, memory and skill accumulation, and executable harnesses. These approaches connect to revisions of curricula, rewards, and research programs in different ways. Contact validity, recovery, retention, and resource costs determine whether the resulting gains accumulate during continued deployment. An L0-L3 rubric distinguishes task-local adaptation, persistent capability gain, inherited process revision, and verified improver gain. Representative benchmarks and within-study contrasts relate these distinctions to existing results. We further propose common-data and interactive comparisons that evaluate reference and revised improvers from shared learner starts, separating the use of experience from its acquisition. This perspective connects the diverse methods, physical operating conditions, and evaluation evidence, underpinning embodied RSI. A comprehensive list of studies in this survey is available at https://github.com/nkd-lkz/physical-ai-rsi-survey.
Oct 27, 2026

When the Critic Falls Behind: Co-Evolving Rubrics and Harnesses for Continual Agent Self-Improvement

Autonomous agents increasingly depend on harnesses that govern interaction, memory, tools, and execution around large language models (LLMs). While recent work has begun to evolve these harnesses from execution experience, the supervision used to guide evolution often remains relatively static, making it difficult to track changing behavioral weaknesses across rounds and potentially limiting generalization to unseen tasks. To address this issue, we propose RuHarness, a rubric--harness co-evolution framework for continual agent self-improvement. RuHarness continually discovers and reassesses behavioral criteria from execution trajectories, prioritizes the most relevant unresolved weaknesses, and uses them to guide targeted harness updates while keeping the task objective fixed. Extensive experiments across diverse agent tasks and backbone models show that RuHarness outperforms strong harness-evolution baselines, particularly on unseen held-out tasks. Further analyses show that adaptive rubric prioritization tracks shifting weaknesses and supports more sustained improvement and stable generalization across evolution rounds.
Oct 26, 2026

The Trinity: Capability-Driven Recursive Self-Improvement for Multimodal Agents

Multimodal intelligence can be viewed as human-guided co-evolution between worlds and agents through interaction. However, scaling this process faces two bottlenecks: constructing heterogeneous, verifiable environments is costly, and manual Harness iteration cannot keep pace with growing task diversity and complexity. A key insight is that tasks with different modalities and surface forms can share the same underlying capability requirements. We therefore introduce The Trinity, a recursive self-improvement framework coupling world generation with Harness evolution through three roles: Creator, Explorer, and Evolver. Drawing on verified execution trajectories, Evolver shifts the basis of task organization from surface categories to shared requirements, reorganizing the original task tree into a hierarchical capability tree. We introduce Capability-Driven Real2Sim2Real: for heterogeneous tasks at the same node, Creator abstracts their common requirements into simplified, verifiable simulated worlds for capability learning, while evaluation on original tasks measures transfer. Along this capability tree, Explorer progressively evolves reusable capability modules through selective inheritance, forming a Harness tree whose validated updates accumulate across iterations within a fixed topology. The resulting Harnesses specialize in different capabilities, motivating a Capability-Aware Harness Router that uses public task information to select compatible module configurations from the tree. Our evolved Harnesses improve mean performance by 34 points across 28 training benchmarks and 26 points across 18 unseen benchmarks, including two real-world embodied tasks.
Oct 26, 2026

Infinity Machine: a self-improving AI agent for research

We present the Infinity Machine, a self-improving AI agent that we use for research on problems whose answers aprogram or data can check. Each candidate solution is produced by a full tool-using agent that works for up to an hour in a fresh sandbox; proposers see only a public score, and a private split decides what counts. The harness itself(prompts, tools, skills, playbook, meta agent) is an editable genome, changed only through a kernel-enforced gate with held-out and cost checks. An autonomous mode goes from a plain-text goal to a verified report with no human step: an agent picks an open problem and writes its verifier, the kernel calibrates it, an adversarial agent audits it, and an agent that never sees the verifier re-checks the result. Across fourteen problems in six days, for about $180 of model usage, the system produced four results beyond the published state of the art on catalogued open problems in quantum information: a certified depolarizing-channel threshold point p = 0.064966, a qutrit positivity frontier of 0.2910672, a 44-gate depth-6 Golay state preparation, and a stabilizer-rank bound chi(T^7) <= 10. It also cut SABRE qubit-routing overhead from 68,559 to 12,087 added gates. In hardware, it cut the energy per MAC of an open 8x8 INT8 systolic tile by 77.7% through a full open RTL-to-GDS flow, bit-exact. Three fully autonomous runs ended in honestties with public records; one audit caught a stale record, and one agent-written score pointing the wrong way went unnoticed. We report the failures as carefully: the one self-derived harness generation was rejected on cost, proposers gamed lenient scorers four times, and operator changes were decisive for several results.