LLM Agent Training

Reinforcement learning is commonly used to train language agents in interactive environments, but cannot be directly applied when rewards are unavailable. Recent methods use environmental feedback as privileged context for hindsight self-distillation, but our analysis suggests that simply conditioning the teacher on feedback is insufficient, motivating us to rethink how environmental feedback is used in agentic self-distillation. Given that environmental feedback contains rich supervision for modeling how the environment responds to agent actions, we introduce \textit{agentic SElf-distilLation with environmental Feedback modeling} (SELF), a framework that jointly optimizes environmental feedback modeling and hindsight self-distillation. SELF learns to predict environmental responses while distilling guidance from a feedback-conditioned self-teacher into the policy. Our analysis reveals a mutually reinforcing mechanism: environmental feedback modeling strengthens hindsight supervision and policy learning, while self-distillation enhances the model's ability to model environmental feedback. With Qwen3-8B, SELF outperforms SDPO and GRPO by 6.4 and 4.1 percentage points in $τ$-bench success rate, and by 10.71 and 3.57 percentage points in AppWorld task goal completion, respectively. These results show that SELF uses environmental feedback more effectively within agentic self-distillation, improving agent capabilities.

Reinforcement learning environments are now a primary lever for improving large language model (LLM) capabilities in post-training, yet most agentic benchmarks remain static: the world moves only when the agent acts, the reward is a terminal verdict, and the pass bar is set arbitrarily. We introduce StoreBench, a live-commerce environment in which an agent runs a mid-size online apparel store on a production-grade commerce backend, testing long-horizon planning and economic judgment under uncertainty. Customers order around the clock, suppliers reprice and fail, and market shocks arrive with partial or no warning. The agent acts through the same 29 merchant tools a human operator would use, under a windowed operation budget that makes simulated time a function of actions taken, so model latency cannot influence simulated time. Pass thresholds are calibrated against scripted anchor policies, the reward is hardened against a catalogue of reward hacks, and every episode replays identically given a sequence of actions. We evaluate seven frontier LLMs on 11 scenarios of 30 to 45 days and a full simulated year, over three world seeds at matched reasoning effort. No model matches the scripted smart-triage policy on average: the best, DeepSeek-V4-Pro, passes 49% of task-seed cells against the heuristic's 97%. Human experts working through the same tools and budgets outscore every model (mean composite 0.708 vs. 0.700). Over a full simulated year under the Claude Code harness, most models show dramatic performance improvement. In a GRPO post-training run, Qwen3.5-27B trained on only five disjoint tasks raises its mean composite on the held-out evaluation tasks from 0.136 to 0.373. We release five example training-split tasks, ten sample trajectories, and the scoring and verification tooling; the full environment and evaluation suite are withheld to keep the benchmark uncontaminated.

As option markets grow and AI advances, agentic systems for option trading are gaining increasing attention. Language-model-based agents can reason over contextual information such as news, but option trading presents a particularly challenging decision problem: a single stock can have thousands of contracts, and the agent must decide both which contracts to trade and how to combine them. Existing approaches often sidestep this complexity by restricting the policy to a fixed strategy structure, such as a straddle, limiting their ability to switch strategies as market conditions change. We present SOTA (Stock Options Trading Agents), an agentic trading framework for structured option-strategy selection. SOTA abstracts the large option universe into strategy-level decisions while deterministic resolvers handle portfolio implementation. We develop SOTA by post-training Qwen3.8-27B with supervised fine-tuning followed by reinforcement learning. SOTA is evaluated on options on nine large-cap U.S. equities and SPY against rule-based and machine-learning strategy selectors in the same trading environment. Over a six-month out-of-sample period, SOTA earns an 18.3% total return with a Sharpe ratio of 1.60 and a maximum drawdown of 8.96%. We also document an asymmetric role of news: news improves frontier-teacher trajectories, but retaining news during reinforcement learning reduces out-of-sample return from 18.3% to -2.7%.

Large language model agents tackle multi-step tasks by interleaving reasoning and tool calls with observations from the environment. Prior work has shown that natural-language feedback can help these agents revise their decisions during task execution. We introduce Caddie, a method for training critics to provide natural-language analysis and advice as agents work through a task. Unlike approaches that rely on step-level labels or reference critiques, Caddie learns from whether the agent ultimately succeeds after receiving the critic's feedback. We optimize the critic through reinforcement learning while keeping the base model frozen. Trained on multi-hop question answering with a single base model, our Qwen3-4B critic improves success rates across four base models of different scales and architectures, including three not used during critic training. On the MuSiQue benchmark, the trained critic improves Qwen3-4B's success rate by more than 25 percentage points, surpassing the performance of Kimi K3 without a critic. The same critic also yields gains on out-of-domain interactive benchmarks, including $τ^3$ and DeepDive, with no additional training. Our results show that agents can decide when to seek help from a critic at inference time and that outcome-based critic training can produce guidance that transfers across base models and task domains.

Training and evaluating interactive language agents typically requires rich user interactions, yet collecting human feedback is expensive and difficult to scale. Simulated users offer a scalable alternative, but they must both resemble real user behavior and provide useful learning experiences for agents. In contrast, most agent-training frameworks rely on off-the-shelf assistant LLMs, whose helpfulness can make them overly cooperative, explicit, and behaviorally homogeneous compared with real users. We introduce MIMESIS, a purpose-built user simulator trained on human conversations with explicit reasoning supervision and 13 realistic behavioral patterns derived from real user interactions. Empirically, our 9B model achieves a SOUL-Index of 65.7, surpassing the strongest frontier model. Compared with Claude-Opus-5, the strongest baseline on RealUserSim and SimulatorArena, MIMESIS improves behavioral fidelity by 13.4 points and reduces Turing distance by 3.6 points, respectively. We then freeze the simulator and train an agent by interacting with the frozen simulator using multi-turn reinforcement learning. Across eight environments, training with MIMESIS yields better agent performance than training with GPT-5.5 under all nine unseen user simulators, demonstrating stronger generalization to new user simulators. Moreover, we propose Coached On-Policy Self-Distillation (CSD), which leverages simulator-generated private reasoning traces and subsequent utterances as feedback on how well the agent addresses user needs. A coach converts this information into concise coaching notes that describe how the agent can better anticipate user needs and adapt its behavior over the course of an interaction. CSD turns this feedback into dense, token-level supervision beyond sparse task rewards, yielding further gains across all nine evaluation user models.

As large language models become more powerful, self-evolving agents are able to tackle challenging tasks including AI for machine learning (AI4ML). In AI4ML, while empirical verification is available, it often requires computationally costly model training and evaluation, limiting the speed and scale of agent evolution. Yet verification efficiency remains under-explored, and frontier models provide only limited gains when used directly as idea selectors. We address this gap with specialized idea-level critic models that predict whether a proposed ML modification will improve upon the current solution, allowing agents to screen ideas and concentrate verification resources on the most promising candidates. We train the critic models through supervised fine-tuning on high-quality critiques synthesized by Gemini-3.1-Pro, followed by GRPO to further improve their predictive accuracy. Empirically, our critic models outperform Gemini-3.1-Pro in static idea evaluation, and these gains extend to agent inference, continual learning, and policy training. During inference-time evolution, they improve final solution quality under the same verification budget by selecting more promising ideas, with further gains from continual learning. During policy training, they serve as learned reward models, reserving empirical verification for uncertain cases and enabling substantially more policy updates with the same verification resources. Together, these results show that idea-level critic models help ML agents discover better solutions and learn stronger proposal policies under limited verification budgets.

On-policy distillation post-trains large language model agents by supplying dense, step-level guidance from a teacher policy when the reinforcement-learning reward is sparse and arrives only once per trajectory. Existing instantiations allocate this guidance by the size of the teacher-student divergence at each step, on the single-turn intuition that a large disagreement marks a mistake worth correcting. Once decisions chain over many turns, that rule misfires, since an early drift enters every later context both policies condition on, leaving the teacher consistent with the drifted trajectory instead of flagging its cause, while interchangeable steps register large but outcome-irrelevant divergences. We demonstrate this on an agentic benchmark, where distilling the highest-divergence steps brings no consistent benefit over random selection. To this end, we introduce GraphOPD, the first method to bring graph-based structural augmentation into on-policy distillation for agent capabilities. It reads which steps enabled which later ones from the environment's own record of state changes, immune to the drift that corrupts the teacher-student gap, organizes them into a dependency graph, scores each step by a random-walk stationary distribution over it, and fuses that structural credit with the divergence signal into a trajectory-relative mask concentrating supervision on each rollout's highest-aptitude steps. Across three model scales and eleven baselines on ALFWorld, WebShop, and SearchQA, GraphOPD shows competitive performance throughout, improving over the strongest baseline by up to +5.8 pp. An executed-replay audit further shows that this structural credit score tracks true causal impact far above chance, that both fused signals are independently necessary, and that the same signal transfers to out-of-domain tool-integrated reasoning.

Web agents complete user requests by reading and acting on pages that third parties write, so an instruction planted on a page can redirect the agent away from the user's goal. The agent cannot simply ignore the page, because the page also holds the values and controls the task requires. Current defenses fine-tune the agent on injections fixed before training, and attackers that adapt to the trained model bypass them. Adversarial training lets the attacker adapt but keeps the tasks fixed, so a task stops teaching once the agent solves it. We introduce AdvSim2Real, which co-evolves a task curriculum, an injection adversary, and the agent inside a frozen web world model. The curriculum is rewarded for tasks the agent solves about half of the time, and the adversary only for a success flip, an injection that turns a judged success into a failure. Training in the simulator makes a 4B agent both more capable and more robust: its completion rises with and without attacks, holds against a frontier-model adversary it never trained against, and its capability gain carries over to a real browser. On 150 web tasks, AdvSim2Real raises completion under this unseen adversary by 33.6% relative to the base agent.

Tool-using language-model agents are vulnerable to indirect prompt injection because they must act on untrusted external content. Existing training-time defenses can reduce attack success rates, but often at the cost of general capabilities. We show that training-based defenses induce substantial drift in the model's output distribution, altering its behavior even in benign settings and providing a potential mechanism for utility degradation. We further identify a failure mode of these defenses: On benign tool-use tasks, the model refrains from a step needed to finish an authorized task, particularly when that step is indicated by a tool output. To address these limitations, we introduce RAISED (Robust Attack Invariance through Self-Distillation), a training framework that combines self-generation and self-distillation. The model first generates its own tool-use scenarios, with an emphasis on cases where task completion requires acting on legitimate guidance from tool outputs. Then, through self-distillation, the student is trained to match the teacher's clean-context behavior on both clean and injected variants of the same trajectory. RAISED substantially reduces the attack success rate of prompt injections in tool responses while, unlike prior training-based defenses, preserving utility on both agentic and general-purpose benchmarks.

Graphical User Interface (GUI) agents have emerged as a promising paradigm for automating complex digital workflows across diverse applications. However, training highly capable and generalizable agents fundamentally relies on massive, high-fidelity visual-action trajectories, which are notoriously difficult to acquire. While human demonstrations are unscalable, existing GUI world models rely on text descriptions or HTML rendering, discarding crucial pixel-level visual details like icons and layout styles. To address this issue, we introduce Infinite-Dreamer, a simulation-free data synthesis method powered by a pixel-level Image Editing World Model. By conceptualizing GUI transitions as image editing tasks, we leverage Vision-Language Models (VLMs) to describe action-induced UI changes as structured delta-text. We then fine-tune an image editing backbone to controllably synthesize realistic screenshot transitions. We utilize this model to generate both single-frame visual robustness data and multi-step imaginary trajectories. To validate the effectiveness of our approach, we fine-tune the Qwen3-VL baseline solely on the synthesized data to obtain Infinite-Actor, and evaluate it on AndroidWorld, MobileWorld, and AndroidControl-Curated benchmarks. Infinite-Actor consistently outperforms the Qwen3-VL baselines across scales: Infinite-Actor-8B improves AndroidWorld Pass@1 by +4.45 and nearly doubles the MobileWorld Pass@3 success rate, while Infinite-Actor-2B improves Pass@1 by +9.05. Code is available at https://github.com/swaydy-n/Infinite-Dreamer.

Terminal agents are commonly trained by imitating long teacher trajectories, yet how much of each trajectory to supervise remains unexplored. We study the \emph{supervision horizon}, the number of trajectory tokens retained for training, and show that it is a key design axis for reliability and cost. Reliability improves with longer horizons but saturates: on Terminal-Bench, a 12K-token horizon solves more tasks than 16K ($29\pm0.7$ vs.\ $26\pm0.8$) while requiring 30% less training time. The horizon also shapes agent behavior: short horizons cause premature termination, intermediate horizons yield productive error recovery, and long horizons induce over-persistence. We analyze this saturation through a bias--complexity bound, in which longer supervision reduces temporal supervision bias but increases finite-sample estimation error from more heterogeneous late-stage histories. Guided by this analysis, we propose \emph{selective long-horizon refinement}, which first trains on short prefixes and then refines only on continuations that are most likely under the warm-start model. It consistently outperforms full long-horizon training. At 16K, it raises successful attempts from $110\pm2.7$ to $126\pm2.1$ and tasks solved in at least six of eight attempts from $9\pm0.7$ to $14\pm0.6$; with half of the long-horizon data, it still reaches $122\pm2.4$ while cutting training time by 23%. The gains transfer across benchmarks, from $64\pm2.6$ to $73\pm2.1$ on Terminal-Bench v2.0 and from $137\pm2.7$ to $155\pm2.2$ on OpenThoughts-TBLite. For long-horizon supervision, selecting the right trajectories matters more than training on all of them.

Small language models (SLMs) offer a promising foundation for on-device agents through low-latency, resource-efficient inference, yet limited reasoning and planning capabilities constrain their performance on long-horizon tasks requiring multi-step interaction with the environment. Step-level collaboration between SLMs and larger cloud-hosted models can bridge this gap, but identifying states that warrant cloud assistance remains challenging: the contribution of each cloud call is entangled with subsequent actions and can be assessed only from the final task outcome. Compounding this challenge, the SLM must balance two competing objectives: maximizing task success and minimizing cloud calls. To address this, we propose Sibyl, an algorithm that trains SLM agents to selectively consult cloud models at the step level and internalize their guidance for subsequent decisions, achieving strong task performance with minimal cloud reliance. Sibyl follows a three-stage training pipeline that (1) builds a robust base policy through consultation-free self-evolving reinforcement learning (RL); (2) cold-starts consultation behavior via decisive-disagreement state mining; and (3) jointly optimizes consultation decisions and guidance internalization through consultation-aware RL. Experiments on ALFWorld and WebShop demonstrate that Sibyl, using only a 0.6B-parameter model, outperforms state-of-the-art baselines, including agent training and routing methods, by 95.2% and 80.4% in success rate while averaging only 0.8 and 3.9 cloud calls per trajectory, respectively.

A large language model (LLM) agent solves long-horizon tasks through many reasoning-action turns, with one verification signal at termination. Deployed agents face streams of related tasks, making their trajectories a natural resource for improvement. In-context adaptation agents store reflections, memories, or skills as text, so reuse depends on retrieving the right experience and on a frozen policy executing it. We study Online Agentic Test-Time Training (OaTTT), which trains the LLM's weights on its own execution trajectories during deployment. The agent executes each task once, in one pass over the stream, and the executed trajectory with its verification result is the only learning signal for weight updates that persist across tasks. Directly imitating or reinforcing the generated tokens of this single attempt destabilizes the policy. We introduce ASCENT (Agentic Self-distillation for Cross-task EvolutioN at Test-time), which instead self-distills verified experience. A stable version of the LLM, its frozen initial copy, receives the verified trajectory as privileged information and predicts next-token distributions along it with this hindsight. Distilling them into persistent LoRA fast weights updates the agent for later tasks, without an external reference solution or stronger teacher. By further removing invalid-action turns, ASCENT distills enhanced privileged experience for more efficient execution. We characterize its population target and the limits of sparse outcome selection. Across ALFWorld, WebShop, and AppWorld at varied model scales, ASCENT improves task success and interaction efficiency as experience accumulates, outperforms online adaptation methods, and transfers to held-out scenes, showing that an agent can consolidate verified experience into its weights without a separate training phase or memory retrieval. Project page: https://artificer-ai-lab.github.io/ASCENT

Language agents rely on external harnesses to track state, organize workflows, and verify answers. Beyond providing tools and information, these harnesses supply control decisions about what to investigate, whether to revise, and when to stop. Training on successful harness-supported trajectories can improve task performance while leaving these decisions dependent on runtime intervention. We ask whether harness-supported experience can also teach the model to make these decisions, allowing the division of control to change as the model learns. We call this objective harness internalization: learning to assume specified control responsibilities while retaining task performance after the corresponding support is withdrawn. We introduce HARNESS ANNEALING TRAINING (HAT), which combines explicit control supervision with a curriculum over teacher trajectories collected under progressively weaker harnesses. Experiments with 9B and 35B models on SWE-QA and SWE-QA-Pro evaluate every checkpoint under four deployment harnesses. Selected annealed checkpoints operating with tools alone achieve scores close to those of their respective starting checkpoints deployed with the full harness. The benefits vary with model scale and deployment configuration, and further annealing does not uniformly improve performance. These findings suggest that harness-supported experience can help reduce the runtime control required by a trained agent.

Large language model (LLM) agents increasingly operate in private environments and accumulate valuable experience from task execution, tool use, feedback, and local knowledge. Yet such experience is distributed across organizations and cannot be directly shared because of privacy and proprietary constraints. Conventional federated learning is insufficient for this setting, as agent capabilities extend beyond model parameters to memory, tools, rewards, skills, and structured knowledge. In this paper, we formulate \textbf{Federated Agent Optimization (FAO)}, which studies how distributed agents can collaboratively improve through controlled information exchange while keeping raw data, complete trajectories, and private knowledge local. We define FAO as a multi-objective problem balancing agent utility, privacy leakage, and communication cost, and organize its optimization space across policy, memory, tool use, reward, and structured knowledge and skills. We further characterize how private experience can be abstracted, protected, aggregated, and adapted into transferable capabilities, providing a unified view of how agents can benefit from one another without direct experience sharing. Finally, we identify the key challenges of FAO and outline several promising directions for future research toward trustworthy federated agent systems.

Tackling complex real-world tasks can exceed the capabilities of a single large language model (LLM), motivating the use of multi-agent workflows that coordinate specialized agents to work together on these tasks. Recent methods train LLMs to construct better workflows from execution outcomes, but they optimize only the workflow generator, while the other agents that build or execute each workflow remain fixed even though every outcome depends on all of them. However, extending training beyond the generator is challenging: the agents are coupled, and a workflow's outcome is a single sparse score that cannot tell which agent causes a failure. We propose FloWright, which leverages the workflow as a harness to optimize workflows. By introducing a hierarchical, structure-aware reward paradigm, FloWright enables one role to self-evolve and two or more roles to co-evolve, with no additional models, labels, or executions. Considering the limitation that workflows are commonly trained and evaluated on data that a single agent can already handle, we further propose DataWright, an adaptive data hardening approach that converts existing datasets into workflow-level tasks with increased difficulty. Across document, slide, chart, code, math, and finance tasks, small open models trained with FloWright achieve improved performance by up to $+7.41\%$, with co-evolving ($+5.03\%$) more roles gaining more than optimizing one of them alone ($+2.83\%$). Our project page: https://xhguo7.github.io/FloWright/.

Supervised fine-tuning (SFT) on offline agent trajectories is the standard approach for training specialized tool-using agents, but forcing models to imitate reasoning and actions token by token may harm other capabilities (e.g., general reasoning, tool calling, code generation) of the base model. In this work, we focus on studying \emph{how to better balance the trade-off between acquiring new capabilities and preserving existing ones during agent trace SFT}. By comparing several baselines in our setup, standard SFT improves the target benchmark while lowering several non-target benchmark scores; meanwhile, simply constraining distributional drift using KL penalty or limiting the update magnitude did not avoid this regression trend. Motivated by recent token-wise adaptive learning objectives, this work proposes \textbf{Privilege-Guided SFT (PG-SFT)} to leverage turn-level information gain of agent trajectories as an indicator to adjust supervision strength. PG-SFT yields a more favorable observed trade-off on the evaluated benchmarks, substantially reducing distributional drift and broad capability degradation at the cost of slight degradation in target-task performance. Our findings suggest that balancing the acquisition--retention trade-off depends not only on whether the model is anchored to its base behavior, but also on where and how strongly supervision should depart from that behavior.}

On-policy distillation (OPD) is a promising approach for training language agents, providing dense teacher supervision on student-generated trajectories. However, in multi-turn interaction, an incorrect action changes the states the student encounters later, so errors compound across turns. In preliminary experiments across three Qwen3 models (8B to 235B), we find that more than half of the failed rollouts contain a pivotal mistake, an action that moves the agent farther from completing the task, and this mistake typically occurs early. These pivotal mistakes often remain recoverable: guiding the model for only a few turns after the pivotal turn can restore task success. We therefore propose PivotOPD, an on-policy distillation framework that jointly trains the student to prevent pivotal mistakes and to recover from the states they create. At each pivotal mistake, a teacher model provides a gold action and then names a recovery action at each of the next few turns. Preventive distillation uses the gold action with reverse KL to steer the student away from the pivotal mistake, while recovery distillation uses the recovery actions with forward KL to transfer recovery behaviors that the student rarely samples. Against 13 baselines on ALFWorld, WebShop, and Search-based QA, PivotOPD achieves the strongest average performance for both Qwen3-1.7B and Qwen3-8B students, improving over the strongest baseline on ALFWorld by +5.5% with the 1.7B student. The gains also transfer to another model family on the software engineering domain, where PivotOPD raises the resolve rate of a Nemotron-3.5 student on SWE-Bench Verified by +3.2%. Project page: https://research.nvidia.com/labs/lpr/pivotopd/

Online training enables computer-use agents (CUAs) to improve through interaction with executable environments. However, existing methods primarily rely on sparse outcome rewards, which provide no supervision for intermediate actions. On-policy self-distillation (OPSD) offers token-level learning signals through privileged rescoring, but directly applying it to CUA online training presents two challenges: fixed guidance may become misaligned with the student's current state, and guidance-induced probability shifts may conflict with step-level correctness. We introduce ComputerSD, an online self-distillation method for CUAs that converts real-time feedback from executed GUI transitions into guidance for policy learning. A fine-tuned GUI analyzer produces guidance and a step-level value score after each action; the guidance provides privileged context, while the score regulates the resulting OPSD signals. ComputerSD jointly optimizes token-level OPSD and trajectory-level GRPO in a fully asynchronous training framework. On OSWorld-Verified, ComputerSD outperforms outcome-only GRPO by 1.9 and 4.1 percentage points on the general-purpose Qwen3-VL-8B-Thinking and specialized EvoCUA-8B backbones, respectively. Evaluation in out-of-distribution settings further supports the generalizability of ComputerSD. These results demonstrate the effectiveness of learning from real-time feedback through online self-distillation for CUAs.

Training LLM agents with reinforcement learning (RL) is bottlenecked by environments, which must provide verifiable rewards, support long-horizon interaction, and scale cheaply. Existing approaches rely on costly human-curated data or on LLM-generated environments that risk hallucinations and benchmark contamination. We show that LLMs can instead be trained into capable search agents using synthetic environments generated entirely by rules, whose generation requires no LLM and has zero marginal cost. We build PhantomEnvironments, multi-turn RL environments from fictional worlds, where agents must search a corpus of templated articles to answer multi-hop questions. Despite sharing no facts with the real world, these strikingly simple environments yield agents that transfer to real-world multi-hop search benchmarks, often outperforming real-world training data on newer benchmarks. Trained agents generalize to unseen fictional universes, and Qwen models learn to scale their search budget roughly linearly with question difficulty, suggesting emergent search scaling from environment interaction alone. Ablating environment complexity reveals that hop count drives transfer more than constraints or comparisons: even the simplest rule-generated environments are a surprisingly effective, free resource for training generalizable LLM agents.

An unsuccessful LLM agent rollout contains more information than its final reward: the observations available to the agent, the actions it chose, and the environment's responses. Reusing this experience for learning requires identifying a decision to revise and testing a concrete alternative. We introduce the Agent Error Dataset (AED), comprising 50,228 error-diagnosis pairs from 9,961 source tasks across 33 environments, 19 harness families, and 23 policy models in text-based agent systems. We retain source traces and execution metadata to support cross-setting failure analysis and re-diagnosis without repeating the original rollout. Our five-stage Agentic Error-to-Training (AET) pipeline collects natural failures, generates diagnoses and proposed corrections, and checks them against recorded evidence. Where replay is supported, we compare corrections with original-action retries from the same checkpoint under matched execution settings. We then construct separate training views for diagnosis and actor recovery. Across 3,062 matched replay pairs, first-proposal corrections raise verifier pass rates from 18.4% to 51.1%, a gain of 32.7 percentage points. Using a separately frozen diagnosis release, full-diagnosis fine-tuning on 1,656 source tasks raises Qwen3-8B's exact-step agreement with internal teacher labels from 47.2% to 63.6%, averaged over three seeds on a 943-case holdout. The strongest prompted reference in this comparison scores 54.7%, and mean agreement improves at each of four increasing training-set sizes. In a single-seed comparison of actor-training recipes, action-only repair training scores 6.67 percentage points higher on WebShop-lite than success-only training.

GUI agents built on large language and vision-language models still struggle on unseen applications and complex multi-step tasks, as completing real GUI tasks depends on app-specific, temporally volatile operational knowledge that is scarce in pretraining corpora. Retrieval-augmented execution offers a natural remedy but faces two coupled bottlenecks: knowledge at scale is hard to acquire, and self-collected priors inevitably drift from the live environment due to version updates, promotions, ads, A/B tests, and personalization. We therefore argue that GUI agents should not pursue perfect knowledge but learn to act correctly under imperfect priors, and propose our framework that couples knowledge acquisition with noise-robust utilization: a structured exploration strategy traverses interactive elements, builds a UI state-transition graph, and synthesizes (task, trajectory) pairs via a VLM without human annotation; a noise-aware training strategy, grounded in a taxonomy of real GUI drift patterns, injects five types of realistic errors into self-explored trajectories to teach the agent to assess prior reliability before acting. Experiments on physical devices and online emulator benchmarks show that our method discovers more unique screens, covers more benchmark tasks, and more effectively rejects erroneous priors while leveraging correct ones, with accuracy gains that transfer across datasets.

The ability of Large Language Model (LLM) agents to complete daily and professional work is receiving increasing attention. Training such agents requires realistic work scenarios. Expert-authored occupational work is costly and slow to produce, while unconstrained synthesis often yields tasks with weak factual grounding or internally inconsistent requirements. To bridge this gap, we introduce WorkGenesis, a framework that constructs executable occupational work from real-world artifacts through two core technical innovations: (1) Evidence-Based Work Construction, which grounds each unit of work in real-world evidence by retrieving public files guided by O*NET occupational knowledge and synthesizing the surrounding context, companion materials, work request, and itemwise rubric around them; and (2) Execution-Guided Consistency Verification, which renders a reference deliverable inside the constructed work, attributes every unsatisfied rubric item to the agent, the task, or the rubric, and uses task and rubric defects as feedback to iteratively repair the work until it passes the audit. Experimental results demonstrate that Fx-Work-35B, trained with simple supervised fine-tuning (SFT) on only 20K units of work synthesized by WorkGenesis, achieves the highest scores among all comparable-scale baselines on the five reported metrics across GDPvalAA-v2, APEX-Agents-AA, and JobBench (31.00 versus 24.79 average score), and even surpasses frontier models such as the 1.6T DeepSeek-V4-Pro-Preview. These results show that WorkGenesis provides scalable training data for working agents.

Working agents need to read diverse files, coordinate tools, and produce deliverables. Training such agents requires tasks built on many real files with verifiable results, but few pipelines exist to synthesize this kind of data. Existing pipelines either generate files with models, which lack realism and diversity, or build tasks on real files without task-specific verifiers, leaving result quality unchecked. We introduce GraphForge, an evidence-graph based framework that grounds both the task and its verification in real files. Starting from occupation-grounded seeds for controlled diversity, GraphForge assembles a workspace of real files for each seed and builds an evidence graph over their relations. Since the task statement and rubrics are both derived from this graph, task requirements are backed by the workspace files and each criterion is anchored to the files needed to verify it. An initial rollout further tests executability, and a revision agent repairs the task and rubrics against the original files before trajectories are collected. Fine-tuning Qwen3.6-27B on 2,169 GraphForge trajectories brings GDPVal to 1445.7 (+65.7) under OpenHands, and Workspace-Bench-Lite and SpreadsheetBench II to 63.7 (+7.7) and 24.0 (+13.7) under Claude Code. Rejection fine-tuning on the SFT model's own rollouts, with candidates selected by the evidence-anchored rubrics, yields further improvements on all three benchmarks, suggesting that the rubrics provide a useful selection signal.

LLM agents often admit multiple high-quality solutions to the same task, differing in reasoning structure, tool-use pattern, or interaction trajectory. Yet existing notions of diversity in LLM post-training are mostly implicit, arising from general stochasticity and regularization mechanisms rather than explicitly targeting task-relevant behavioral variation. While such implicit diversity can be useful, it does not directly specify which forms of behavioral variation should be encouraged for a given task. In this work, we study explicit trajectory diversity in RL-based post-training for LLMs. Our key idea is to define diversity through user-specified, task-specific trajectory descriptors, which map each sampled trajectory to an interpretable behavioral representation, and then measure diversity as a set-level functional over the resulting descriptor matrix. Building on this formulation, we introduce Trajectory-guided Joint Policy Optimization(TJPO), a single-policy framework that optimizes explicit diversity over sampled trajectory groups, avoiding the need for population-based policy training, and instantiate it within group-based policy optimization through trajectory-level learning signals. This design makes the diversity objective both interpretable and controllable. Experiments on Sokoban and ALFWorld show that TJPO improves task-specific trajectory diversity while maintaining competitive task performance. Descriptor and trajectory analyses show that the learned variation follows the specified behavioral dimensions and includes distinct successful strategies. Extra experiment results suggest that explicitly shaping trajectory diversity can help LLM agents satisfy user requirements and remain effective when task conditions change.

Graph agents extend large language models (LLMs) with the ability to actively explore and reason over knowledge graphs through multi-step interactions with graph tools. However, training capable graph agents typically requires large collections of question-answer pairs and reasoning trajectories, whose manual construction is costly and difficult to scale. Moreover, employing proprietary LLMs to generate such supervision further risks exposing sensitive graph data to external services. Therefore, we propose GraphCert to bootstrap agentic graph reasoning with certified evidence rubrics during post-training. Specifically, the Bootstrapped Graph Quizzer guided by generation controls produces graph-grounded QA pairs and marks supporting evidence, which undergo execution certification and semantic curation. The accepted evidence is then canonicalized into certified evidence rubrics that later reward Graph Solver evidence alignment alongside answer correctness during GRPO training. Experiments on five graph reasoning domains in GRBENCH demonstrate that GraphCert consistently outperforms substantially larger LLM agents and post-training method. Furthermore, our analysis demonstrates that the learned policy transfers robustly across heterogeneous graph domains, suggesting that GraphCert acquires reusable graph-reasoning capabilities rather than domain-specific patterns. These results establish executable self-certification as an effective approach to self-training compact graph reasoning agents. Our code will be made publicly available.

Large language models (LLMs) are increasingly deployed as agents for multi-step decision-making, yet transfer poorly to unseen environments. World-model methods address this by training agents to predict future observations, at the cost of additional training and errors that compound when predictions are used for planning. However, for LLM agents operating in digital environments, much of this world knowledge is already internalized during pretraining, which shifts the problem from acquiring it to eliciting it. We argue that typical post-training provides little pressure for such elicitation, since supervision under a single goal at each visited state inadvertently drives policies to rely on superficial contextual habits. We introduce EVOKE, a post-training method that supplies this pressure through goal diversity at fixed states. Motivated by theory showing that an agent competent across diverse goals must encode a world model recoverable from its action preferences, EVOKE holds the environment state and interaction history fixed and ranks the same candidate actions under alternative goals, forcing action preferences to change, so that a policy relying on contextual habits or single-goal correlations cannot order them correctly. This implicitly elicits the policy's pretrained world knowledge to inform decisions. We evaluate EVOKE across diverse tasks in three backbones, demonstrating improved task performance, unseen environment generalization, and data efficiency. We further conduct controlled analyses to better understand what drives these gains. These findings offer a new perspective on eliciting internalized world knowledge for transferable action through direct decision supervision.

Risk aversion in resources could prevent misaligned AI agents from causing catastrophic harm. Misaligned but risk-averse agents would tend to favor safer strategies like making deals with humans over riskier strategies like rebelling. We train agents to be risk averse through character training, finding that persona traits provide a robust mechanism for instilling risk preferences. To do this, we construct a model constitution describing constant absolute risk aversion (CARA) over an agent's resources and instill it through on-policy distillation. Despite never seeing the benchmark's decision format during training, character-trained models are competitive with baselines trained directly on it, and generalise better than them out of distribution on two of our four models. We also modulate different aspects of the constitution, finding that token budget and model choice are the most influential aspect of character training to instill risk aversion. We conclude from these results that character training is a promising and scalable way to instil broad dispositions, which we can use to our advantage in mitigating risk from misaligned AI agents.

Computer use agents (CUAs) have demonstrated strong capabilities in completing digital tasks. However, existing CUAs either rely solely on graphical user interface (GUI) interactions, which are often inefficient and error prone, or augment GUI interactions with application specific APIs or tools, which require substantial engineering effort and are difficult to scale across applications. We argue that the next generation of CUAs should combine GUI interactions with the command line interface (CLI), leveraging the generality of the GUI and the efficiency of shell commands. A critical challenge, however, is that current models do not know when or how to use the CLI during task execution. To address this challenge, we develop a data construction pipeline that produces three types of trajectories: GUI only, CLI only, and interleaved GUI and CLI trajectories. This pipeline results in HybridCUA-8K, containing 5K hybrid trajectories and 3K verified RLVR tasks. Building on these data, we propose a training framework with two stages: supervised fine tuning on the constructed trajectories, followed by reinforcement learning with our CLI aware rewards that encourages agents to use the CLI selectively and reliably. Experiments show that HybridCUA-9B achieves 53.6% accuracy on OSWorld, improving over the base model by 14.8 percentage points, and improves performance on WindowsAgentArena by 4.0 percentage points. These results demonstrate the effectiveness and cross platform generalizability of the hybrid GUI and CLI paradigm for computer use agents.

We present AREX-2, an effort to advance the self-improving capability of LLM agents, which we define as the ability to iteratively refine a solution at test time. This ability rests on two complementary capabilities: reflection, which produces a solution better than the current one, and long-horizon execution, which keeps the iteration effective over many rounds. We hypothesize that both capabilities are domain-agnostic, and can therefore be learned in scenarios that are well suited for supervision. Accordingly, we synthesize long-horizon improvement trajectories from machine learning and algorithmic programming tasks, two domains that offer verifiable feedback and reward sustained iteration. Trained on this data, our agent, built on Qwen3.8-27B, achieves strong results on MLE-bench Lite (81.8) and Frontier-CS (70.7), transfers to deep research with 84.0 on BrowseComp, 52.6 on HLE, 92.2 on GAIA, and 93.8 on DeepSearchQA, and keeps improving as its budget of rounds grows. These results show that long-horizon reflective data is an effective route toward self-improving agents.