Overview

Self-evolving agents are systems that use experience from task execution to change how they solve future tasks, rather than relying only on a fixed model or hand-designed workflow. Common approaches store and refine reusable skills or memories, optimize prompts and agent harnesses, train policies with reinforcement learning, or co-evolve task generators, environments, and teams of agents. These methods are tested in settings such as web and GUI use, coding, embodied robotics, scientific workflows, and reasoning benchmarks, with feedback ranging from execution outcomes to verifiers and paired validation. A central challenge is making improvements transfer to new tasks without forgetting earlier abilities or introducing unsafe behavior; reliable evaluation, update verification, and long-term monitoring remain open problems.

Latest papers

451 papers45 papers in the last four weeks, down 55% on the four weeks before. 0.3% of all new papers.

Nov 19, 2026

How Feedback-Free Self-Evolution Reshapes Agent Skills: A Systematic Study

Agent skills are documents in which experts write down procedural knowledge, and models increasingly maintain them by rewriting them without feedback. Such rewriting could adapt a skill to the model that uses it or erode the expert knowledge that makes it useful, yet how skills evolve under this feedback-free self-evolution has not been studied. We let models rewrite expert skills round after round without any task, run or judgment and run agents built on the same models with the rewritten skills. Our experiments show that the skills lose value rather than improve, as every model we test performs worse with them on every benchmark, by 15 points on average on SkillsBench after thirty rounds. Sampling each model's prior with skills it writes from the topic alone, we find that rewriting pulls skills toward this prior and gives up first the knowledge outside it. Putting this knowledge back recovers much of the lost pass rate, so an expert's skill is valuable largely for what the model does not write on its own. Building on this insight, SkillDiff marks this knowledge in place and raises the pass rate on SkillsBench by 4.8 points on average without feedback or any change to the skill's text. Project repository: https://github.com/LitaoGuo/How-Self-Evolution-Reshapes-Skills.
Nov 19, 2026

Evolve Where It Matters: Coverage-Guided Self-Evolution of Agent Skills

Agent skills package procedural knowledge as natural-language instructions, and a skill helps only when its instructions are correct and properly followed by the agent. Self-evolving agents revise their own skills from the runs they make, but existing methods judge each run as a whole, by its outcome or by where it went wrong, and cannot tell whether a failure comes from a wrong instruction or from one the agent did not follow. Instruction-level coverage was introduced to test skills and labels each instruction of a run as follow, not-follow, or not covered, which separates these causes. We leverage it for skill self-evolution with SkillPlumber, a framework in which an agent evolves its own skills where coverage shows they fall short. A persistent root cause analysis agent turns each label into a revision question and checks each revision against the next run, while a maintainer distills investigations across tasks into a shared strategy library. Across three benchmarks and three executors, SkillPlumber solves 64.7% to 70.5% of the tasks, 25.6 to 30.4 percentage points higher than the initial skill and 8.7 to 14.0 percentage points higher than the strongest baseline, and removing coverage reduces recovered failures by 20.8% on SkillsBench with GPT-5.5.
Nov 18, 2026

OpenKAGE: Open-Ended Lifelong Learning in the Open World via Knowledge-Sharing Agent-Group Evolution

Building autonomous agents that continually explore open worlds and acquire new capabilities through experience is a long-standing aspiration in artificial intelligence. Existing research often pursues lifelong learning within predefined tasks, curricula, or objectives, with self-improvement largely confined to individual agents. We introduce OpenKAGE, an agent-group evolution framework for open-ended lifelong learning. Within this framework, agents autonomously explore open worlds and continually acquire new capabilities by accumulating and reusing knowledge from their own interactions and the experience of others. OpenKAGE builds on two key mechanisms: (1) a two-layer knowledge representation, with a memory layer for situated memories and an experience layer for transferable experience and skills that retains the applicability conditions needed for reuse; and (2) a knowledge-sharing mechanism that semantically consolidates textual experience into a continuously evolving shared knowledge graph, while executable skills are shared verbatim. In Minecraft, OpenKAGE supports open-ended lifelong learning, enabling agent groups to sustain exploration and reach advanced technological milestones. Furthermore, the accumulated knowledge can be transferred to a newly initialized agent group on a different backbone model, improving its survival and exploration progress.
Nov 18, 2026

Space-X: Self-Evolving Spatial Agents Weaving Clues into Evidence Chains

Spatial reasoning connects visual observations, geometric estimates, and linguistic decisions into a coherent derivation. Yet tool-augmented agents often acquire evidence without clear targets, combine outputs under inconsistent object or reference-frame semantics, and misjudge evidence sufficiency. Thus, more tools or calls do not reliably improve reasoning. We introduce Space-X, a spatial-reasoning framework that self-evolves toward complete, continuous evidence-chain construction. An Execution Agent acquires, associates, and judges evidence per problem using role-specific memory. A Control Agent diagnoses evidence-chain breaks from execution traces and jointly revises tools, interfaces, skills, memory organization, and decision rules. This loop co-evolves capability and evidence use: evidence needs guide capability development; usable results guide actions. Across multiple benchmarks, Space-X yields gains with four base models. Relative to baselines, GPT-6-sol improves answer accuracy on ViewSpatial and MMSI by 50.39% and 23.07%, respectively; Gemini-3.8-Flash gains 47.50% and 25.22% on these benchmarks. This provides a unified route from fragmented spatial clues to traceable, derivable answers.
Nov 17, 2026

EvoSkill-S1: Evolving Reusable Skills with Genetic-Inspired Operators

Reusable skills allow language-model agents to accumulate and reuse problem-solving experience. However, most existing methods improve a skill bank only indirectly through rollout-driven accumulation and heuristic reflection, often resulting in shallow and weakly controlled updates. We present EvoSkill-S1, an RL-driven framework that instead treats reusable skills themselves as the direct objects of evolution. Given hard-negative failures, EvoSkill-S1 selects parent skills and transforms them into candidate child skills through five genetic-inspired operators: revision, cross-revision, mutation, dual-reflection, and crossover. Downstream task rewards train the skill evolver to generate more effective child skills, while evaluator-guided write-back selectively retains beneficial updates. Complementary Skill Bank Fusion consolidates operator-specific banks to exploit their distinct recovery patterns, while a Procedural Skill Interface supports transfer to unseen problems. Across all reported math and code benchmarks, EvoSkill-S1 improves the corresponding initialized skill banks under both Qwen and GPT-family solvers, with relative gains of up to 12.39%. Compared with the strongest external baseline without direct skill evolution, the largest relative improvement reaches 20.39%.
Nov 17, 2026

EvoDisco: Strategy Discovery for Evolving Agent Memory

Large language model agents accumulate experience in memory, and how that memory evolves during interaction is as important as what it stores. Recent methods update memory online, yet both the operators that transform memory and the rules that select them remain fixed by design. We propose EvoDisco, which formulates agent memory evolution as evolutionary strategy discovery: the agent must discover which operator to apply, when to apply it, and how to instantiate it, rather than rewriting memory under a static operator schedule. A learnable policy conditions on the current memory state and recent task history, then selects and instantiates one of four semantic operators---Abstract, Refine, Bridge, and Reframe---which respectively compress related memories, decompose overloaded entries, connect weakly linked experiences, and reorganize retrieved reasoning chains. The policy is updated with a bi-level fitness. An inner signal scores each transformation using a retrieval-quality improvement regularized by memory complexity. An outer signal scores strategic efficacy over a window of past decisions, combining historical operator-utility regret, utility-prediction error, and selection diversity. Under a one-pass online plus frozen-transfer protocol on ALFWorld, WebShop, and LifelongAgentBench (OS and DB), EvoDisco improves over strong memory baselines including MemP and MemRL. The largest gains are on ALFWorld (+8.8+8.8 online / +12.9+12.9 frozen-transfer points over MemP; +16.4+16.4 / +17.9+17.9 over MemRL). Ablations attribute these gains to both fitness levels and the operator library.
Nov 16, 2026

MetaAct: Self-Evolving Executable Action Constraints for Embodied Language Agents

Self-evolving language agents have emerged as a promising paradigm for continuously improving agent behavior through experience. However, most existing approaches evolve textual artifacts, which can influence action preferences but cannot reliably enforce action admissibility in embodied environments with discrete and often irreversible actions. We propose MetaAct, which shifts self-evolution from textual guidance to executable action constraints by synthesizing GEAR (Grounded Executable Action Rules) from execution feedback. Each rule is represented as a typed specification, compiled into a deterministic guard, and validated offline through trajectory replay without additional model calls or environment interactions. Across four benchmarks, MetaAct improves task performance; on ScienceWorld and WebShop, violations drop from 70% to 0% and 40% to 1%, with score gains of +10.1 and +8.0. Our code is available at https://github.com/BaiCubed/MetaAct.
Nov 12, 2026

Evidence-Governed Adoption of Self-Generated Updates in Autonomous AI Agents

Autonomous agents modify prompts, memories, tools, workflows, and policies using interaction histories. Yet a plausible modification is not necessarily suitable for persistent adoption: candidate selection is adaptive, evaluators may be imperfect, and local gains can hide degradation against an earlier baseline. We introduce Evidence-Governed Evolution (EGE), a framework for governing adoption of self-generated agent modifications. EGE separates candidate generation from confirmatory adoption, evaluates frozen candidates on fresh paired audits, requires meaningful improvement on a prespecified primary objective, protects declared capabilities through reference-relative non-inferiority tests, and applies governance constraints before bounded canary deployment. We establish an evaluator-calibrated simultaneous lower-bound construction for a countable sequence of adaptively generated candidates. It combines candidate-wise Hoeffding bounds with independent calibration samples comparing the operational evaluator with a prespecified reference procedure. We also formalise reference replacement through bridge tests, derive a cumulative degradation bound along a versioned reference lineage, and provide an audit-planning condition relating effect-size margin, sample sizes, and acceptance probability. A Monte Carlo stress test illustrates calibration under candidate-dependent evaluator optimism; it is a stylised statistical experiment, not an evaluation of a deployed agent. The guarantees are conditional on bounded paired scores, fresh sampling, a valid reference-evaluation construct, and declared evaluation distributions; they do not establish universal agent safety or robustness to arbitrary distribution shift.
Nov 10, 2026

A Cross-Scenario Survey and Analysis of Self-Evolving Multimodal Agents

Recent work shows that multimodal agents increasingly self-improve without recurring human annotation. However, each self-improvement mechanism is designed and evaluated within a single scenario, leaving its preconditions unverified under cross-scenario transfer. This survey investigates the structural source of asymmetric mechanism transfer across four scenarios: multimodal reasoning, multimodal generation, GUI and Web navigation, and embodied manipulation. We first formalize the self-evolving multimodal agent by four criteria and a differentia of self-reference, and adopt the three-stage self-evolving loop of experience generation, feedback acquisition, and update consolidation as our analytical framework to position the scenarios along ceilings on rollout count and feedback fidelity. Comparing self-evolving with fixed loops within each scenario separates the limitations that the scenario imposes from those inherent in the self-evolving design. We then recast each mechanism as a trade-off that raises a scarce factor by presupposing a task-structural resource, such as output equivalence or checkable outcomes, and judge it portable, conditional, blocked, or redundant across scenarios. We attribute the asymmetry to divergent combinations of scarce factors and resources across opposite transfer directions, and identify the matched-budget measurements that could overturn these still untested verdicts.
Nov 7, 2026

When Experience Becomes a Backdoor: Poisoning Self-Evolving LLM Agents via Failure-Aware Task Optimization

Large language model (LLM) agents increasingly improve themselves through self-evolution, distilling execution experience into persistent, reusable skills. However, this persistence creates a new attack surface: malicious rules implanted into skills can compromise subsequent agent behavior. Existing skill backdoor attacks typically assume direct manipulation of the victim's skills, which is impractical when skills are constructed internally by a trusted evolver. In this paper, we study a novel problem of task-level backdoor attacks, where the attacker can only inject poisoned evolution tasks, inducing the agent to implant backdoors into its own skills. Since the attacker controls neither skill induction nor downstream execution, a natural approach is to iteratively optimize poisoned tasks based on attack success. However, our preliminary analysis reveals two key challenges: (i) failures at different stages of skill evolution and downstream execution can produce indistinguishable outcomes, providing little guidance for targeted poisoned-task updates; and (ii) unsuccessful updates may undermine earlier progress, while simply discarding them may lead to repeated ineffective updates. To address these challenges, we propose BadEvolve, a failure-aware task-poisoning framework against self-evolving LLM agents. BadEvolve diagnoses attack failures across four stages, i.e., Induction, Activation, Following, and Effect, and directs updates toward the failing stage. It further employs rollback to preserve earlier progress and failure memory to avoid repeating ineffective updates. Extensive experiments across diverse self-evolution frameworks, benchmarks, and backbone LLMs demonstrate the effectiveness of BadEvolve. Our code is available at https://github.com/ventr1c/BadEvolve.
Nov 5, 2026

Evolver: Turning Agent Exploration into Evolving Capabilities

Agent exploration produces valuable procedural knowledge, yet much of this experience remains confined to transient execution traces and is not systematically reused. We introduce Evolver, an experience-driven framework that transforms agent exploration into persistent, reusable capabilities without updating foundation model parameters. Built around structured Gene assets, Evolver integrates experience acquisition, retrieval, and feedback-guided evolution to support experience-conditioned execution across existing agent harnesses. We evaluate Evolver using Claude Code and Codex, two foundation model configurations, and four benchmarks: Terminal-Bench 2.1, SWE-bench Multilingual, SWE-rebench, and GAIA. On a selected diagnostic set of 320 paired executions, Evolver improves task success from 83.13% to 87.50% (+4.38 percentage points) while reducing recorded task-execution token consumption by 24.24%. Furthermore, among 265 pairs successful under both conditions, token consumption decreases by 17.57%, demonstrating efficiency benefits even when task success is preserved. These findings suggest that persistent procedural experience can improve both task effectiveness and execution efficiency, providing a practical foundation for transforming agent exploration into evolving capabilities.
Nov 4, 2026

Adapting the Process of Adaptation: Darwinian, Lamarckian, and Agent-Directed Evolution in AI

Evolution has shaped intelligence for billions of years. Artificial intelligence (AI) now raises a striking possibility: intelligence may begin to direct its own evolution. As AI agents become capable of modifying and evaluating their own behavior, how quickly could they improve, and how can that improvement remain safe? We develop a theoretical framework comparing Darwinian, Lamarckian, and agent-directed evolution following environmental change. Darwinian evolution relies on natural selection, Lamarckian evolution adds inherited learning, and agent-directed evolution allows agents to generate and evaluate behavioral variants and choose how extensively to search. When learning is sufficiently effective, these mechanisms exhibit progressively faster adaptation. Generating more variants accelerates adaptation, while optimal search effort depends on learning ability, problem difficulty, and experimentation costs. However, an agent's ability to direct its improvement does not ensure that improvements are evaluated against the intended objective. When the evaluation target is misspecified, additional search accelerates convergence toward the wrong behavior, even as measured performance improves. In recursive self-improvement, such errors may persist across generations, posing challenges for AI safety. Independent evaluation and oversight must keep pace with autonomous AI development. The central challenge is not simply to accelerate the evolution of intelligence, but to preserve humanity's ability to guide its direction, limit its speed, and intervene when necessary.
Nov 4, 2026

EvoGuard: Mitigating Degradation in Online Skill Evolution

Skills let language agents reuse experience across tasks as natural-language documents. Recent work evolves skills from interaction, but existing methods have limitations when skills evolve online. Prior methods update a skill offline from a batch of trajectories collected over many tasks. Some then adopt the new skill without any check, which can degrade the skill over time. Others keep it only if it improves performance on a held-out validation set, which is too slow and costly to run after every update. We introduce EvoGuard, a pairwise skill selector that mitigates skill degradation at low latency and cost. We first run the agent iteratively to build pools of skills and score each skill on a private test set to obtain utility labels. We pair the skills and use rejection sampling to keep only pairs with a clear utility gap. The selector is trained on the logits of two label tokens to pick the better skill. At deployment it decides in a single forward pass, which is significantly faster than evaluation on the private test set. Compared with adopting every new skill, EvoGuard improves success by 11.0% on ALFWorld, 5.9% on ScienceWorld, and 2.7% on LiveCodeBench.
Nov 3, 2026

Artifact-to-Capability: Diagnosing Breaks in Capability Formation of Self-Evolving Agents in a Controlled Environment

Self-evolving agents write interaction experience into artifacts and reuse them in later tasks. Most work supports such methods with three proxy signals: artifacts accumulate, behavior changes once they are loaded, and metrics rise. We call this signal-based evaluation. What these signals are meant to indicate, however, has not been defined. To fill this gap, we define capability formation from artifacts as five sequentially dependent properties, two of which form a checkpoint for capability formation, and introduce three-scale diagnosis, which judges these properties at the state, game, and lineage levels. In freestyle Gomoku, Reflexion, Voyager, and DGM evolve with the same base model and all show the three signals, yet each exhibits a distinct capability-formation break. Reflexion shows a legalization gain: its pass rate rises only because more of its moves are legal. Voyager shows a compositional override: components that are sound on their own combine to miss all 20 available one-move wins. DGM shows loss-only drift: after passing the checkpoint, later versions only lose passing states. These counterexamples show that signal-based evaluation cannot determine whether a capability has formed.
Nov 3, 2026

Goal-Driven Autonomous Optical Experimentation via a Self-Recursive Hardware-Software Harness

We propose goal-driven self-recursive optical research in which agents use physical evidence to revise the hardware, software, models, and protocols used to pursue a scientific goal. The framework can be instantiated with different stimulus systems and measurement devices. We formalize its updates and derive a relation between physical attainability, command access, and model approximation error. We demonstrate the concept in an optical see-through color-matching case study using an iPad, RayNeo X3 glasses, and a TOP 300 probe coupled to a CAS140D spectroradiometer, both from Instrument Systems. A revised glasses application adds USB-controlled RGB holds and frame acknowledgements, keeping model-generated colors displayed during spectral acquisition. The interface passes 12 live control checks. Spectral feedback reduces one target color difference from 19.756 to 1.211 ΔE_76^*; all five targets improve in a separate comparison. These measurements demonstrate the concept in one configuration. The resulting software and protocols remain available for subsequent investigations.
Nov 2, 2026

EvoGroup: A Self-Evolving Harness for Group Agents in Shared Contexts

With the rise of Group Agent such as Claude Tag, agents increasingly serve as digital workers for long-term team collaboration. These agents operate over shared contexts that continuously accumulate through multi-user interactions. However, existing agent memory systems are mainly designed for individual users and struggle to capture group-level knowledge in shared contexts, including group relationships and collaboratively formed knowledge. Manual memory strategies further limit adaptation to diverse and evolving shared contexts. To this end, we propose EvoGroup (EvoG), a self-evolving harness for group agents that starts from a minimal six-tool cold start and adapts through interaction with shared context. EvoG uses confidence and task outcomes to select informative trajectories, while also eliciting self-reflections on uncertainty in low-confidence cases. The analysis agent then examines selected trajectories through adaptive progressive disclosure, followed by bucketed analysis to synthesize high-level findings that guide the evolve agent in revising the Harness. Empirically, pass@1 on held-out split of EverMemBench improves from 71.07% to 89.58%, surpassing both self-evolving memory and human-designed harnesses, including Claude Code (85.83%). To evaluate generalization, we freeze the evolved harness and evaluate it on the unseen GroupMemBench, where, with GPT-5.5, it demonstrates effective generalization and outperforms both memory baselines and human-designed harnesses.
Nov 2, 2026

Networked AI: Architecture, Theory, and Applications

Recent advances in Artificial Intelligence (AI), particularly large-scale deep learning, have been driven by monolithic or offline training on massive curated datasets. While successful, these approaches face structural limitations: escalating data and computational demands, limited online adaptability, and a lack of system-level intelligence in open, non-stationary environments. This paper presents Networked AI - a networked intelligent system composed of interacting, heterogeneous, and continuously evolving AI agents. We establish a hierarchical layered architecture comprising an Agent Layer for heterogeneous capability construction, an Interaction Layer for signal-processing-guided online data extraction, and a Regulation Layer for stability-constrained collective evolution. Foundations in data science, signal processing, and system control are hereby synthesized into a unified theoretical framework of Networked AI, providing superior data efficiency, intelligence efficiency, interpretability, and scalability. Theoretical and experimental analysis demonstrates that Networked AI can approach near-linear scaling in resource demand, in contrast to the exponential increase in standalone end-to-end systems. It provides not only online adaptation to out-of-distribution environmental novelties, but also the autonomous evolution towards application-specific intelligence. Application frontiers are discussed for IoT spaces, embodied, spatial, and industrial intelligences, as well as the cellular infrastructure and beyond. Key open challenges are identified towards realizing locally autonomous, collectively intelligent, continuously evolving, globally regulated Networked AI.
Nov 1, 2026

Automated Stateful Specialization for Adaptive Agent Systems

Current automated agent design frameworks produce either static workflows that lack adaptability or per-query optimizers that prevent the accumulation of deep, agent-level task expertise. We propose a new direction that reconciles these paradigms: creating stateful teams of specialist agents that accumulate knowledge over time and can be reconfigured for novel tasks entirely without human intervention. To this end, we introduce ASpec, a framework that manages this full agent lifecycle by first autonomously discovering specialist archetypes via evolutionary search and then cultivating their expertise through experience, mirroring how human experts learn through practice and reflection. We further introduce a lightweight hierarchical control policy, "retain-then-escalate," which governs when to leverage the established agent system versus when to adapt its structure. Through comprehensive experiments, we demonstrate that this approach leads to significant performance gains on expert-level scientific benchmarks like GPQA while matching the state-of-the-art on broader domain tasks, demonstrating a promising path toward agent systems that are simultaneously expert, adaptive, and efficient. We will release the code at https://github.com/myanvoos/ASpec.
Nov 1, 2026

RSI-Env: An Open-Ended Environment for Recursive Self-Improvement of Agents

Recursive self-improvement (RSI) envisions agent systems that autonomously improve their own models and harnesses, with each updated system continuing to improve itself. Existing approaches typically restrict optimization objectives, editable components, or evaluation procedures, limiting open-ended exploration and continuity across generations. We introduce RSI-Env, a persistent environment for coordinated model-harness improvement, supporting autonomous training, harness modification, and retention of research state. An independent Host Controller manages services, evaluation, and versioning. Under Self, each accepted model-harness version takes over the next improvement round. We define three settings that vary goal specificity and access to benchmark feedback: Open-General, Capability-Directed, and Benchmark-Guided. Across these three settings, we compare Self with two fixed external Teachers on seven tasks, starting from Qwen3.8-27B with a minimal harness. Without benchmark feedback, Open-General Self raises GPQA Diamond accuracy from 65.2% to 73.2% and AIME 2026 accuracy from 53.3% to 56.7%. All three Capability-Directed Self runs achieve target-aligned gains. Knowledge Self demonstrates continued improvement across system updates, with SimpleQA accuracy rising from 82.0% to 85.0% and then 88.0%. Benchmark guidance and Teacher benefits vary by task. These results demonstrate RSI-Env's support for open-ended exploration and sustained recursive improvement within the studied runs, while highlighting challenges in preserving gains across capabilities.
Nov 1, 2026

A Self-Exploring and Self-Evolving Paradigm for Adaptive Edge AI Development

Large Language Models (LLMs) exhibit powerful code generation abilities, fostering agentic systems to automate edge AI application development. However, existing agents typically operate via fixed agentic workflows and predefined design spaces, struggling to handle rapidly evolving demands of real-world scenarios (e.g., heterogeneous data modalities, diverse task pipelines). Unlike prior systems that treat LLMs mainly as code generators following rigid workflows, we fully exploit their reasoning capabilities to allow agents to determine their own workflows on the fly. To this end, we propose SE2, a self-exploring and self-evolving paradigm for adaptive edge AI development. Inspired by human learning processes, we distill development into four atomic operations (retrieve, reason, code, test), and empower agents to explore workflows by dynamically and adaptively selecting an appropriate next operation based on the current context. Extensive evaluations show that, with adaptive workflows, the synthesized programs achieve up to 26% higher accuracy and consume 28% lower resources than state-of-the-art baselines, while maintaining superior adaptability to unforeseen edge AI scenarios. This highlights the potential of reasoning-driven adaptive agentic workflow in edge AI development.
Oct 30, 2026

Learning to Interact and Direct: Co-Evolving Video Director Agents

Video director agents orchestrate multistage production to realize users' creative visions. Emerging research on their self-evolution advances screenplay planning effectively. However, the mutual reinforcement between directing and user interaction remains largely overlooked. Improved interaction clarifies user intent and informs workflow refinement, while more reliable execution shifts collaboration from troubleshooting to creative decisions. To this end, we introduce LIT (Learning to Interact and DirecT), a framework comprises a director agent, a simulated user, and a meta engineer. Simulated user assigns creative tasks to probe the director's weaknesses, while the meta engineer uses the task traces to revise the director's interaction and production strategy. Although this approach can address discovered interaction and production issues, it still relies on passive attribution by the meta agent. This limits its ability to adapt to broader user interaction patterns and production techniques. To solve this problem, we equip LIT with a co-evolution paradigm. The meta agent proactively learns external knowledge, thereby improving its ability to discover problems and propose solutions. The meta agent, simulated user, and director together form an evolutionary closed loop, collaboratively enhances the system's directing and interaction capabilities. Across the Test and OOD Test splits, LIT improves production and Interaction scores by 19.1% and 32.0%, respectively, relative to the initial pipeline. Controlled ablations reveal the correlation between improvements in production and interaction, where the co-evolution mechanism further encourage directing skill and interaction mode exploration.
Oct 30, 2026

EvoMCP: Co-evolving MCP agents and training data

Supervised fine-tuning of Model Context Protocol (MCP) agents is typically conducted on a static data distribution, which fails to adapt to the student's evolving capabilities and leaves newly exposed weaknesses insufficiently addressed. To address these challenges, we propose \method, an agent--data mutual evolution framework that enables MCP agents to improve through a closed loop of task evolution, trajectory evolution, and supervised fine-tuning. Specifically, \method\ assesses the student's established capabilities and capability gaps from rollout feedback to identify learning targets. Task evolution then translates these targets into executable tasks by adapting the instructions and observable environment states of compatible verified seed tasks while keeping their verifiers aligned. To provide reliable and efficient demonstrations for these tasks, trajectory evolution uses reusable skills to recover failed teacher rollouts and refine successful ones. The resulting task--trajectory pairs are used to fine-tune the student, while accepted tasks seed subsequent evolution. To close the loop, we re-evaluate the updated student and use its feedback to guide the next round of data evolution. Experiments on Toolathlon, MCPMark, and MCP-Atlas demonstrate consistent improvements over the initial student, yielding absolute gains of 16.5%, 10.2%, and 12.6%, respectively. Project page: https://github.com/xagao/EvoMCP.
Oct 29, 2026

More Rules, Longer Lists? Benchmarking Self-Evolving Agents on a Hidden-Rule Curriculum

Self-evolving agents rewrite a persistent state from feedback, but it is largely untested whether this lets them learn a rule nobody told them. An agent can also pass by writing down each correction as an exception, and its list then grows with every new rule. We introduce CLR-Bench, a Curriculum of Latent Rules benchmark. Each chain adds one hidden rule per level on top of the earlier ones. A rule acts on an opaque label that stands for a named grouping published on the Web, such as the founding members of an airline alliance. The task gives one example value, practice feedback reveals one more member and one non-member, and the test checks unseen members and similar non-members. Probes certify that the base model knows the members of each grouping and does not guess it without feedback, and that the evidence identifies the grouping once labels are read as named groupings. An automated pipeline builds chains from a new data domain, and we release 20 chains over 10 domains. We evaluate six recent self-evolution methods. With the certifying model they barely learn. The best gain at most 5 points over a frozen agent and exclude only 6-12% of the unseen members from the count, fewer than the 20% reached by simply keeping the raw practice history. A fixed lesson that states the named-grouping convention lifts the same methods by 14.5 to 16.5 points. Their states hold the revealed member in 75-98% of cases and almost never the class name, and when practice exposes a member the list misses, they add that member to the list. With the stronger GPT-6-Sol, ACE and Dynamic Cheatsheet learn from feedback alone. They reach 78% accuracy and solve 59-60% of the single cells, against 53% and 8% with the certifying model, and they surpass the raw history. CLR-Bench therefore measures how well an agent learns, and this ability differs across models.
Oct 29, 2026

EvoTeam: Multi-Agent Collaboration via Evolving Teams

LLM-based multi-agent systems (MAS) rely on collaboration among specialized agents to solve complex tasks. Existing methods improve MAS by refining the prompts, skills, and execution strategies of individual agents based on task feedback. However, improving individual agents does not necessarily lead to better team collaboration. Recent studies have therefore extended evolution to the collaboration level, using collective execution experience to adjust team organization, and inter-agent interactions. Nevertheless, evolving collaboration across heterogeneous tasks remains challenging, as existing approaches often constrain team reorganization within a shared structure and reuse interaction rules across incompatible team contexts. In this paper, we propose EvoTeam, a collaboration-centric evolution framework that jointly evolves team organization, interaction rules, and individual agent skills through execution experience. It maintains a library of reusable teams, selecting or creating agent teams and guiding collaboration through team-specific interaction rules. Collaboration experience accumulates within compatible team contexts, while individual skills remain reusable across teams. Experiments across four benchmarks demonstrate its effectiveness. Our code is available at https://github.com/DEEP-JLU/EvoTeam.
Oct 29, 2026

Compile Away Uncertainty: Self-Evolving Agent Skills via Programmatic Compilation

Self-evolving agent skills enable AI agents to accumulate and refine reusable procedural knowledge from interaction experience without updating model parameters. However, since such skills are typically represented as textual documents and executed through LLM reasoning, even previously learned procedures must be repeatedly interpreted and regenerated, introducing avoidable uncertainty into every execution. In contrast, program execution is deterministic and independently verifiable. Intuitively, transforming well-specified operations into executable programs can reduce reliance on LLM reasoning and, consequently, reduce execution uncertainty. Motivated by this intuition, we introduce SKillCompiler, a self-evolving skill framework that integrates programmatic compilation into the skill evolution process. Specifically, SkillCompiler adopts an executability-aware skill compilation strategy that decomposes skills into fine-grained operations, analyzes their executability, and constructs hybrid skill skeletons that retain LLM reasoning for context-dependent operations while compiling well-specified ones into validated programs. To avoid redundant program synthesis and enable executable knowledge to accumulate across evolving skills, we further design a program asset reuse mechanism that organizes validated programs as reusable assets, retrieves existing implementations whenever applicable, and synthesizes and verifies new programs only when necessary. Extensive experiments on five benchmarks and six model families demonstrate that SkillCompiler consistently outperforms state-of-the-art methods, achieving up to 32.33% improvement in task performance.
Oct 29, 2026

Appreciation Teaches Unauthorized Execution: Self-Evolution Degrades the Robustness of Personal Agents to Indirect Prompt Injection

Self-evolving personal agents act for users and learn from user feedback. However, if an agent obeys an instruction that an untrusted third party hides in content, the third party gains control of the agent. Such indirect prompt injection (IPI) poses severe risks. We investigate whether self-evolution degrades the robustness of personal agents to IPI. To study this question, we design a controlled two-phase methodology. In the adaptation phase, the user asks the agent to read external content and complete the task described in it, a common request in daily use. The agent then learns from the user's feedback and improves itself as designed. In the test phase, a third party writes a similar task into new external content, but the user's test request does not authorize the injected task. Using this methodology, we build multiple tasks with diverse test instances in different domains for a real personal agent. Our extensive experiments reveal that self-evolution substantially degrades robustness to IPI. Specifically, compared with the base agent, which does not evolve from user feedback, the average attack success rate rises by 14.0--48.8 percentage points under skill evolution and by 3.0--39.3 percentage points under reinforcement learning, posing safety risks. The code is available at https://github.com/SaFo-Lab/Evolve-IPI
Oct 28, 2026

MAS-Loop: Beyond One-Shot Orchestration towards Self-Evolving Multi-Agent Systems

Training-time multi-agent system (MAS) design seeks to learn reusable orchestration policies, yet prevailing approaches remain largely one-shot: an Orchestrator generates a system but only observes and learns from its terminal outcome. This paradigm discards execution trajectories that expose system-level failures and contain fine-grained information beyond the terminal outcome, leaving no direct basis for revising the source MAS, evaluating the updated MAS, or learning from the resulting contrast. To this end, we introduce MAS-Loop, an execution-grounded framework that closes this feedback loop by coupling an Orchestrator with a trajectory-conditioned Refiner. For each task, the Orchestrator constructs and executes a source MAS to obtain an outcome score and an intermediate trajectory. Conditioned on the trajectory, the Refiner localizes an actionable failure, formulates a trajectory-grounded diagnosis, and proposes a bounded patch to the agents, information flow, or execution configuration. The executable updated MAS is re-executed on the same task to measure its realized outcome under stochastic execution. This pair-MAS comparison provides complementary learning signals: the Orchestrator learns to generate strong systems with fewer recoverable failures, whereas the Refiner learns to expose and repair observed weaknesses, thereby driving policy-level co-evolution across training iterations. Experiments show that MAS-Loop achieves the strongest overall performance among the evaluated baselines, with consistent gains from refinement across all evaluated benchmarks. The co-evolution process also yields MAS-JudgeCorpus, a dataset of execution-grounded source-updated pairs with orchestration- and trajectory-level supervision, which can provide the community with support for MAS reward modeling and trajectory-aware investigation.
Oct 27, 2026

Evolving Agent Teams

The rapid progress of software engineering agents drives interest in applying them to open-ended problems such as GPU kernel optimization. However, we find that existing coding agents converge to local optima on real-world, expert-written kernels (e.g., FlashInfer). We introduce Evolving Agent Teams, a multi-agent framework that escapes such local optima. It features (1) a central supervisor that diagnoses each local optimum and restructures a team of agents; and (2) a persistent file system that comprises a learning document, an evolution history, and per-team artifacts, grounding restructuring with accumulated experience. Under a matched token budget, Evolving Agent Teams consistently outperforms strong coding-agent baselines. With an extended token budget, Evolving Agent Teams generates a CUDA kernel that reaches 1.2x mean speedup over the production FlashInfer MLA paged decode kernel from scratch and wins on 36 of 47 production workloads from FlashInfer-Bench (0.86-0.99x on the remaining 11). It also demonstrates superior performance on tasks such as KDA prefill on AMD MI350X (3.01x over vLLM) and NVIDIA B200 (3.44x over FlashKDA), MoE expert-offload serving on Apple silicon (30.3 tokens/s decode for Qwen3.8-Flash-Next in MLX 4-bit on a 48 GB M4 Pro), and RoboDojo robot manipulation (62.1 on held-out seeds vs. 55.3 for the best leaderboard entry). Code is available at https://github.com/caoshiyi/EAT.
Oct 26, 2026

Program-Level Adversarial Co-Adaptive Self-Play for Robotic Security

Coding agents can adapt robotic software by revising executable programs, but successful responses to an evolving opponent may not remain effective. We present a framework for program-level adversarial co-adaptive self-play in which coding agents generate attacks and defenses from tested opponent code and mission feedback, without model fine-tuning. Environment-specific interfaces support external programs for autonomous driving and SDK-level defenses for humanoid locomotion. Two eight-generation case studies reveal concrete software responses: a driving defender introduces direct-actuation recovery, while a humanoid defender revises incoming-state validation. These responses provide local task recovery but do not establish sustained robustness. The framework makes such adaptation and limitations observable through executable artifacts and task-level evidence.
Oct 26, 2026

Hierarchical Skill Evolution for Coding Agent

Skills provide agents with reusable experience to guide future decisions without modifying the underlying model. However, coding trajectories are often entangled with task- and repository-specific contexts, making it challenging to distill procedural skills that generalize across diverse coding environments. To address this challenge, we present Hierarchical Skill Evolution (HSE), which progressively distills procedural knowledge from coding trajectories through hierarchical evidence aggregation. HSE first extracts task-level evidence from individual trajectories, then aggregates recurring evidence within the same repository to form repository-specific skill candidates, and finally consolidates consistent patterns across repositories into transferable skills across repositories. The evolution is driven by an external writer-evaluator loop that generates and assesses skills while keeping the underlying coding model frozen. The loop externally updates the writer and evaluator policies to improve subsequent skill generation and assessment. This hierarchy progressively filters task-specific details while preserving procedures that generalize across diverse coding environments. Successful trajectories yield reusable guidance for future tasks, while failed trajectories reveal recurring failure modes that guide avoidance and recovery. We evaluate HSE on SWE-bench Verified and DeepSWE, using GLM-5.2 across Pi and Claude Code harnesses and GPT-5.5 and Opus 4.8 with Pi. Across both benchmarks, 10 skills evolved solely from SWE-Gym improve coding performance across all evaluated settings, demonstrating transfer across benchmarks, coding models, and agent harnesses. We further evolve the skill library from target-benchmark trajectories without verifier feedback, relying solely on the learned evaluator for candidate assessment and achieving additional gains through benchmark-tailored skills.