每天知道
你的领域
出了什么

Long-horizon information-seeking agents often accumulate noisy or misleading context, causing early mistakes to persist and making recovery increasingly difficult. We introduce an autonomous search harness in which the agent manages its own search process through three states: Rubric, Answer, and Verify. The agent first defines criteria for a valid answer, searches under these criteria, and then independently verifies the result before deciding whether to terminate or continue searching. It is further equipped with a Seal Memory tool that enables active context management. Training this behavior with reinforcement learning, however, can induce Seal Collapse, resulting in unstable training and preventing the agent from reliably learning when and how to use its memory tools. We solve this with a simple strategy that trains only the final segment after context management. Our 35B model achieves 72.83 on BrowseComp, outperforming comparable open-source systems, and consistently improves over the base model across BrowseComp-ZH, xbench, DeepSearchQA, WideSearch, financial investigation, and product search. Ablations show that autonomous compression outperforms automatic compaction and validate our RL design.

Average performance on routine driving benchmarks does not establish planner reliability under rare, safety-critical hazards. We proposed ExceptionDrive, a counterfactual planning benchmark that uses VLM-assisted screening, localized multi-view editing, and quality auditing to insert hazards into real nuScenes scenes while preserving their context. Its 21 tasks span six safety families and define hazard or conflict regions, local safety constraints, and acceptable responses. Because hazard insertion can invalidate the recorded human trajectory, our reference-free protocol evaluates edited predictions using Unsafe Rate (UR), Hazard Clearance Compliance (HCC), Hazard Proximity Response (HPR), and Counterfactual Trajectory Shift (CTS), which measure core-region intrusion, clearance compliance, clearance relative to a prescribed margin, and counterfactual trajectory change. Seven representative planners frequently intrude into hazard regions or provide insufficient clearance. We also develop a Reminder Agent that, without sample-specific task labels, converts visual evidence and the shared taxonomy into structured records of hazard presence, type, and a recommended high-level strategy. The agent neither predicts trajectories nor controls the vehicle; its records guide a VLM-based decision agent. In zero-shot experiments, the reminders improve strategy accuracy and reduce under-warning.

Agents can learn from past executions, but enabling different agents to reuse and build on one another's experience remains challenging. We introduce EpiCon, a shared multimodal memory framework for agent collective learning without updating host model parameters. EpiCon links question-level memory evolution to a persistent experience bank through two independently trained 2B models: a memory controller and a tree self-organizer. The controller jointly refines textual guidance and visual evidence across attempts and selectively includes visual memory. The self-organizer consolidates lessons hierarchically and retrieves experience and rules for new problems. We evaluate EpiCon on eleven benchmarks spanning four multimodal task domains, using two harnesses and multiple backbones. A frozen bank improves other systems even with a single solving attempt. A second harness raises the original system's macro-average score by 2.6 points across eleven benchmarks. Across four host configurations, EpiCon improves macro-average scores by 1.7 to 4.9 points over No Memory and reduces memory-operation time by 67% to 74% relative to backbone-sized memory models.

World-action models (WAMs) jointly predict how a scene will evolve and how an agent should act, however joint generation alone does not necessarily impose a shared geometric constraint on these predictions. We present PhysWAM, a unified world-action model for autonomous driving that co-denoises multiview video, metric depth, and ego motion within a single flow-matching transformer. To ground world and action generation in measured scene geometry, we introduce Coupled Point Projection (CPP) that unprojects the generated depth into 3D points, transforms them using the generated $\mathrm{SE}(3)$ ego motion, and minimizes their distance to LiDAR points transformed using the recorded ego motion. This geometric constraint promotes physical consistency with the measured scene by jointly supervising generated depth and motion alongside their standard flow-matching objectives. At inference, trajectory selection relies only on a simple label-free consensus rule, with no learned scorer or simulator feedback. We evaluate PhysWAM across NAVSIM v1 and v2 planning, zero-shot closed-loop transfer, and future video and metric-depth prediction. Despite PhysWAM's simple selection procedure, it achieves strong planning performance and transfers zero-shot to unseen driving environments. It also generates accurate metric depth and temporally coherent video, with CPP improving both planning and depth prediction. Together, these results demonstrate that the geometric relationship between scene depth and ego motion provides a direct way to couple world and action generation within a simple unified model.

Chain-of-thought traces are widely read as records of how models reach their answers, informing debugging, agent auditing, and claims about reasoning. Testing this interpretation is difficult because natural-language thinking traces are rarely mechanically verifiable. We revisit it in iGSM, a synthetic grade-school mathematics benchmark designed to study thinking traces and used to support claims of learned reasoning and planning. Crucially, iGSM exposes the exact quantities and dependencies that a correct solution should use, allowing generated traces to be checked programmatically step by step and enabling us to test whether correct answers are reliably accompanied by valid traces. We first evaluate models trained exclusively on valid, minimal traces. Answer correctness and trace validity nearly coincide in distribution but decouple out of distribution: on the hardest instances, 31.6% of correct answers have invalid traces, over half of which pass all syntactic and arithmetic checks but fail semantic dependency checks. We then intervene on trace supervision. Non-minimal training traces induce non-minimal outputs, while re-asking the same problem with a different query reveals computations inherited from the original query, weakening minimality as evidence of selective planning. Shuffling tokens in 10% of training trace sentences preserves near-clean accuracy even out of distribution despite no trace passing verification. Swapped training traces likewise retain high in-distribution accuracy. We discuss the implications of these findings for chain-of-thought monitoring and interpretation in the context of AI safety.

Agent skills provide a lightweight mechanism for self-evolving agents to accumulate reusable procedural knowledge without updating model parameters. However, existing learned skill curators typically optimize curation without explicitly modeling downstream executor behavior. We show that this can cause systematic cross-executor degradation: curators trained with different executors perform best when paired with their own training executor, indicating that effective skill curation is executor-dependent. We formulate behavior-adaptive skill curation and introduce EASE, a framework that learns a single curator that adapts its decisions to different executor behaviors. EASE maintains an online behavioral profile of recent execution patterns and conditions the curator on this profile, the current trajectory, and retrieved skills to add, modify, or remove skills from an evolving repository. We train the shared curator jointly across multiple frozen executors with reinforcement learning, using retrieval-aware and behavior-aware temporal attribution to focus optimization on curation actions with observable downstream influence. Across ALFWorld, ScienceWorld, and WebShop, with executors ranging from Qwen3-8B/32B and GPT-OSS-120B to unseen Kimi K2.6, DeepSeek V4 Flash, and Gemini 3.5 Flash, EASE outperforms strong skill- and memory-based baselines without per-executor finetuning. EASE also maintains 34.5--41.0% fewer skills, improves skill retrieval by 36.3--38.7% and measured edit utility by 51.8--60.0%, and reduces deployment-time inference tokens by 9.1--14.5%. These results establish behavior-adaptive skill curation as an effective principle for building self-evolving agents.

To advance the development of embodied intelligence, Open-Environment Active 3D Mapping has attracted increasing attention, aiming to perform a long-horizon and shortest trajectory exploration for reconstructing unseen scenarios. Since only limited information about unseen environments is available, methods built on the closed-set assumption, i.e., assuming that the test environments are similar to those seen during training, cannot generalize satisfactorily. In existing active mapping methods, long-horizon exploration is often guided by predicting a coarse long-range goal and then converting it into an executable path. However, this stage is usually formulated as single-point prediction. Under partial observability, the same local observation may correspond to multiple plausible exploration directions, making such deterministic prediction prone to brittle decisions and degraded performance in unseen scenarios. Our experiments further verify that this is a key factor underlying their weak generalization. To address this issue, we reformulate long-horizon target prediction as conditional multimodal anchor generation using Conditional Flow Matching.Instead of predicting a single goal, our method learns a conditional distribution over coarse exploration anchors from the current mapping state. These anchors are first converted into executable candidate paths through obstacle-aware planning. We then apply exploration-mode clustering to compress geometrically similar trajectories and reduce candidate redundancy. Finally, a hierarchical selection module selects the most promising mode and reranks paths within it to produce the final executable trajectory. Experiments show that our method improves generalization and reconstruction efficiency in open environments.

Power-sharpened sampling is an inference-time alternative to reinforcement-learning (RL) post-training for enhancing reasoning in large language models (LLMs). High-probability sequences are amplified under the base model without parameter updates or external rewards, avoiding the costly optimization and jagged generalization of RL. However, this approach faces a fundamental exploration--exploitation trade-off, as % strong sharpening restricts exploration, trapping samplers in plausible but incorrect reasoning trajectories, whereas weak sharpening leaves the answer distribution diffuse. To resolve this trade-off, we introduce Parallel Power Tempering (PPT), instantiating power-sharpened LLM sampling via parallel tempering. Running multiple interacting replicas in parallel at different sharpening levels allows lower-power replicas to explore diverse reasoning trajectories and higher-power chains to further exploit higher-likelihood responses favored by the sharpened target. Specifically, we tailor \method{} to inference-time sampling by mitigating a truncation bias, identified in prior power samplers, and investigate effective swap strategies under finite memory and compute budgets. Extensive experimentation shows that \method{} substantially improves single-chain power-sharpened sampling and outperforms RL-post-trained models, producing higher-quality reasoning traces and even achieving performance comparable to frontier models.

Software engineering agents increasingly use reusable skills distilled from prior experience to resolve repository-level issues, yet such skills often fail to transfer across repositories. A central challenge is that a behavior appearing in a successful trajectory is not necessarily responsible for the successful outcome: it may be genuinely useful, merely incidental, or simply a recurring habit of the model. We introduce XRepoSkill, a trajectory-based approach for learning transferable skills. We represent a skill as a collection of rules, each specifying what action to take and when to take it during issue resolution. XRepoSkill first contrasts successful and failed trajectories of the same agent on the same issue and derives candidate rules from where their execution paths diverge. Each rule is paired with an executable predicate that enables its prescribed behavior to be evaluated systematically on other trajectories. A rule is verified based on its association with successful issue resolution and retained only when its prescribed behavior recurs across multiple repositories; repository-specific variants of the same behavior are then consolidated into transferable rules. For a new issue, XRepoSkill selects relevant rules to guide the agent. We learn skills from publicly released trajectories on the official SWE-bench Verified leaderboard and evaluate them on SWE-bench Pro and DeepSWE using three backbone LLMs from different vendors; none of the evaluation repositories appears in the skill-learning trajectory pool. Against three recent skill learning methods, XRepoSkill achieves the highest issue resolution rate in all six benchmark--LLM combinations. In particular, on the challenging long-horizon DeepSWE benchmark, XRepoSkill improves issue resolution by 10.3 percentage points over the same agent without learned skills and by 5.0 points over the strongest skill-learning baseline.

As the capabilities of large language models (LLMs) continue to advance, increasing attention is turning to how to translate their abilities into useful behavior. Personal agents bring this question into everyday settings, where models are expected to serve individual users and continually adapt to their preferences. With the underlying model held fixed, such adaptation relies on harness engineering: designing and evolving the surrounding layer that manages context, memory, tools, and execution. Despite rapid progress, the factors governing effective harness evolution remain insufficiently understood. To narrow this gap, we investigate three central questions concerning harness architecture, harness scale, and self-evolution algorithms through complementary empirical and theoretical analyses. Empirically, we introduce a preference-oriented benchmark and systematically characterize the capabilities and limitations of personal agents associated with these three dimensions. Theoretically, we formulate harness evolution as a learning problem and explain these phenomena through approximation, generalization, and optimization errors. Analyses of reachable policies, capacity under finite interaction evidence, and biased update dynamics provide theoretical accounts of the observed phenomena. Together, these results offer a unified perspective on the limits of personalization through harness evolution and inform future harness design.

Tool-using agents are entering settings where a wrong action carries real cost, and the benchmarks certifying them grade what each simulated tool call reports having done, assuming the tool did what its interface advertises. The audit taxonomies we survey publish no category for that assumption, and a defect beneath a score is present on every rerun. We treat a tool's advertised surfaces as an executable contract, check the implementation against it, and trace each score's provenance through the task files and evaluator code to the verdicts that derive from state a defective tool should have written. Across 34 audited mutating tools in four benchmarks we confirm seven tool defects and one evaluator property at pinned commits. On injected defects the checker raised no false positive in 25 flags, flagged 2 of 5 negative controls, and missed most: in 29 of 33 scored misses a clause covered the defect but no probe revealed it. The checker's own static half, run alone, flags 14 of 17 confirmed sites, so on these findings the dynamic half confirms and traces rather than discovers. Twelve further AgentDojo tools, with six held-out tools and the seven audited first, complete its 25-tool mutating surface, on which at least 5 tools diverge from their advertised surface as our contracts read it, a rate for AgentDojo alone. No gold trajectory reaches either tau2-bench defect; on 1,120 paths built to isolate the telecom defect, a number fixed by construction, the evaluator rewards a refuel of a suspended line and fails the repaired tool. The clearest case is a clinical benchmark whose tool tells the agent each write executed under a documented no-write design its interface does not disclose; its grader takes that message as evidence, so its action success rate records whether a request carried the expected payload, not whether any record changed.

Skills equip LLM agents with professional knowledge and guidance to complete long-horizon and complex tasks. Although skills have been widely adopted in recent agent paradigms and harnesses, how to synthesize reliable training data and how to train agents for skill use remain underexplored. In this work, we propose SkillGym, an automatic pipeline to build verifiable environments, collect trajectories, and train skill-use agents. SkillGym first crawls a large volume of skills from the internet, then keeps those whose workflows can run reproducibly offline. A builder-reviewer pipeline is used to construct difficulty-controlled tasks, spanning four task types, each with a reference solution and an executable verifier. With this pipeline, we build 6.8k environments and collect 19k verified successful trajectories for supervised finetuning. Finetuning on these trajectories improves LLMs of different families and sizes, from 2B to 122B parameters across four skill-use benchmarks; Our Qwen3.5-9B SFT model outperforms the 397B untrained model on two of them. Further analysis shows that training teaches agents to invoke skills, raising the rate of reading the relevant skill from 28% to 96%, and that the gains hold across reasoning structures, extending to task types that form a minority of the training data and to skills held out from training

LLM agents performing long-horizon tasks accumulate tool results that later steps may need. Passing the full history to every invocation is costly even when it fits within the context window, while reducing it risks omitting needed information. Existing context management methods can overlook how earlier tool results are used in subsequent execution, leaving needed information out of context. We introduce ContextRender, which manages context through a persistent graph of execution dependencies. We develop Tool-Flow Analysis to track how later operations reuse information from earlier tool results, providing a signal called observed reuse. A renderer combines this signal with recency and semantic relevance to select results within a fixed history budget, retaining omitted results for later use. Across AppWorld and 8-objective QA with three execution models, ContextRender outperforms the evaluated context management baselines using a 6K history budget, well below the models' maximum context windows. Within this budget, it achieves task performance close to or above that of passing the full history while reducing mean inference cost by 10.2%-32.2% relative to Full history. Ablations show that observed reuse improves task performance and retention of results reused later.

Vision-language-action and world-action models have demonstrated impressive capabilities in robotics, yet generalization to unseen tasks remains challenging. More recently, general-purpose multimodal agents have shown great potential for zero-shot robotic task solving. However, they often incur high execution costs by reasoning and exploring the physical world from scratch. To reduce these costs, we introduce RoboSkill, a framework that connects skill acquisition and reuse through an Explore, Execute, Evolve loop. Within this loop, the agent explores to gather task-relevant information, executes tasks while adapting to feedback, and evolves its skill library based on execution records. It then reuses these skills to guide exploration and execution in the next cycle, closing the loop. To improve loop efficiency, we complement vision with tactile feedback to reduce uncertainty during physical interaction. We further augment textual guidance with reusable code to reduce reasoning overhead during skill reuse. On LIBERO-10, RoboSkill improves first-episode success rates by 12.5--25.0 percentage points and reduces average runtime by 7.6--72.4% across four agents. On real robots, it improves success rates by 8.3 percentage points and reduces average runtime for successful trials by at least 14.4%.

Fully asynchronous reinforcement learning (RL) improves resource utilization in large language model post-training by overlapping rollout generation with policy optimization, but it also introduces policy lag as trajectories are generated and queued while the trainer continues to update. We study how this lag accumulates over a trajectory's lifetime and how it can be controlled without sacrificing the wall-clock benefits of asynchronous execution. We decompose trajectory staleness into Generation Staleness, accumulated before rollout completion, and Waiting Staleness, accumulated after a completed trajectory enters the pool. Motivated by this decomposition, we introduce PACE (Pool-Aware Control of Effective Staleness). PACE converts excess pool occupancy into an adaptive rejection budget and ranks completed trajectories using an effective-staleness score that combines Waiting Staleness with prefix-aware Generation Staleness. This avoids penalizing long or interrupted rollouts solely because they span multiple policy versions. In single-turn mathematical reasoning, PACE improves the six-benchmark average validation accuracy by 18.7% over unfiltered asynchronous RL at the same wall-clock budget and matches synchronous RL performance with 47.1% less GPU time. PACE also improves validation performance in multi-turn tool-integrated reasoning, outperforming both synchronous and unfiltered asynchronous RL. Further experiments with the mixture-of-experts model and an alternative RL algorithm support its applicability across model architectures and training algorithms.

Post-training has been shown to significantly improve language models' performance on tasks with verifiable outcomes, including mathematical reasoning, software engineering, and computer use. However, whether the same approach can improve forecasting in financial markets is much less clear. Compared with tasks with verifiable outcomes, not only are realized returns noisy, but even what constitutes a relevant information set for making effective predictions is not obvious a priori: the model must decide which observations to gather and then commit to a numerical judgment before the outcome is known. We study this question in a chronological stock-price sandbox, where a language model gathers price, volume, relative-performance, and market-context evidence and predicts a future return. We post-train Qwen3-4B with supervised fine-tuning (SFT) on tool-use demonstrations, then proximal policy optimization (PPO) with a terminal reward given by the forecast score against the realized return. The resulting AURA-4B more than doubles the starting direction--magnitude score, from 20.94 to 43.31, and is comparable to frontier language models on this benchmark. Conditional magnitude agreement rises from 33.3 to 66.2, while directional accuracy changes from 62.9 to 65.4. SFT expands tool use, and PPO further increases the share of ranking and market-context queries. These results show that post-training can substantially improve financial forecasting performance, together with changes in how the model investigates the market, on this outcome-selected benchmark.

Prospective memory allows an agent to retain an intention tied to a future condition, but the stored intention does not reveal whether that condition currently holds. Checking it may require web access, multi-step tool use, and paid calls. Existing systems decide when intentions require attention, but do not allocate the resulting observations under a shared budget. We introduce the first resource-allocation formulation for the external observations required by stored intentions under a shared episode budget. BudgetPM offers two policy variants that share a hard-budget executor. BudgetPM-Static uses a lightweight Logistic scorer to learn whether a check improves the current decision. BudgetPM-Sequential distills full-episode hindsight schedules into a lightweight policy that decides when to spend or reserve capacity using only pre-query information at deployment. We evaluate BudgetPM against two public memory-agent systems, five matched controls, and four hand-designed monitoring or budget-adaptation rules. Across two benchmarks and three backbones, BudgetPM-Static outperforms adapted Mem0 and PMA workflows. On PM-Bench, its Logistic scorer reaches competitive quality--cost operating points alongside higher-capacity scorers and retains 99.9--100% of unconstrained quality with 42--54% fewer observations. Under severe scarcity and the same hard caps, BudgetPM-Sequential exceeds the strongest tested natural monitoring schedule by 1.92--2.58 Set F1 points. It reaches the same Set F1 and on-time recall with 16--33% fewer observations. Matched attribution, exact-cost analysis, and a fixed-budget load intervention link this gain to competition between present and future opportunities. These results yield a demand--capacity design rule: local gating works when capacity covers demand, while future-aware supervision adds value when observations compete across time.

Agentic reinforcement learning (ARL) with verifiable rewards improves the ability of large language models (LLMs) to tackle knowledge-intensive tasks by learning to interleave search and reasoning. However, most existing ARL methods optimize only LLM-generated tokens and treat retrieved evidence as environment observations. This creates an information-credit gap: failures caused by missing or misleading evidence are attributed to the LLM policy rather than to the retriever, which motivates training the LLM and the retriever jointly. In this paper, we show that retrieval and LLM policy learning are order-sensitive: adapting the retriever before optimizing the policy yields a larger reward gain than the reverse order. To preserve this hierarchy while allowing both components to co-adapt, we formulate retrieval-augmented agentic RL as a bilevel optimization problem. To solve it efficiently, we introduce BRIDGE, a memory-efficient first-order bilevel method motivated by a loss-landscape analysis of the RL and retrieval objectives. Across seven open-domain QA benchmarks, BRIDGE achieves the highest average accuracy with both 3B and 7B backbones, improving the multi-hop average over the strongest baseline by 9.6 and 3.4 EM points, respectively. It also achieves the best averaged answer accuracy and reasoning quality across medical QA benchmarks.

Large language model (LLM) agents reuse external memory to guide new tasks, but effective retrieval requires learning which memory sets improve execution. Such learning relies on costly outcome feedback: ordinary retrieval observes only executed sets, while evaluating alternatives requires additional rollouts. We introduce \textsc{UpliftMem}, which learns memory retrieval from set-level execution uplift relative to the same executor without memory. A theoretical analysis of how retrieval preferences restrict feedback coverage motivates targeted probing of alternative memory sets. Probe selection follows an expected value of sample information (EVSI) criterion, derived in closed form under a correlated Gaussian model, to allocate limited training rollouts according to their expected improvement in local retrieval decisions. The shared scorer is trained with a frozen executor and selects memory sets without test-time probes. Across ALFWorld, WebShop, and BigCodeBench, \textsc{UpliftMem} achieves the best success rates among evaluated baselines on the main evaluation sets. Controlled fixed-store and matched probe budget evaluations further demonstrate improved memory-use decisions and more effective use of execution feedback.

Recent approaches to reinforcement learning (RL) post-training for large language models increasingly remove the critic to reduce training instability and memory overhead. Even where a critic is trained, it is discarded once training ends, although it has learned to predict outcomes. We revisit this trend and show that a pretrained critic's ability to predict future outcomes can make it a valuable asset for efficient long-horizon reasoning. First, we find that instability in critic-based RL for long chain-of-thought reasoning is largely an optimization artifact: keeping policy updates small and low in variance restores stable convergence. Second, a well-pretrained critic estimates the posterior probability of eventual success from later trajectory states and unfinished prefixes. Its predictions provide outcome-derived, dense, per-prefix learning signals that, during policy optimization, require neither completed rollouts, step-level annotations, nor external reward labels. Building on this insight, we introduce Reward-Free Policy Optimization (RFPO), which repurposes a single calibrated, frozen critic as a rollout-level reward, a value baseline for generalized advantage estimation, and a success forecaster for unfinished prefixes. We further show that binarizing the debiased score stops the policy from exploiting the critic's length bias. Binarized, RFPO matches supervised PPO without a single label in the training loop, while cutting compute and memory overhead. This makes RFPO well suited to long-horizon reasoning tasks, where outcomes arrive late and generation dominates cost: because rollouts can be rewarded before they finish, training no longer has to pay for waiting on every trajectory to complete. Our findings challenge the prevailing critic-free paradigm and establish critic-based, reward-free optimization as a scalable and computationally efficient path for LLM post-training.

Large language models (LLMs) are increasingly deployed to solve complex scientific and practical problems via iterative optimization. However, dynamically coordinating diverse search mechanisms as candidate quality, failure modes, and resource budgets evolve remains a critical open challenge. Targeted empirical diagnostics reveal that mechanism effectiveness is highly state-dependent. Motivated by this, we analyze how individual decisions drive final outcomes, decomposing the expected terminal improvement under a shared budget into cumulative decision opportunities minus cumulative selection losses. Guided by this opportunity-loss theoretical foundation, we propose OptiCom, a unified framework that represents LLM-driven optimizers within a shared configuration space: C=(A,Q,O,E,M,S), corresponding to artifact, query, operator, evaluation, memory, and strategy. Operating within this space, a fast LLM-based Optimization Controller dynamically composes immediate mechanisms through structured Action Packages, while a slower Strategy Adapter refines long-term selection preferences, operator weights, and templates based on accumulated trajectory feedback. Comprehensive evaluations across 32 benchmark groups demonstrate the superiority of framework: OptiCom achieves an average Max-score rank of 1.72 among 14 evaluated configurations, securing the top score in 23 groups. Ultimately, these results highlight the broad applicability and high extensibility of OptiCom as a general-purpose paradigm for robust LLM test-time scaling.

Content-generation agents continuously receive impressions, clicks, conversions, and negative feedback from recommendation systems, providing real-world outcome signals for memory evolution. However, these signals are delayed and noisy, confounded by audience composition, placement, and recommendation policies, and may result from the combined influence of multiple memories, making accurate attribution difficult. Existing methods rely primarily on immediate feedback or semantic retrieval and therefore struggle to reliably translate recommendation outcomes into memory fitness. To address this challenge, we propose TIDE (Trajectory-Informed Directed Memory Evolution), an external memory evolution framework driven by delayed recommendation feedback. We further introduce Memory Evolution Gain (MEG), which measures the utility improvement of evolved memory over a no memory baseline on strictly future tasks. TIDE treats memory as a capacity-constrained population of experiences: temporal and semantic credit assignment estimates contextual fitness, while responsibility credit distributes outcome signals according to the memories referenced during generation. These signals are then used to reinforce, crossover, mutate, or evict memories. On an e-commerce membership marketing content-generation agent, TIDE achieves a +7.75-percentage-point MEG in offline temporal replay and significantly improves both unique click-through rate (UCTR) and activation rate in an online A/B test. On a delayed-label benchmark, TIDE achieves the lowest mean absolute error (MAE) and root mean squared error (RMSE) and the highest MEG among the compared methods, demonstrating its effectiveness.

LLM agents accumulate interaction histories that grow linearly with task length, causing quadratic inference cost scaling and performance degradation from attention dilution. Existing context-compression methods learn what to discard offline: by contrastively optimizing guidelines, distilling compressors, or training compression policies. This incurs a substantial cost. Further, the compression policy is learned a priori and is not dynamically conditioned on the evolving test-time trajectories. In this paper we ask a complementary question: Which past interactions causally shape the agent's future decisions? We recast context compression as a causal decision preservation problem over discrete interaction units and introduce FOCUS, a training-free context compression framework that operates entirely at test time. Our method requires no offline data collection or fine-tuning, and is architecture-agnostic, attaching to any closed-API frontier model as a modular compression layer. We evaluate FOCUS on diverse agentic benchmarks including API and tool-calling, QA, web domain and multi-turn dialogue. Our method establishes new state of the art performance, cutting peak context by up to 48% and dependency by 73% while improving task success by up to 8.9 percentage points over uncompressed execution.

Autonomous agents have made rapid progress in general-purpose computer use, yet reliable automation of professional industrial engineering remains out of reach. Engineering workflows require reasoning over geometric and physical constraints and keeping dependencies consistent across software and design stages. We present EngiWorld, a benchmark designed around the capabilities that real engineering projects require, from operating a single application to solving engineering problems end to end. It contains 1,301 expert-curated tasks spanning six engineering domains (CAD, CAE, CAM, BIM, EDA, and DCC) and 26 professional software applications, with both GUI and CLI interfaces. The tasks are organized into six types, corresponding to capabilities that real engineering projects require. We further introduce an artifact-centric evaluation methodology built on a unified suite of domain verifiers. The verifiers programmatically check whether final and intermediate artifacts are geometrically valid, physically feasible, and compliant with design rules. Beyond binary success, they also score how well optimized designs meet their specifications. Evaluation of seven frontier models reveals a substantial capability gap: the strongest model scores only 44.7/100, and just 3.6% of runs on tasks that require cross-software coordination succeed. EngiWorld provides a rigorous foundation for measuring progress toward agents that operate professional engineering software end to end.

Active multimodal agents use visual tools to acquire task-relevant evidence while reasoning. Although reinforcement learning samples multiple interaction trajectories per input, outcome-based objectives primarily use the group to estimate scalar advantages, leaving complementary visual discoveries underused. We introduce VISTA, which internalizes collective visual experience through on-policy distillation by turning observations from same-input rollouts into shared supervision. Collective visual experience distillation (CVED) organizes these observations with their interaction context and aligns them with individual decisions, while heterogeneity-aware policy improvement (HAPI) reinforces successful trajectories and provides experience-guided distillation for unsuccessful attempts. An experience-conditioned teacher evaluates the student's sampled response prefixes, allowing discoveries from one trajectory to guide learning in another without replacing the student's original history or generating new target trajectories. The trained agent retains its visual tools and acts using its own interaction history. VISTA achieves the strongest average performance among the evaluated active multimodal agents of comparable size and consistently outperforms same-backbone training baselines across fine-grained perception and general reasoning tasks, demonstrating the value of collective experience for active multimodal learning.

Motion planning often admits multiple feasible solutions, making multimodal generation valuable, particularly for flexible multi-robot coordination. Diffusion models naturally learn such trajectory distributions, yet incorporating coarse and partial trajectory priors without restricting generation remains challenging. Such priors indicate a desirable region of the solution space rather than a single solution, motivating conditioned generation that preserves multimodality. In this paper, we guide trajectory generation in the clean trajectory space and progressively incorporate trajectory priors with a timestep-dependent guidance strength. At each reverse diffusion step, the reconstructed clean trajectory provides a unified space for integrating planning costs and partial trajectory priors. Planning costs are incorporated through gradient-based refinement, while the partial prior is progressively injected at the corresponding noise levels with decreasing guidance strength. This guides generation toward the prior in early stages while gradually releasing the constraint to preserve the inherent multimodality of the diffusion model. The framework naturally extends to multi-robot planning by incorporating inter-robot collision costs. Experiments on single- and multi-robot planning tasks demonstrate controllable trajectory synthesis, diverse feasible solutions, and safe multi-agent coordination.

We study reinforcement learning (RL) methods for cooperative multi-agent Vision-Language-Action (VLA) models. This problem is challenging because VLAs are pretrained on large-scale single-agent data and therefore lack the fine-grained coordination skills required for inter-robot collaboration. Supervised fine-tuning (SFT) on multi-robot demonstrations partially bridges this gap, but its performance is bounded by the demonstration data and cannot improve from its own experience. We present a three-stage reinforced fine-tuning (RFT) pipeline for multi-agent VLAs. First, initialization-aware data collection sweeps over initial configurations and invokes human demonstrations only when the pretrained VLA repeatedly fails, yielding robustness to initialization shift with reduced human cost. Second, offline credit-filtered tuning assigns credit to individual agents and fine-tunes on per-agent trajectories with positive advantage rather than on entire joint rollouts. Third, we find existing online RL for VLAs are less effective for hard multi-agent tasks, which we attribute to noisy co-exploration and unstable updates. We instead use online latent-space fine tuning, which freeze the VLA and perform RL in its latent noise space. We evaluate our multi-agent VLA with both $π_0$ and $π_{0.5}$ backbones across 11 tasks in RoboTwin, RoboFactory and real-world manipulation with two Franka robots. Our multi-agent VLA improves the average success rate by $+23.1%$, $+16.4%$, and $+44%$ on RoboTwin, RoboFactory, and real-world tasks, respectively. Code available at https://anonymous.4open.science/r/mavla_rft-2BC0/.

As large language models (LLMs) advance, AI agents are increasingly deployed in open-world environments to tackle complex sequential tasks (e.g., document processing, cross-application collaboration), relying heavily on actions ranging from GUI operations to semantic APIs. However, three core challenges persist: the "scale dilemma" of massive tool ecosystems exceeding LLM context windows, the "non-stationarity" of tool quality due to updates or outages, and the "heterogeneity" of feedback formats (pixels, text, structured data) creating information silos. To address these, we propose AnyAct, a universal action layer that unifies available capabilities into a self-evolving action space, enabling agents to operate efficiently and reliably in large-scale, dynamic tool ecosystems. AnyAct's core design focuses on two objectives: constructing this action space via hierarchical progressive retrieval (filtering task-relevant actions) and test-time reliability evolution (pruning unreliable actions), and enabling reliability-aware action orchestration through a heterogeneous observation grounding module that unifies multi-modal feedback. Additionally, it defines a hybrid action space (primitive + semantic actions) and optimizes for a balance between task success rate and execution cost. Evaluations on LiveMCPBench and OSMCP (a new benchmark we developed for multi-granularity action collaboration) demonstrate state-of-the-art performance. AnyAct delivers substantial performance gains over baseline methods across various LLM base models on LiveMCPBench and improvements are particularly notable for models with constrained native capabilities. On OSMCP, it achieves 77.27% overall success with only 50 steps, which is half the steps required by most competitors.

Long-form video understanding requires multimodal agents to iteratively gather evidence over many reasoning steps. However, most existing agentic methods suffer from semantic thrashing: as append-only working memory grows, attention to key evidence collapses, and the agent loses access to what it has already found. First, we provide a structural argument showing that append-only memory can incorporate newly observed target evidence, but cannot remove accumulated noise or prevent ordered context growth without a rewrite operator. Second, motivated by this analysis, we propose VideoLoop, a multimodal agent with two coupled loops. The outer loop reasons over the video and the inner loop, after each step, retrieves artifacts from an unbounded filesystem of past observations and intermediate analysis, and rewrites a bounded working memory. Extensive experiments demonstrate the effectiveness of VideoLoop, which improves four popular LVLM backbones in a plug-and-play manner, with an average gain of 4.2% points over baseline on VideoMME (long). Further analysis of working memory suggests that VideoLoop mitigates semantic thrashing: on the hardest quarter of VideoMME (long) questions, a blind judge that reads only the agent's context answers 81.1% correctly, versus 60.9% for the append-only agent. With Gemini 3.1 Pro, VideoLoop reaches 88.3% on VideoMME (long), 88.8% on VideoMMMU, and 80.9% on LongVideoBench (long).

Computer-use agents have become increasingly capable of executing tasks on live desktops through natural-language instructions, based on trajectories of screenshots, actions, and reasoning. We discover that they can stealthily exhibit inertia, in which they repeat fruitless actions despite recognizing that these actions are ineffective. We hypothesize that inertia is reflected in the agent's internal state, i.e., the activation values of the agent's underlying model, and propose a protocol to measure the relationship between the two. Extensive analysis of high-dimensional activation states shows that inertia corresponds to an absorbing region of activation space, where activation values become stale across actions and even after attempts to steer them. We conjecture that drastically changing the agents' activations by re-initializing them is necessary to escape inertia. Specifically, we propose R$^3$ (Reset, Reroute, Restore), which temporarily resets the agent's context trajectory to escape the absorbing region and then restores the historical context to effectively complete the task. Our approach yields 17-55% lower measured inertia across models relative to unmodified agents. These results suggest that changing the context can interrupt recurrence more effectively than directly steering the resulting activations. Our code is available at https://anonymous.4open.science/r/vlm-agent-defense-D076