每天知道
你的领域
出了什么

Large language models increasingly operate over large collections of tools, functions, APIs, and specialized agents. As the candidate action space grows, a function-calling model must process more schemas, consume more prompt tokens, and distinguish among increasingly similar or irrelevant alternatives. We study a complementary systems strategy: reduce the candidate set before language-model inference while leaving the downstream model unchanged. We introduce AgentWeave, a deterministic pre-inference routing layer that constructs a bounded model-visible action space using eligibility, requirement, capability, and routing signals. We evaluate AgentWeave with a frozen BFCL-derived routing-pressure protocol using the public MadeAgents/Hammer2.1-1.5b model. On 48 fresh BFCL V4 multiple-function tasks, AgentWeave achieves 6/48 (12.5%) native BFCL successes, whereas all-tools, deterministic random top-8, and semantic top-8 baselines each achieve 0/48. The paired success difference is +12.5 percentage points with a 10,000-resample paired bootstrap 95% confidence interval of +4.17 to +22.92 points and exact McNemar p=0.03125. Relative to all-tools exposure, AgentWeave presents 70.18% fewer tools, uses 61.70% fewer input tokens, and exhibits 50.95% lower mean local-model latency. The result is deliberately narrow: this is a BFCL-derived routing-pressure study rather than an official full BFCL leaderboard score, and absolute task success remains low. The evidence nevertheless shows that candidate-space construction can materially affect a fixed model's function-calling behavior and motivates evaluating routing as a distinct stage before model reasoning.

Large language models (LLMs) are increasingly used for scientific decision support, yet reliable confidence estimation remains difficult in black-box settings. We study uncertainty estimation for hierarchical taxonomic reasoning generated by a black-box LLM in a long-tailed biodiversity monitoring pipeline. Using proxy features extracted by an open-source tool LLM, we train lightweight supervised estimators with hierarchy-aware supervision to predict rank-wise correctness. Across three tool LLMs, the supervised estimators consistently outperform a token-likelihood baseline for micro discrimination and selective prediction under a single global rejection threshold, improving micro AUROC from 0.57 to 0.75--0.80. The best results are achieved by a rank-specific multi-head design (H3), suggesting that accounting for hierarchical output structure is important when a unified abstention rule is required. Our code is publicly available at https://github.com/uoguelph-mlrg/hierarchy-aware-llm-uq

Large language models (LLMs) often produce fluent but incorrect answers with unwarranted confidence. A central limitation is that standard LLMs represent uncertainty through a single predictive distribution, conflating epistemic ignorance with genuine ambiguity. We introduce Credal Large Language Models (CLLMs): an ensemble of LoRA adapters induces a credal set whose lower and upper probabilities expose the spread of plausible predictive distributions rather than collapsing to a single softmax output. From this representation we derive two complementary commitment scores. Credal Token Commitment (CTC) is a token-space score that combines lower-bound support, credal width, and intersection entropy, computed without additional generation. Semantic Commitment Consistency (SCC) extends commitment to semantic space using sampled completions, with SCC-Gap measuring the mismatch between token-level and semantic-level support. We evaluate hallucination detection, calibration, selective prediction, and reasoning on Gemma-2-9B, Llama-3.1-8B, and Qwen2.5-7B across OpenBookQA, CoQA, TriviaQA, and ARC-Challenge. CLLM is the best method on QA accuracy at competitive expected calibration error, and CTC tracks the best hallucination AUROC within 1.5 pp on most settings without additional generation. On selective prediction at 80% coverage, CLLM with SCC reaches 99.0% accuracy on OpenBookQA, and on ARC-Challenge CLLM with Csem confidence achieves <= 0.6% ECE across the three backbones.

Misinformation that cites legitimate papers can be especially harmful when it distorts what those studies actually report. While existing automatic fact-checking systems based on large language models (LLMs) can assess whether a model assigns an Incorrect verdict and can gen- erate explanations for that decision, they typi- cally do not indicate whether the model follows the same reasoning path as human experts or arrives at the verdict through a different but still valid path. In this work, we introduce a graph- based framework (typed reasoning graph) for comparing human and LLM reasoning paths in scientific fact-checking. Building on prior work on fallacious reasoning in biomedical misinformation, MISSCIPLUS (Glockner et al., 2025), we model each explanation as a rea- soning graph that links the false claim to the relevant study context, study findings, fallacy- supporting premises, and fallacy labels. This representation enables one-to-one alignment of human and LLM reasoning at the level of fallacy-specific sub-graphs. For non-human- aligned LLM paths, we validate grounding in the cited study, relevance to the claim, and suf- ficiency for the verdict. Using 84 false claims from MISSCIPLUS, we evaluate GPT-5, Claude Opus 4.7, and Qwen3-32B across prompt and evidence settings. Results show distinct perfor- mance dimensions: Qwen3-32B has the lowest verdict failure rate, GPT-5 the highest human alignment, and Claude Opus 4.7 weak verdict prediction but often valid reasoning in success- ful cases

World models enable agents to reason about future outcomes and learn policies from their knowledge of state transition, but existing approaches primarily focus on reconstructing future observations or features, which introduces unnecessary complexity and limits their effectiveness for decision making. In this work, we propose a compatibility prediction Latent World Model (LWM) for robot navigation that predicts action-conditioned latent feature compatibility rather than reconstructing observations. Our key insight is that spatial proximity correlates with latent feature similarity, enabling action consequences to be evaluated directly in latent space. To support counterfactual training, our model leverages action sequences sampled across trajectories and learns to predict which sequences lead closer to the goal. Furthermore, we demonstrate how the learned world model can supervise policy learning from unlabeled video data and further improve policies through reinforcement learning entirely within the world model. This imagination-driven framework eliminates the need for action annotations and additional environment interaction. Extensive experiments on multiple real-world robot navigation datasets show that our approach significantly outperforms prior world model and imitation learning methods in prediction accuracy, policy learning, and real-world navigation performance. The code, pretrained models, and additional materials are available at https://wzm206.github.io/latent-world-model-nav.

Process supervision has improved mathematical reasoning, where intermediate steps are naturally expressed as chains of thought. In code generation, however, process supervision remains underexplored because there is no standard notion of a step. Supervision can target lines, reasoning traces, or program states, making it unclear what to label and optimize. We propose STEP-KTODER, a framework for code preference optimization that defines steps as module-level functions in decomposed multi-function programs and assigns binary correctness labels via automatically generated unit tests. Our method provides a code-specific instantiation of stepwise KTO, combining function-level process supervision with outcome-level feedback on the full program. We evaluate on HumanEval(+), MBPP(+), BigCodeBench, and LiveCodeBench, showing that STEP-KTODER improves over outcome-only KTO and DPO. Further analysis shows that execution-based labels are essential: LLM-as-a-judge annotations systematically over-predict function failures, corrupt positive step labels, and degrade downstream preference optimization. Code is available at: https://github.com/inechnech/STEP-KTODER.

A tool call can be perfectly valid yet still leave an autonomous agent unable to determine what to do next. For example, if an external effect commits but its response is lost, committed and uncommitted states may become indistinguishable to the agent even though they require different continuation actions. We study this gap between callability and operability: whether a tool interface exposes the action-relevant state and semantics needed for an agent to continue safely under operational uncertainty. We operationalize tool operability through Agent-First Tooling (AFT), a set of interface mechanisms spanning selective capability discovery, execution lifecycle and recovery, explicit external-effect semantics, machine-readable results, and postcondition verification. We introduce AFT-Bench, a controlled interface-intervention framework that holds the task, backend, initial state, injected failure, agent, and language model fixed while varying the interface exposed to the agent.

Large language models (LLMs) rely on tool calling as a fundamental agent capability, enabling them to invoke external systems and complete tasks beyond text generation. However, clean end-to-end (E2E) success cannot identify where a tool-use failure originates or how it propagates through a call. We introduce ToolRobustBench, a stage-wise diagnostic benchmark for tool-calling agents, where a tool-calling agent is an LLM system that selects a tool, supplies structured arguments, and interprets its returned feedback. ToolRobustBench aligns four perturbation families with the tool-use pipeline: tool-interface, user-intent, tool-output/observation, and runtime-environment perturbations. It attributes failures to tool selection, schema grounding, argument binding, tool-output/runtime-feedback handling, and E2E task success. Experiments on 15,456 single-family instances across 7 models, 16 sampled local tools, 4 perturbation families, and 14 subtypes show high but non-uniform clean performance and substantial robustness degradation, with tool-output/observation perturbation the dominant bottleneck. Mixed-family experiments reveal non-additive failure patterns that are not explained by isolated single-family results. Thus, ToolRobustBench provides a deterministic and cascade-aware benchmark for diagnosing robustness beyond clean tool-calling accuracy;

Radiologists generate diagnostic reports through iterative and selective revisiting of suspicious regions to refine their interpretations. Recent multimodal large language models (MLLMs) for radiology report generation (RRG) have shifted from text-only reasoning toward a ``Thinking-with-Images'' paradigm, incorporating visual evidence into the reasoning process. However, existing methods provide static visual evidence without a dynamic revisit mechanism during reasoning, neglecting how radiologists re-examine uncertain observations. To this end, we propose an Uncertainty-aware Revisit Reasoning MLLM (UR$^{2}$-MLLM) framework that dynamically revisits uncertain regions during reasoning for RRG. UR$^{2}$-MLLM is first equipped with uncertainty perception by training on an uncertainty-aware dataset. We then construct a multimodal reasoning trajectory dataset together with a detect-and-copy mechanism, which guides when and where to revisit. Finally, a visual grounding reward refines this behavior through reinforcement learning, aligning the revisited regions with corresponding anatomical structures. Experiments on MIMIC-CXR and IU-Xray show that UR$^{2}$-MLLM achieves state-of-the-art performance, highlighting the value of uncertainty-aware visual revisit reasoning for reliable and clinically aligned report generation.

Retrieval-augmented generation (RAG) enables LLMs to access external knowledge for answering knowledge-intensive questions. For complex multi-hop questions, multi-turn retrieval-augmented reasoning extends RAG into an iterative process that repeatedly searches for and integrates evidence across documents. However, existing reinforcement-learning (RL) approaches for agentic RAG are typically optimized with final-answer rewards, which provide sparse supervision and overlook whether the model actually retrieves the required evidence chain. We present \textsc{GTA-RAG}, a graph-trajectory-augmented RL framework for multi-turn retrieval-augmented reasoning. From an entity--document graph, we sample connected document paths, synthesize multi-hop QA trajectories, and validate them with the deployed retriever to obtain executable trajectory-level supervision. We then optimize the retrieval policy with Group Relative Policy Optimization (GRPO) and a trajectory-guided reward that encourages both accurate answers and acquisition of target evidence documents, followed by answer-reward training on natural QA instances. Experiments on three multi-hop and two simple QA benchmarks show that \method{} consistently outperforms RL-based RAG baselines with both Qwen2.5-3B and Qwen2.5-7B backbones, while substantially improving evidence-chain coverage. Our code is available at https://github.com/cjcj46262/GTA-RAG.

Current work on improving reliability in large language model (LLM)- generated answers has primarily leveraged Retrieval-Augmented Generation (RAG), knowledge-graph augmentation, and reinforcement learning. While these methods are adept at enhancing and measuring reliability through semantic similarity and faithfulness, they often struggle to distinguish semantic similarity from geographic validity. This is especially critical in natural hazard management domains where geographic granularity (i.e., town vs. city vs. state) is significant for decision-making, as responses valid in one municipality may not transfer to another. In such domains, a confidently wrong answer carries greater risk than abstaining. We present GeoRisk-RAG, a novel hierarchy-aware framework that addresses this geographic-validity gap through selective answering. This framework explicitly estimates geographic applicability using a Directed Acyclic Graph (DAG)-based distance for context retrieval before response generation. Experiments on a novel held-out wildfire-related question-answering (QA) dataset show that GeoRisk-RAG significantly reduces false confidence rates for location-dependent questions, lowering the rate to 0.009 compared with ~0.090 for standard semantic similarity and reranking baselines, while consistently achieving higher human preference alignment. This work provides a more comprehensive assessment of end-to-end RAG pipelines by integrating geographic validity and selective-answering behavior for safer decision-making in geospatial domains.

Pore-scale flow governs transport and permeability behaviour in porous media engineering applications, yet repeated lattice Boltzmann method (LBM) simulation across many geometries and design queries remains costly for repeated deployment. This study formulates transient pore-scale flow prediction as a geometry-conditioned query-time operator and introduces QSGS-Transient-7606, a benchmark of 7,606 two-dimensional porous structures each paired with 30 logarithmically sampled LBM states. The proposed continuous-time pore-scale flow surrogate model (CT-PoreFlow) integrates topology-aware geometry encoding, compressed spectral mixing, and log-time conditioning with a late-time flux-calibration objective. On unseen test geometries, CT-PoreFlow achieves a velocity relative L2 of 0.2248 and a terminal permeability error of 12.81%. Frozen morphology and computed tomography image audits confirm reasonable cross-geometry robustness without fine-tuning. The surrogate is then embedded in an inverse design workflow, screening 9,216 generative adversarial network and diffusion candidates across 18 property targets prior to LBM verification. Guided GAN sampling attains 98.11% through-connectivity and 72.28% conditional design success, exceeding diffusion-based generation. The framework unifies transient flow prediction, transport-aware screening, and LBM-verified inverse design for porous media.

We benchmark transport-based generative models as well as distillation-based few-step methods for the probabilistic forecasting of stochastic fluid flows, with a particular focus on performance under limited inference budgets. All methods are evaluated on a two-dimensional Kolmogorov flow with stochastic forcing. We measure one-step distributional accuracy against large simulated reference ensembles and assess whether the invariant measure is preserved during autoregressive rollouts via the enstrophy spectrum. On the stochastic task, flow matching achieves the most accurate one-step conditional distribution at high inference budgets, while the second-order exponential integrator DPM-2 is strongest at very low NFE. Few-step distillation methods are competitive with the multi-step methods and preserve the enstrophy spectrum particularly well. A deterministic control task, in which the forcing over the prediction interval is observed, separates aleatoric from epistemic uncertainty. Model performance does not translate between the two settings: the distilled models are competitive on the stochastic task but least accurate on the control task. While stochastic diffusion samplers such as DDPM better preserve the enstrophy spectrum during rollouts in the stochastic setting, deterministic samplers such as DDIM and DPM-2 show better spectral preservation in the deterministic setting.

Generative adversarial networks (GANs) can provide efficient image generation, while diffusion models offer high-quality image restoration but require iterative sampling. This paper presents a hybrid GAN-guided diffusion framework that uses a pretrained Wasserstein GAN with gradient penalty (WGAN-GP) as a feature prior for conditional diffusion-based image restoration. Intermediate features from the frozen WGAN-GP generator are incorporated into a diffusion U-Net through cross-attention and remain fixed during the DDIM sampling process. The framework is evaluated on two restoration tasks, Gaussian denoising and 2Xsuper-resolution, using CelebA face images. During development, several sources of instability were identified and addressed, including adversarial learning-rate imbalance, inappropriate diffusion initialization, excessive corruption, and insufficient parameter averaging. The resulting framework consistently improves the quality of both degraded and low-resolution images. In particular, it improves denoising performance by 4.40 dB in PSNR and super-resolution performance by 3.70 dB over their respective input baselines. These results demonstrate the potential of a frozen GAN feature prior to guide diffusion models toward stable and effective image restoration.

World-action models predict a future outcome and then infer an associated action. Although this factorization can improve representation learning and data efficiency, it is unclear whether it provides stronger control capability than direct behavior cloning when both are trained from the same observational demonstrations. We compare a direct behavior-cloning policy, an imitation-trained world-action policy, and a policy optimized with an action-conditioned world model. At the controller-class level, every world-action policy can be flattened into a direct stochastic policy with the same closed-loop trajectory distribution. At the population level, under realizability, exact optimization, common deployment information, and distribution-preserving deployment, direct behavior cloning and world-action imitation both recover the observational behavior policy. Thus, future prediction changes the learning factorization but not the unrestricted external policy class or ideal imitation target. Action-conditioned world-model learning differs by predicting outcomes under specified actions and comparing them through a control objective. We characterize the irreducible action-specific prediction error of future models that do not condition on the candidate action, identify conditions under which a world-action joint can recover an interventional forward model, and show that observational demonstrations do not identify action effects in general. Finally, we construct an environment family in which every observational learner has positive worst-case regret, whereas one informative intervention permits zero regret. The key distinction is therefore between predicting futures associated with observed behavior and predicting consequences of specified actions for policy optimization.

World models predict action-conditioned futures and serve as critical internal simulators for downstream planning and control. However, catastrophic prediction failures of world models could dangerously propagate through the control pipeline, as subsequent agent or model training and decision-making depend heavily on the continuous environment evolution forecasted by these world models. Existing evaluations overlook this systemic risk: by aggregating average errors over benign generations from general queries, they fail to stress-test the model against catastrophic collapses under rare or unobserved condition-action combinations. To bridge this gap, we formalize the natural-input failure discovery problem: under a finite query budget, finding environment-valid conditions and action prefixes that induce severe prediction risk, verifying whether these failures reproduce on fresh seeds, and testing their persistence under nearby valid edits. Discovering such critical failures is computationally challenging, as valid condition-action combinations explode exponentially, rendering exhaustive search or standard sampling infeasible given the high cost of noisy rollouts. To tackle this, we propose BasinLens, which exploits the underlying structure of valid inputs, where each coordinate possesses environment-defined semantic types and admissible domains, by pairing uncertainty-guided global search with typed local replacements. Across diverse benchmarks and world-model families, BasinLens exposes reproducible and locally persistent failure modes that conventional evaluations fail to reveal, showing that average-case benchmarks can mask important vulnerabilities in world-model-driven control.

Vision-language models can be personalized in a training-free manner by directly providing user profiles, preferences, or visual references at inference time, without updating model parameters. However, direct personalized prompting does not guarantee that the model will reliably exploit such evidence. The predictive distribution under the positive user profile often mixes two sources: personalized signals genuinely supported by the current profile, and the model's generic visual or linguistic priors. As a result, from the positive-profile response alone, it is difficult to determine whether a high-confidence answer is supported by the user profile or merely reflects the model's default preference. To address this problem, we propose a training-free calibrated residual decoding framework. Given the same image and question, we construct three evidence conditions: a positive profile , a counterfactual profile , and an empty profile . Our method keeps the prediction under as the anchored base, and explicitly estimates the marginal contribution of personalization from score differences across the three conditions. We further introduce normalized-entropy-based uncertainty calibration, allowing the strength of personalized enhancement to adapt to the reliability of the residual signal. Experiments on MMPB, YoLLaVA, and MyVLM show that the proposed method improves personalized multimodal understanding without fine-tuning, with consistent gains on identity-sensitive visual personalization tasks. Additional analysis shows that entropy calibration stabilizes residual decoding when the contrastive personalization signal is uncertain.

Visual autoregressive (VAR) models have emerged as a fast, high-quality alternative to diffusion for text-to-image generation, but like diffusion models they exhibit persistent compositional failures, producing images that violate the attribute bindings and spatial relations specified in the prompt. While a rich line of test-time alignment methods has developed for diffusion, no comparable approach exists for next-scale VAR generation, whose stateful, discrete, multi-resolution sampling process makes existing techniques inapplicable. We close this gap with VISTA (Visual Autoregressive Semantic Test-time Alignment), the first gradient-based test-time alignment framework for next-scale autoregressive image generation. Built on Infinity, VISTA intervenes directly in the generation process, optimizing intermediate representations through the frozen transformer to steer visual predictions toward compositional constraints, without modifying model parameters or requiring additional training. VISTA introduces the mechanisms needed to make such optimization stable across scales, together with an extensible objective space that any differentiable constraint on cross-attention can plug into. Across two benchmarks and two model scales, VISTA improves every targeted compositional category, raising the mean targeted score by nearly 20% on a 2B backbone and almost 6% on an 8B backbone, with the largest gains on spatial relations. Image quality is preserved: an independent preference model VISTA never optimizes scores its outputs nearly 20% higher. Notably, the 2B model with VISTA surpasses a backbone four times its size, indicating that a substantial part of the compositional gap between model scales is recoverable at test time.

Flow-matching language models refine all token positions in parallel and can trade sampling steps for latency, yet generation quality still degrades sharply with few sampling steps. We trace a source of this degradation to a train--inference mismatch in previous-prediction self-conditioning: during training, the self-conditioning input is computed from the current noisy state with no intervening solver step; during sampling, the solver folds the previous prediction into the latent before that same prediction reappears as the explicit self-conditioning input. This coupling, absent during training, creates redundancy that grows with step width. We show that the mismatch degrades both the self-conditioning input and the solver update, and derive a correction for each from the model's own structure. From the frozen projection weights we identify directions along which the self-conditioning input is redundant with the latent and dampen them; from the solver's integration structure we derive that a step-average prediction is needed and approximate it from prediction history, with scale set by offline trajectory statistics. The resulting sampler, Untied Self-Conditioning, requires no retraining and uses one evaluation per step. At 8 sampling steps on LangFlow, it reduces OpenWebText generative perplexity from $531$ to~$62$ ($8.6\times$); under an adapted Arena-Hard-Auto~v2 protocol, its outputs are preferred in $96%$ of pairwise comparisons. On ELF-B it reduces generative perplexity from $71$ to~$43$. Improvements hold from 8 to 256 sampling steps.

Subsampling is effective in tackling computational challenges for massive data with rare events. Overly aggressive subsampling may adversely affect estimation efficiency, and optimal subsampling is essential to mitigate the information loss. However, existing optimal subsampling probabilities depend on data scales, and some scaling transformations may result in inefficient subsamples. This problem is more significant when there are inactive features, because their influence on the subsampling probabilities can be arbitrarily magnified by inappropriate scaling transformations. We tackle this challenge and introduce a scale-invariant optimal subsampling function in the context of sparse models, where inactive features are commonly assumed. Instead of focusing on estimating model parameters, we define an optimal subsampling function to minimize the prediction error, using adaptive lasso to outline the estimation procedure and study its theoretical guarantee. We first introduce the adaptive lasso estimator for rare-events data and establish its oracle properties, thereby validating the use of subsampling. Then we derive a scale-invariant optimal subsampling function that minimizes the prediction error of the inverse probability weighted (IPW) adaptive lasso. Finally, we present an estimator based on the maximum sampled conditional likelihood (MSCL) to further improve the estimation efficiency. We conduct numerical experiments using both simulated and real-world data sets to demonstrate the performance of the proposed methods.

LLM-based agents are increasingly deployed in persistent social environments, where generated claims can be posted, replied to, remembered, and reused. We study human-directed stereotypes on Moltbook, an open agent-native social platform, asking how agents construct humans as a social category. For this human-target analysis, we introduce an annotation framework with four evaluative dimensions---morality, friendliness, competence, and autonomy---and a second-stage subtype scheme for descriptive other attributions. We find that competence dominates human-directed evaluations, while many other attributions describe humans as epistemic, cultural, or embodied subjects. We further examine how these human representations appear in human--agent narrative contexts and platform-level circulation. As an auxiliary comparison, we analyze agent-internal community feedback through behavioral host affinity. Rather than reproducing the stable insider--outsider rejection often observed in human online communities, Moltbook feedback patterns are better explained by exposure, author visibility, and content selection. These findings suggest that bias in agent societies should be studied not only as isolated model output, but also as a discourse process.

In domain-specific multimodal long documents, images and text jointly convey complex knowledge that cannot be fully captured by plain text alone. However, existing paradigms like DocVQA primarily focus on generating textual answers or localizing evidence regions, rather than outputting query-specific textual attribute values and corresponding images. To address this gap, we propose query-driven image-text joint extraction from long documents, requiring models to output query-requested textual attribute values and corresponding image bounding boxes. Based on challenges related to both user intent and document content, we designed a two-level taxonomy that operates at the query and instance levels. Further, we construct ITJoint, the first high-quality, manually annotated benchmark for this new task, comprising 2,455 pages of domain-specific documents with numerous non-decorative images, 316 queries, and 910 answer instances. Finally, we evaluate representative standalone Vision-Language Models from different providers and further design Q2IT, a multi-agent collaborative framework consisting of three progressively collaborating agents for evidence collection, page selection, and target-image localization. Using a joint evaluation approach that assesses both text extraction and image localization, our experiments show that standalone VLMs struggle with this task, while Q2IT significantly improves performance on ITJoint, although a substantial gap remains toward perfect results.

Large language model (LLM) agents operate in dynamic environments where knowledge continuously evolves. Existing memory systems typically treat external memory as a monotonically growing repository, inevitably leading to retrieval degradation and increasing computational costs over time. We argue that the core challenge is not retrieval alone, but managing the knowledge lifecycle: deciding what to externalize, update, or ultimately internalize. Inspired by Complementary Learning Systems (CLS) theory in neuroscience, we propose Dual-Layer Agentic Memory, a framework that shifts memory management to the write phase through cost-aware epistemic routing and periodic parametric consolidation. Incoming information is categorized as non-write, write-new, or write-update, and routed through a small-to-large model cascade that minimizes routing overhead while filtering redundant memories. A subsequent write-back phase selectively consolidates high-value external memories into model parameters via supervised fine-tuning. Experiments demonstrate the dual efficiency of our approach: a 1.7B/8B cascade prunes up to 68% of redundant external memory while escalating fewer than 50% of inputs, yet retains over 98% of the downstream QA Exact Match (EM) achieved by an exhaustive retention baseline. We further show that periodic consolidation successfully internalizes external knowledge, allowing the router to adaptively suppress redundant writes as the model's epistemic boundaries evolve. Overall, our framework presents a unified paradigm for agent memory: selective externalization followed by selective internalization. Code and dataset will be released upon acceptance.

Explainable AI (XAI) research has produced a plethora of explanation techniques, yet user studies repeatedly show that available explanations are not effective in practice. We argue that, given the siloed nature of conventional XAI, users are struggling to select the appropriate XAI technique. Viewing XAI through a philosophical lens, we offer a formalization of what we call the selection problem: the systematic failure of XAI interfaces to bridge the gap between a user's natural-language uncertainty and the explanation technique that resolves it. Following a logical premise-conclusion format, we show that conventional interfaces require users to translate their uncertainty into a technique selection, a challenging prerequisite to meet. We also propose a structural solution: a multi-agent LLM orchestration tool that translates the user's query to the proper XAI explanation technique. We provide an example of how this structural solution could be instantiated to address the selection problem.

Multimodal Large Language Models (MLLMs) capable of thinking with images often rely on external tools for fine-grained perception. However, this reliance introduces significant inference latency and fails to effectively resolve the spatial-structural gap-a fundamental challenge in text-dense and structurally relational visuals (e.g., charts and visual tables) where strict relative spatial arrangements bind textual elements. Without external tools, standard MLLMs struggle with such fine-grained visual reasoning tasks. To address these issues, we propose Think with Structured Grounding (TwSG), a novel fine-grained image perception framework designed to internalize complex images's tool-use capabilities within the model. TwSG distills the benefits of multi-step reasoning and micro-cropping into a single efficient forward pass during inference. Specifically, we use an MLLM to identify key regions guided by ground-truth answers, and then prompt a teacher model to generate high-quality visual question-answering (VQA) data. These fine-grained, region-based supervisory signals are subsequently distilled back into the full-image representation. Our training pipeline consists of two stages: (1) a cold-start supervised fine-tuning (SFT) phase using multi-turn data with focused area descriptions to foster complex reasoning and error recovery; and (2) a reinforcement fine-tuning (RFT) phase driven by a novel process reward mechanism, TL-GRPO, which encourages strategic reasoning. Extensive experiments across various MLLM architectures demonstrate that TwSG reduces inference latency while substantially improving accuracy and robustness, endowing models with native fine-grained region description and flexible reasoning capabilities.

Software-engineering agents solve repository-level tasks through long, stochastic tool-use trajectories, and repeated attempts often find fixes missed by one run. Test-time scaling is difficult because patches lack canonical answer forms, while sibling actions from a shared prefix are correlated. We study whether native MoE router traces can guide steering and selection without an external judge or selection-time test execution. Our analysis shows that routing provides a robust behavioral role signal; token-granular readouts and decision-matched comparison sets turn it into effective control. We therefore introduce Risa (Routing-Informed Steering and Arbitration): within trajectories, routing encourages diverse exploration and controlled convergence during patch commitment; across separately sampled trajectories, agreement at informative patch positions selects a final candidate. We evaluate on SWE-bench Verified using open-weight sparse MoE agents across scales and reasoning-effort settings. Risa's routing arbitration raises the macro-average resolved rate from 44.9% under uniform sampling to 48.2% on the gpt-oss family, matching text consensus without answer-string matching, and it transfers to Qwen3.6, where it improves on uniform choice and matches text consensus on the full 500-task benchmark.

Agent benchmarks often evaluate only final answers even when agents run on stateful runtimes. We argue this under-specifies what is being evaluated: the proper unit is a declared model-plus-runtime configuration whose failures can occur in evidence acquisition, runtime routing, safety boundaries, or repeated execution. We present ClawProBench, a trace-aware benchmark for runtime-native agent evaluation instantiated on OpenClaw, a live agent runtime with workspace tools and native surfaces for browsing, memory, messaging, scheduling, skills, and subagents. ClawProBench defines two tracks: a 102-scenario full profile with live workspace and native-runtime routing tasks, and a frozen 68-scenario holdout with closed-world JSON output contracts for robust ranking. Trials are scored from execution traces via a safety-gated formula combining correctness, process quality, and efficiency, preserving failure evidence for audit. Our anonymous artifact includes benchmark definitions, scoring code, manifests and sanitized traces. We evaluate 68 configurations on the full profile and 37 on holdout. The top safety-gated average trace score is 0.7671. Native-runtime tasks underperform workspace-live tasks (0.5238 vs. 0.6415). On holdout, pass@k-any outperforms strict three-trial pass (0.6638 vs. 0.2890), while full-profile and holdout rankings show weak alignment (Spearman 0.1300). Rankings based purely on correctness differ substantially from process-aware, safety-gated and strict-pass views. Final-answer leaderboards may hide native-surface weaknesses, one-off successes and trace-local agent failure modes.

Long-term memory is crucial for personalized responses and long-horizon agent interactions. Existing methods often rely on LLMs to compress or rewrite dialogue histories and use the transformed memories as retrieval evidence. Despite the progress in organizing fragmented contexts, two major drawbacks persist: (1) information loss from compression, which discards fine-grained but later useful details, and (2) semantic drift from rewriting, which erodes the original tone and situated context. In this work, we propose a novel Human-profile Enhanced Retrieval Optimization framework for long-term agent memory (HERO). Specifically, HERO converts the dialogue history into a traceable heterogeneous memory graph that preserves raw dialogue text as evidence for reasoning, thereby mitigating information loss. For retrieval, HERO extracts initial anchors from the current query and incorporates human profiles via an iterative graph traversal; these anchors and profiles provide guidance signals that adaptively activate the most informative regions of the graph. Experiments on two benchmark datasets show that HERO outperforms strong baselines on both factual and personalized reasoning, while providing more faithful access to raw dialogue evidence.

Autonomous computer-use agents are increasingly applied to long-horizon tasks requiring coordinated application calls, persistent state tracking, and verifier-sensitive writes, yet they remain prone to procedural failures: misreading application state, tool semantics, or task progress. Procedural memory promises more consistent decisions and less redundant exploration, but constructing high-quality memory without model training remains challenging. We introduce CONTRAMEM, a source-flexible, training-free framework for self-evolving procedural memory that treats same-task outcome variation as supervision: differences in correctness, efficiency, recovery, and failure modes expose outcome-relevant procedural distinctions, distilled into a compact bank of app-level Function Cards and task-level Skill Cards that evolves through localized curation rather than append-only accumulation or whole-bank rewriting. On held-out GAIA2/ARE computer-use tasks, CONTRAMEM more than doubles the success rate across the three source-model targets (26.2% to 55.3%), with consistent per-model gains (GPT-5.5: 27.5 to 61.0; Claude Sonnet 4.6: 28.0 to 52.5; DeepSeek V4 Pro: 23.0 to 52.5). The same bank transfers unchanged to the unseen Qwen3.7 Plus (18.5 to 35.5), indicating transferable procedural knowledge rather than model-specific behavior. The same construction carries over unchanged to AppWorld, beating both no memory and its own single-source self-memory variant for all three mid-tier agents on both public test splits. Under a matched trajectory budget, heterogeneous multi-model trajectories yield stronger memory than self- or same-model multi-rollout memory: the margin comes from contrastive behavioral diversity, not stronger source agents or more sampling.

Long-horizon GUI agents can retain complete action histories as compact text, but only a few historical screenshots fit in active context. We formulate this as budgeted fidelity restoration: every event remains summarized, while a fixed budget $B$ determines which events regain their archived screenshots. Recent-$B$ assigns all visual slots to the latest events. CausalCache instead scores the complete history and swaps in an older event only when its predicted utility exceeds that of a recent event. A history-gated key/value adapter modifies only restored history-image tokens and is exactly bypassed when no history image is active, preserving current-screen processing. The adapter and selector are trained with matched-budget interventions on desktop trajectories and evaluated zero-shot on mobile. On OSWorld-Verified, activating historical screenshots improves success by about $13$ percentage points over summary-only memory. Under the official $15$-step limit, CausalCache and Recent-$4$ are statistically indistinguishable; in a $30$-step diagnostic, CausalCache achieves $46.7%$ success versus $42.4%$ ($+4.3$ points). Zero-shot on $117$ MobileWorld tasks, CausalCache improves over Recent-$4$ from $30.2%$ to $36.8%$. The gain is concentrated on a pre-defined cross-app memory-candidate split ($30.6%$ vs. $19.4%$, $+11.2$ points), while single-app controls show no detectable difference ($43.6%$ vs. $42.4%$). These results show that selecting which past events regain pixels is more effective than spending a fixed visual budget entirely on recency.