每天知道
你的领域
出了什么

Background. Large language models and AI agents are increasingly used to support biomedical research, but native model outputs may omit key analytical steps, misuse methods, or overstate conclusions. We evaluated whether autonomous access to a medical research skill package was associated with higher-quality AI-generated transcriptomic research-analysis outputs compared with native AI without skills. Methods. We conducted an exploratory multi-model human evaluation using a non-small cell lung cancer immunotherapy biomarker task. Six model backbones were tested. The evaluation included 21 anonymized outputs: 9 native-AI outputs and 12 skill-augmented outputs generated through an AI agent implementation represented by OpenClaw. Four non-expert biomedical reviewers and two blinded experts evaluated each output, with two ratings from each reviewer type. The primary outcome was expert-rated overall quality. Results. Skill-augmented outputs showed directionally higher expert overall quality than native-AI outputs (mean 5.50 vs 5.11; difference=0.39; bootstrap 95% CI, -0.04 to 0.90; Welch p=0.156). Non-expert reviewer quality showed the same direction (mean 4.72 vs 4.47; difference=0.26; bootstrap 95% CI, -0.25 to 0.80; Welch p=0.373). Expert agreement was limited (single-rating ICC=-0.15), and model-specific effects were descriptive and heterogeneous. Conclusions. Autonomous skill access showed a directional quality signal in this exploratory sample, but the signal was smaller than expert-rating noise and should not be interpreted as confirmatory evidence. The findings primarily motivate larger evaluations of skill-augmented AI agents with stronger reliability controls, platform replication, and biological-validity assessment.

Scientific discovery workflows usually contain and rely heavily on lab notes, where researchers record observations, interpret uncertain results, and plan follow-up experiments. Such informative lab notes preserve evolving scientific reasoning and author uncertainty, rather than polished final results exhibited in publications, providing a valuable opportunity for AI to engage in scientific exploration at a more comprehensive and deeper level. However, most prior work on scientific text focuses on papers, protocols, or structured databases, leaving informal laboratory notes underexplored as inputs to AI agents for science. This gap matters because lab notes often intermingle validated observations, tentative judgments, and possible experimental next steps within the same passage. If these signals are conflated, an AI agent may mistake uncertain scientific judgments for confirmed conclusions or executable actions. To this end, we present Notes2Skills, a two-stage framework for turning lab notebooks into verifiable skills for scientific AI agents while preserving the author's certainty. Across seven conditions and three wet-lab sessions, Notes2Skills is the only configuration that neither mistakes uncertain notes for firm instructions nor discards firm ones. We show that certainty preservation is the missing piece between lab notebooks and reliable agent skills, opening a path toward safer AI co-scientist systems.

Trusted monitoring is a cornerstone of AI control. However, as frontier models grow more capable, the increasing capabilities gap between trusted and untrusted models may render trusted models unreliable monitors. We introduce bootstrapped monitoring, a protocol that addresses this by inserting a stronger, intermediate untrusted model with transparent chain-of-thought reasoning into the oversight chain. The untrusted monitor ($U_m$) evaluates the agent's actions, while a weaker trusted model ($T$) oversees $U_m$'s reasoning to detect collusion. We evaluate bootstrapped monitoring on multi-turn software engineering tasks (BashArena) across multiple agents and monitors. Bootstrapped monitoring substantially improves catch rates over trusted-only monitoring, even when the untrusted monitor actively colludes with the agent, provided we have access to its raw chain-of-thought. Our results suggest that bootstrapped monitoring can extend the useful lifetime of trusted models in control as AI capabilities advance.

Agent skills let LLM agents reuse instructions, resources, tools, and workflows, but they also create a new place for malicious behavior to hide. A skill may look benign in its documentation or code while becoming harmful only when it is invoked with particular user requests, local assets, persistent state, or multi-step tool interactions. This makes purely static vetting brittle. We present Runtime Skill Audit (RSA), a dynamic analysis method that audits skills by asking what the skill-mediated agent actually does under targeted runtime conditions. Instead of testing every skill with the same generic tasks, RSA profiles risk-relevant interfaces, prepares the execution context needed to exercise them, and assigns security labels from the resulting trace evidence. We instantiate RSA on OpenClaw and evaluate it on 100 skills against representative static baselines. RSA achieves 90.0% accuracy with an 88.0% true positive rate and an 8.0% false positive rate, improving accuracy by 13.0 percentage points over the best static baseline. Under self-evolving attacks, static detectors collapse after one or two rounds, while RSA continues to detect 19--20 out of 20 malicious skills across rounds.

Custom AI agents areagents that live inside their own application, talk to their own data and tools, enforce their own security boundaries, and carry their own brand and audit trail. What separates them from the general-purpose tier is fit, not capability: each is built for one job, by the engineer who will maintain it. No published practice sets out how to build one end to end. The pieces are everywhere (function-calling APIs, the Model Context Protocol, code agents to pair with), but the practice that chains them lives in podcasts, blogs, and leaked system prompts. This paper writes that practice down as a methodology, Agents All the Way Down: two preconditions crossed once and kept, then three practices repeated for the agent's life. The preconditions are (P1) Substrate, the LLM as a software component, framed as tools, then system, then messages under prompt-caching; and (P2) Building blocks: function calling, MCP, CLI orchestration, the liteshell pattern, the agent loop, skills, characters, hooks, and scaffolding. The practices are (P3) prototype with a general-purpose agent; (P4) harvest, fold, and ship the result as a CLI, the Turtle pattern; and (P5) agent-tests-agent, in which a general-purpose agent drives it through behavioural scenarios, a complement to classical testing, not a replacement. The working loop is P3 to P4 to P5 and back, and one corollary falls out for free: multi-agent orchestration is just CLI composition. The methodology is framework-free by construction. It was distilled from the AAC, a custom agent for the open-source LAMB platform, built in about ten days by one developer with an AI pair-programmer and in production . We present it as a transferable practice, independent of any language or framework.

This paper explores the value of agentic AI tools for cybersecurity purposes. We evaluate the efficacy of a general-purpose GenAI Large Language Model- (GenAI-) based agent when powered by three different Ollama-hosted general-purpose open source models. We assess each agent's performance using precision, recall, false positive count, and a calculated composite score based upon the interplay of the captured metrics, against the baseline performance of an existing, vetted Static Application Security Testing (SAST) tool, Bandit. Our findings refute the notion that a modern open-source GenAI LLM-based agent is currently suitable for the specialized task of SAST scanning under realistic conditions.

Software engineering tools increasingly rely on LLM based agents to localize files to change to resolve a software issue. Most AI agents explore repositories linearly, that is, visiting one directory or file per step. We postulate that this is a structural mismatch for changes that span several subsystems. We compare linear sequential exploration against non-linear, domain-scoped parallel agentic exploration. Using SWE Bench Pro as initial benchmark, we focus on ansible as an exemplar. We construct an approach for persistent-session evaluation of GitHub issues anchored at a single base commit. We compare our non-linear domain-agent file traversal system against a base LLM without direct repository access, a single agent Recursive Language Model (RLM) baseline with a persistent Python REPL and an external CLI baseline using Codex 5.5 High. Domain scoped parallel agent spawning with a small Haiku-class model achieves the highest micro F1 among Haiku class models by a large margin. Domain-agents is the second highest behind only the much larger Codex 5.5 High on our own expanded benchmark including over more recent PRs from 2025 and 2026. On the original, curated, 2020 SWE-bench Pro benchmark, a larger Sonnet plain LLM baseline attains higher micro F1 by predicting few files, leading to higher precision, but at significantly lower all gold recall. We also present three additional findings. First, documentation evolution is a latent dependency unresolved by any approach. Second, naive file system access can degrade localization driven by test-file over prediction. Lastly, forced multi-agent consultation does not measurably help and raises token cost substantially.

High-precision robotic manipulation requires fine-grained spatial reasoning that is often difficult to achieve with RGB-only policies due to depth ambiguity and perspective scale issues. Policies that leverage 3D information directly, such as those based on point clouds, offer a stronger geometric prior over purely image-based ones, yet their performance remains highly task-dependent. We hypothesize that this discrepancy may be due to the spectral bias of neural networks towards learning low frequency functions, which especially affects architectures conditioned on slow-moving Cartesian features. We thus propose to map point clouds from Cartesian space into high-dimensional Fourier space, effectively equipping the point cloud encoder with direct access to high-frequency features. We experimentally validate the use of Fourier features on challenging manipulation tasks from the RoboCasa and ManiSkill3 benchmarks and on a real robot setup. Despite their simplicity, we find that Fourier features provide significant benefits across diverse encoder architectures and benchmarks and are robust across hyperparameters. Our results indicate that Fourier features let policies leverage geometric details more effectively than Cartesian features, showing their potential as a general-purpose tool for point cloud-based imitation learning. We provide source code and videos on our project page: https://fourier-il.github.io/fourier-il

Stance detection requires identifying an author's position toward a target, often from short-form texts where stance is implicit, indirect, or rhetorically framed. Although large language models (LLMs) achieve strong performance on this task, single-pass prompting can be brittle when multiple interpretations are plausible. Existing aggregation strategies, such as majority voting or self-consistency, improve robustness by combining labels, but they discard the intermediate reasoning needed to resolve conflicting interpretations. We introduce a multi-agent reasoning framework with adaptive worker allocation for stance detection that shifts aggregation from label-level voting to reasoning-level synthesis. The framework employs a Manager-Worker architecture in which a Manager adaptively allocates a variable number of Worker agents based on input complexity. Each Worker analyzes the input from a distinct perspective and produces a reasoning-only explanation without emitting a stance label; the Manager then synthesizes these explanations to produce the final prediction. We evaluate the proposed framework on SemEval-2016, P-Stance, and COVID-19 Stance using Llama, Mistral, and Gemini. Results show that the framework yields the largest gains on implicit and context-dependent stance cases, achieving 86.07 Macro-F1 on COVID-19 and 82.90 on SemEval-2016, while remaining competitive on more explicit stance datasets such as P-Stance. These findings suggest that adaptive reasoning-level aggregation is most beneficial when stance cannot be reliably inferred from surface cues alone.

Forecasting real-world events requires language-model agents to reason under uncertainty from incomplete, time-bounded information. Yet evaluating whether agents genuinely forecast requires more than final-answer accuracy: a model may be correct by recalling memorized training facts, citing fabricated evidence, or producing an unsupported causal story. We present WorldReasoner, an evaluation framework for temporally valid event forecasting. Each task gives an agent a resolved forecasting question, a simulated forecast date, and access only to evidence available before that date; after resolution, the framework scores the submitted probability, cited evidence, and optional causal event graph. WorldReasoner reports three complementary axes: outcome quality against resolved answers, evidence quality over cited sources, and reasoning quality against post-resolution hindsight graphs. The benchmark is built by an agentic construction pipeline that generates forecasting questions, collects time-stamped evidence, and builds hindsight reference graphs at scale, yielding 345 resolved tasks derived from 14,141 articles with graphs covering 8,087 extracted events. Across six controlled agent settings, temporally valid retrieval is the strongest driver of outcome accuracy; causal graph construction improves key-event recovery; and correct graph-enabled forecasts are more strongly grounded in key events and relevant sources, yet agents still struggle to convert grounded evidence into calibrated probabilities.

Enterprise security was built to govern data boundaries: the protected surface was data at rest and in transit, and the controls — access control, data-loss prevention, perimeter inspection — governed crossings of that boundary. Production AI agents dissolve this assumption. An agent reads context, calls tools, invokes connectors, and modifies systems of record on an enterprise's behalf, so risk moves inside the workflow, into sequences of individually-permitted actions that may transform a business process no one authorized. Existing policy engines do not extend to this regime: they evaluate request-time decisions against atomic principals, where agentic systems require stateful evaluation against composite principals whose authority attenuates through delegation chains. We present a reference architecture for the runtime governance of production agents, built from four composable primitives: a five-plane decomposition (a reasoning plane that adjudicates intent, and four enforcement planes — network, identity, endpoint, data — that realize the decision), stop-anywhere mediation, composite principals with capability attenuation, and audit as a structured evidence substrate. We define a taxonomy of six interruption primitives that generalize allow and deny, state and argue for four correctness invariants, and demonstrate the foreclosure of seven production-agent threats across five concrete workflows. A reference implementation of the policy-engine core supplies measured evidence: attenuation correctness and evidence reconstructability hold on every trial, adjudication runs in single-digit microseconds, and the audit substrate's tamper-evidence behaves exactly as designed. We are explicit about scope: the architecture governs delegated action, not model behavior, and a full-system evaluation against a live agent benchmark is the invited next step.

To make clinically grounded decisions, medical AI agents are expected to go beyond simple recognition and be capable of tool retrieval, evidence acquisition, and integration. Existing benchmarks largely evaluate isolated perception or single-turn question answering, and therefore provide limited visibility into failures of planning, tool recruitment, and rollout reliability. We introduce MedCTA, a benchmark for evaluating medical tool agents on clinician-validated, step-implicit tasks grounded in realistic multimodal clinical inputs, including radiology images, pathology slides, and reports. MedCTA comprises 107 real-world clinical tasks with clinician-verified executable trajectories over 5 deployed tools, and supports process-aware evaluation of tool selection, argument validity, execution stability, trajectory fidelity, and outcome quality. We benchmark 18 open- and closed-source multimodal models and find that even frontier systems remain brittle in multi-step clinical tool use: autonomous rollouts are dominated by protocol failures, premature stopping, and incorrect tool recruitment, while gold-standard tool routing yields large but still incomplete gains. These results show that strong backbone perception does not translate into reliable agentic behavior in clinical settings. MedCTA provides a rigorous testbed for auditing, diagnosing, and advancing trustworthy medical AI agents. The dataset and evaluation suite are available at https://ivul-kaust.github.io/MedCTA/

Financial and tabular question answering requires more than fluent reasoning: answers must be grounded in the exact facts, formulas, units, signs, and scales that support them. A single misread cell or incorrect operation can silently produce a plausible but wrong result. We introduce \textsc{MOCA-Agent}, a market-of-claims code agent that replaces free-form multi-agent debate with claim-level verification. The system decomposes each question into typed atomic claims, asks specialist trader agents to buy or sell those claims, clears their orders into confidence-weighted accept/reject decisions, and synthesizes an executable Python program from market-supported evidence. A code-aware verifier then checks the program for execution, structural consistency, and common financial reasoning errors, with at most one market-aware repair round. Across ten public benchmarks spanning financial numerical reasoning, general tabular reasoning, ESG question answering, and multimodal chart reasoning, \textsc{MOCA-Agent} achieves strong performance using a fixed Qwen3.6-27B backbone, including $78.3%$ on FinQA, $76.0%$ on FinanceMath, $71.2%$ on MultiHiertt, $86.9%$ on ESGenius, and $85.6%$ average on FinChart-Bench. These results show that aggregating evidence at the level of atomic claims, rather than whole answers, improves robustness in high-stakes numerical reasoning.\footnote{The code and data are available: https://github.com/UBC-NLP/MoCA-Agent.

Agent Skills augment large language model (LLM) agents with procedural knowledge at inference time, but current benchmarks rarely distinguish what a Skill says from how it is organized. We study this distinction through Progressive Disclosure, where a concise root file points agents to supporting resources on demand, and compare it with a normalized flat baseline. We present SkillJuror, a framework for evaluating Skill writing paradigms through semantically controlled variants, matched multi-trial evaluations, and trajectory evidence while holding task knowledge fixed. In an 82-task SkillsBench study, Progressive Disclosure changes runtime behavior before aggregate outcomes: distinct Skill resources touched per trajectory rise from 1.18 to 3.85, and effective uptake events rise from 1.33 to 3.92. It also yields 17 additional verifier-passing trials out of 410 matched trials (+4.1%) over the normalized flat baseline. The benefit is task-dependent. Progressive Disclosure helps when supporting resources guide implementation, checking, or repair, but is weaker when success hinges on exact output conventions, numerical thresholds, or long artifact-generation pipelines. These results show that Skill organization is not mere presentation: it can change how agents search and apply procedural knowledge, while outcome gains depend on whether the exposed resources are actionable for the task. Code is available at https://github.com/zhiyuchen-ai/skill-juror.

End-to-end task-success is the dominant way to evaluate LLM agents, but one aggregate number tells you that an agent regressed, not where. We present layer-isolated evaluation: a deployed ordering agent is decomposed into a fixed taxonomy of layers (ontology, intent, routing, decomposition, escalation, safety, memory, and cross-cutting envelope/defense), each exercised by its own assertion slice in a deterministic, no-LLM "pure" mode. The pure suite (238 cases across 23 slices; 225 run in 2.39 s, ~10 ms/case) runs in CI on every change against a locked per-slice baseline. We validate by controlled regression injection, degrading one layer at a time across seven non-safety layers. The effect we did not design in is masking: the aggregate pass-rate barely moves (-1.7 to -5.9 pp for six local regressions), while the matching slice craters (-25 to -91 pp). A layer's slice reacting to its own fault is partly by construction; the measured results are (i) the aggregate masking and (ii) that damage stays off the other slices: the injected layer's slice is the single worst-hit in 5 of 7 cases and top-3 in 7 of 7 (mean rank 1.29 of 19). Localization replicates on a second, structurally different tenant (Starbucks SG): all seven matching slices crater, so it is not a single-catalog artifact. We position it as a concrete, deterministic instantiation of the component-level evaluation EDDOps prescribes but leaves unimplemented, with CheckList as ancestor and as the deterministic mirror image of whole-workflow stochastic mutation testing. Our contributions: (a) a fully decomposed, sub-second, no-LLM per-layer harness for a production agent, (b) a coverage-honesty test-adequacy criterion that refuses to score an unexercised layer, and (c) the regression-injection demonstration that per-slice baseline-locked gates localize regressions an aggregate metric masks.

We propose a multi-agent collaborative framework built upon a lightweight Multimodal Large Language Model (MLLM), specifically designed for social intelligence reasoning. A key feature of our approach is that both the training and inference phases are augmented via knowledge distillation. Within this architecture, multi-modal data pertinent to social intelligence is precisely localized. Furthermore, relevant long-tail events are identified, extracted, and rendered as formatted, explicit text. This formatting strategy prevents critical long-tail information from being overshadowed by head events and environmental noise during the tokenization process. Specifically, we integrate Test-Time Adaptation (TTA) across the entire reasoning pipeline, encompassing the extraction and representation of long-tail events, Chain-of-Thought (CoT) prompting, and self-reflection. This TTA mechanism is also distillation-enhanced, utilizing Low-Rank Adaptation (LoRA) to fine-tune the foundation model exclusively for instance-level reasoning. Extensive evaluations against various open-source and proprietary AI models across multiple benchmarks demonstrate the effectiveness of the proposed framework. With around 30% of training data from IntentTrain, we achieve state-of-the-art results. Codes are available at https://github.com/eeee-sys/MODF-SIR, demo is available at https://huggingface.co/spaces/Harry-1234/MODF-SIR, LoRA is available at https://huggingface.co/Harry-1234/MODF-SIR and the dataset for training router is available at https://huggingface.co/datasets/Harry-1234/IntentRouterTrain.

Large language model (LLM) agents struggle with long-horizon tasks due to their inherent statelessness, requiring all task-relevant information to be encoded in growing input contexts. The resulting degraded reasoning quality, increased inference cost, and higher latency necessitate efficient working memory mechanisms. However, existing approaches either rely on lossy compression or similarity-based retrieval, which often fail to capture temporal structure and causal dependencies required for multi-step agentic tasks. In this work, we present HORMA, a Hierarchical Organize-and-Retrieve Memory Agent that organizes experience into a file-system-like hierarchical structure, where summarized entities are linked to the corresponding raw trajectories, enabling efficient access without losing detailed information. HORMA decomposes working memory into two stages: structured memory construction and navigation-based retrieval. The construction module iteratively refines how experiences are structured by distinguishing between failures caused by missing information and those caused by misleading or overloaded context. The navigation module retrieves task-relevant context by traversing the hierarchy using a lightweight agent trained with reinforcement learning to select minimal yet sufficient context, thereby reducing latency along the critical execution path. Across ALFWorld, LoCoMo, and LongMemEval, HORMA improves task performance under constrained context budgets while requiring at most 22.17% of the baseline token usage in long conversation tasks. Compared to existing methods, it consistently achieves better efficiency-performance trade-offs and generalizes effectively to unseen tasks.

Unmanned aerial vehicles (UAVs) are increasingly used in inspection, search and rescue, environmental monitoring, and emergency response. However, most UAV applications still rely on pre-defined command sequences or task-specific pipelines, where developers manually connect perception, planning, flight control, simulation, logging, and safety modules. This limits the flexibility, reproducibility, and extensibility of autonomous aerial systems. This paper presents AerialClaw, an open-source software framework that enables UAVs to operate as decision-making aerial agents rather than merely command-following platforms. Given a natural-language mission, AerialClaw allows an LLM-based agent to understand the task, maintain context, invoke executable aerial skills, observe perception and runtime feedback, and iteratively update its decisions in a closed loop. The framework adopts a modular brain-skill-runtime architecture, combining hard skills for atomic UAV operations, Markdown-based soft skills for reusable task strategies, document-driven agent state and capability boundaries, memory-driven reflection, safety-oriented runtime validation, and platform-agnostic execution adapters. AerialClaw supports lightweight mock execution, PX4 SITL with Gazebo, and AirSim-based simulation, together with a web console, pluggable model backends, example missions, simulation assets, and staged deployment scripts. By combining standardized aerial skills, document-driven agent state, memory, and closed-loop LLM decision-making, AerialClaw provides a reproducible and extensible open-source framework for building UAV systems that can interpret missions, make decisions, execute skills, and adapt their behavior from feedback.

We propose Ambient Diffusion Policy, a simple and principled method for imitation learning from suboptimal data in robotics. High-quality, task-specific robot data is expensive and time-consuming to collect, while suboptimal datasets with lower-quality or out-of-distribution demonstrations are abundant. Existing methods that co-train on both data sources in robotics often fail to separate the meaningful and the harmful features in the suboptimal samples. In contrast, our method extracts only the useful features by introducing a new axis to co-training in robotics: noise-dependent data usage. Ambient Diffusion Policy restricts the contribution of suboptimal data during training to only the high and low diffusion times. To rigorously justify our approach, we first observe that robot action data exhibits a spectral power law. This induces two important properties on the optimal Diffusion Policy that we exploit: a global-to-local hierarchy and locality. We theoretically formalize this discussion using a simplified model. Our experiments validate Ambient Diffusion Policy on four types of suboptimal action data (noisy trajectories, sim-to-real gap, task mismatch, and large-scale data mixtures) across six tasks. The results show that it effectively learns from arbitrary sources of suboptimal data. Notably, it outperforms existing co-training baselines by up to 33% when scaled to Open X-Embodiment - a large dataset with heterogeneous data quality and unstructured distribution shifts. Overall, Ambient Diffusion Policy increases the utility of suboptimal demonstrations and expands the set of usable data sources in robotics.

Gradient-based adversarial attacks remain a dominant threat to deep neural networks (DNNs), as they exploit gradient information to efficiently optimize adversarial perturbations. To address this, we investigate whether reinforcement learning (RL) training can disrupt the gradient structure used by attackers by training image classifiers with policy-gradient objectives and epsilon-greedy exploration. Through systematic experiments across CIFAR-10, CIFAR-100, and ImageNet-100 with multiple architectures, we find that RL-trained classifiers significantly disrupt gradient-based adversarial optimization. To explain this, we conduct a comprehensive mechanism analysis using loss landscape visualization, static and dynamic gradient indicators, and predictive entropy. Our analysis reveals that RL acts as an implicit regularizer, producing models with highly unstable gradient directions and smaller gradient magnitudes. This combination makes each PGD step both unreliable in direction and limited in magnitude, causing gradient-based attacks to fail within practical iteration budgets. We further show that combining RL with adversarial training (RL-adv) provides a dual-layer defense operating at two complementary levels: RL degrades gradient information available to attackers (gradient-level defense), while adversarial training strengthens decision boundaries (boundary-level defense). RL-adv achieves the highest robustness across all major attack types evaluated, including gradient-based (PGD, AutoAttack), transfer-based, and query-based attacks, outperforming SL-adv by a significant margin. These findings identify RL-induced gradient disruption as a complementary robustness mechanism and motivate future research on hybrid SL-RL training schedules that combine SL's efficiency with RL's gradient-regularization properties.

This paper investigates reinforcement learning (RL) methods for improving tool-calling capabilities in multimodal small language model (SLM) agents. While existing works have explored various reward designs to improve agentic tool-calling ability, these approaches face inherent limitations for SLM training, especially under multimodal scenarios. First, many existing methods evaluate tool use correctness through exact matching against certain ground-truth or predefined formats. However, this assumption is often unsuitable for multimodal tasks, where multiple tool use paths may be valid and annotated tool trajectories are typically unavailable. Second, such sparse and brittle binary rewards provide little guidance on how to improve the underlying decision process, making them particularly difficult for multimodal SLM to learn from. To address these issues, we propose Input Attribution-Aware Policy Optimization (IAPO), an RL algorithm for improving tool use in multimodal SLM by aligning the model's attribution across input components with that of a stronger teacher. Experiments on Qwen2.5-VL-3B show that the proposed method improves visual question answering accuracy by an average of 3% across six test sets compared with existing visual tool use work, by helping the model attend to the most relevant input evidence.

Reward models for text-to-video (T2V) generation guide post-training but often fail at fine-grained semantic alignment. We trace this to two structural weaknesses in existing reasoning-based reward models: they do not systematically verify every condition described in the prompt, and the visual evidence supporting each judgment remains implicit in their free-form reasoning. We propose SG-PVR, a video reward model that addresses these limitations through plan-and-verify reasoning grounded in spatio-temporal scene graphs. The verification plan decomposes the prompt into atomic claims, ensuring every requirement is checked. The spatio-temporal scene graph, encoding entities, attributes, and temporally-grounded relations, is extracted from the video and maintained as a persistent structured visual reference throughout reasoning. Each claim is verified against both the video and the scene graph, anchoring judgments in explicit visual evidence. SG-PVR achieves strong performance on semantic alignment, including fine-grained temporal semantics. As a test-time reranker, it further enhances compositional alignment in T2V generation.

Spatial reasoning remains a challenge for Multimodal Large Language Models (MLLMs), as it requires reliable multi-hop inference over both intermediate states and state transitions. Current studies often leave intermediate states unverified and treat state transitions as implicit processes, which limits reliability in multi-hop spatial reasoning. To address this, we propose State-aware Visualization-of-Thought (SVoT), a reinforcement learning framework that generates interleaved, verifiable intermediate states and visualizations. SVoT integrates transition reasoning chains into the generation processes, enabling the model to verify action preconditions and effects through interleaved textual and visual reasoning. We train SVoT via Group Relative Policy Optimization (GRPO), instantiating verification through reward design and evaluating the efficacy of different fine-grained rewards. As existing benchmarks reduce state transitions to single-variable updates, substantially simplifying the problems, we establish five domains by extending classical environments and introducing two novel domains, Pacman and Gather, that require multi-object interactions and numerical reasoning. These domains support systematic evaluation of multi-hop spatial reasoning with quantitative verification of generated intermediate states and transition reasoning. SVoT with transition-aware supervision achieves state-of-the-art performance across the introduced domains, yielding up to a 65% absolute accuracy gain on out-of-distribution test sets.

Distilling a large speech foundation model (SFM) into an efficient student model has been successfully applied to low-resource environments. Although distillation reduces inference latency, it requires an additional student model training. However, the training efficiency of SFM distillation remains underexplored. In this work, we explore training acceleration of SFM distillation to speed up model deployment. We examine the potential of stacking, in which the model depth is progressively increased through training until the target model depth is reached. While existing stacking methods improve training speed, they suffer from performance degradation. To handle this limitation, we propose interleaved stacking, a novel stacking method that consistently preserves layer position throughout the stacking process. This property is particularly critical in SFMs, in which each layer encodes distinct layer-specific knowledge. We validate the effectiveness of the proposed method on SUPERB.

Recent work has shown that on-policy distillation can internalize privileged context, such as system prompts or task hints, into a student model so that the context is no longer needed at inference time. Although this approach successfully improves the student's no-context performance, we identify an interesting and previously unstudied phenomenon: in many settings, reintroducing the original privileged context to the distilled student actually degrades its performance, even on instances it already solves correctly without context. We term this context-induced degradation and argue that robust internalization demands not only matching the teacher's context-conditioned behavior, but also remaining stable when the context is reintroduced, a property we call context removability. Motivated by this observation, we propose a lightweight consistency regularizer that first anchors the student's no-context output via stop-gradient, then penalizes the context-conditioned output for deviating from it via forward KL divergence. This simple addition requires only one extra forward pass per training step, yet it effectively mitigates context-induced degradation and, in many cases, even improves no-context performance. Across 12 configurations spanning diverse domains and model families, our method improves context-conditioned accuracy in the majority of settings, reduces context-induced harm in 11 out of 12 settings, and effectively eliminates response-length inflation. A mechanistic case study further confirms that context removability is achieved at the representation level, with hidden states remaining nearly identical regardless of whether the context is present.

In earlier work I showed that a 35B-class Mixture-of-Experts model can be loaded and executed on a consumer laptop with 8 GB of GPU memory. That result solved a placement problem and immediately exposed a different one: even correctly placed, the large model needed roughly four seconds to answer, because it was still being invoked at every query. This paper documents what happened when I stopped invoking it. During an offline phase, the large model reads source documents and writes verified answer entries into a structured knowledge store; at runtime, only a lightweight router, a deterministic renderer, and a 1B-class model are active. On the same 8 GB laptop, end-to-end response time fell from approximately 4,465 ms to 518 ms, effective end-to-end throughput rose from 15.7 to 131 tokens per second, and the small model's streaming decode rate held at 226-237 tokens per second with a time-to-first-token of 29-62 ms. The bottleneck is structural: three different large models (Qwen, Gemma, and GLM class) all showed the same multi-second runtime cost, and all three produced usable knowledge stores offline. On a 563-entry store built from seventeen real documents, keyword routing collapsed to 1.5% top-1 accuracy while BM25-based routing reached 92.8% (99.4% top-3), and a confidence gate raised effective top-1 to 98.0% by escalating 12.3% of queries. Exact-match fidelity of the small model ranged from 9/9 to 0/9 across envelope formats carrying identical content. A 16-case verification gate blocked all ten corrupted entries while admitting all six supported ones.

Production LLM systems accumulate reusable operational experience, but the practical deployment issue is not merely whether such experience can help. It is how different serving strategies trade off quality against online cost under realistic constraints. Injecting external experience can improve task quality, yet it also increases prompt burden, latency, and serving pressure. We study external experience serving as a deployment-oriented quality-cost trade-off problem. We evaluate this question in a real production moderation setting, with tool-use and GPQA as supporting contrast tasks that expose different output-cost regimes. We compare no-experience baselines, random experience controls, global prompt injection, and retrieval-based selective injection, and analyze both task quality and serving cost. The results show that, once experience becomes case-dependent, selective retrieval provides a stronger operating point than unconditional global injection. They further show that retrieval quality matters more than simply increasing Top-$K$, and that the same serving policy can exhibit substantially different cost-benefit profiles across short-output and decode-heavy regimes. These findings suggest that external experience is best treated as a selective, cost-aware serving decision rather than as a universal add-on. Overall, in the settings studied here, external experience pays off only when both the serving interface and the task-specific cost structure make its quality gains worth the online cost.

Long input sequences are central to document understanding and multi-step reasoning in Large Language Models, yet the quadratic cost of attention makes inference both memory-intensive and slow. Context distillation mitigates this by compressing contextual information into model parameters, and recent work such as Doc-to-LoRA amortizes context distillation into a single forward pass that generates one LoRA adapter per document. However, producing a single monolithic adapter for all queries leads to irrelevant-query interference, limited compositional recall, and poor scalability to long-document reasoning. To address these challenges, we propose Doc-to-Atom (Doc2Atom), a compositional parametric memory framework that decomposes each document into semantically typed knowledge atoms. Each atom is compiled into an independent micro-LoRA adapter and a provenance retrieval key. At inference time, a lightweight query router selects and assembles only the relevant atoms into a query-specific adapter, which is then injected into a frozen base model. The entire system is trained end-to-end through a multi-objective distillation framework. Experiments on six diverse QA benchmarks demonstrate that Doc2Atom outperforms Doc-to-LoRA baselines while reducing the memory cost of document internalization.

Smart factories are evolving into Cyber-Physical Systems (CPS), demanding increased autonomy. This necessitates real-time decision making, facilitated by insights derived from sensor data. Process mining offers a valuable approach to gain such insights and guide actions. The edge computing paradigm supports this real-time requirement by enabling network communication between sensors and leveraging nearby computing resources. This paper investigates the implications of performing real-time process mining algorithms on the edge. Within this paper, we first propose a formalism to describe relevant datasets and the computing topology. We then evaluate the edge computing approach through a case study involving an edge-based conformance checking algorithm. The results demonstrate the feasibility and benefits of edge-based real-time process mining for enhanced autonomous control in smart factories.

Long-video understanding remains challenging for multimodal large language models, because temporally extended videos often contain thousands of frames and are therefore expensive to process exhaustively. Existing methods usually construct compact visual inputs from long videos under a limited visual budget. However, most of them still follow a frame-centric paradigm and apply similar representations to retained content regardless of its importance. This makes it difficult to preserve both high-fidelity visual evidence and broad temporal coverage. To address this issue, we propose Q-Fold, a training-free input construction framework for long-video understanding. Instead of treating isolated frames as the basic modeling unit, Q-Fold operates on contiguous temporal segments and constructs a heterogeneous Focus--Context representation under query guidance. Query-relevant segments are preserved as high-fidelity Focus Frames, while less relevant segments are folded into chronology-preserving contextual layouts. In this way, Q-Fold preserves critical visual evidence and broad temporal coverage, while better maintaining local temporal continuity within short segments. Experiments on four long-video benchmarks with multiple Video-MLLMs show that Q-Fold consistently improves performance without increasing the input budget. Notably, it achieves gains of up to 9.1 percentage points on an ultra-long video benchmark. Code will be made publicly available.