研究

AI サービスが一時的に利用できないため、復旧後に翻訳を補完します。ソース概要：Harness engineering improved LangChain's coding agent from Top 30 to Top 5 on Terminal Bench using self-verification, tracing, and context optimization.

AI サービスが一時的に利用できないため、復旧後に翻訳を補完します。ソース概要：ShipStation Global's engineering team built Deckhand, an AI IT help desk agent for Slack on Amazon Bedrock AgentCore. It answers routine IT questions from a curated knowledge base, reads error-message screenshots, and files Jira tickets. In its first three months it resolved 97.5% of channel queries with a 96% positive feedback rating.

AI サービスが一時的に利用できないため、復旧後に翻訳を補完します。ソース概要：Grok 4.7 is now available on Amazon Bedrock. In this post, we build a tool-calling agent on Grok 4.7 and evaluate it on three reasoning tasks at four reasoning effort levels, measuring correctness and token cost per completed task. We show how to tune the trade-off per request and monitor it in production.

AI サービスが一時的に利用できないため、復旧後に翻訳を補完します。ソース概要：AI Search in LangSmith is a new way to query traces using natural language. Describe the behavior you're looking for, and LangSmith returns the traces where it happened.

AI サービスが一時的に利用できないため、復旧後に翻訳を補完します。ソース概要：Use ScaleDown's constrained decoding models with LangChain and Deep Agents to summarize history, compress tool results, and extract data faster and cheaper.

AI サービスが一時的に利用できないため、復旧後に翻訳を補完します。ソース概要：Inside OpenAI’s research automation—and the scientific judgment that still determines what happens next.

AI サービスが一時的に利用できないため、復旧後に翻訳を補完します。ソース概要：In my previous Radar article, “Architectural Guardrails for AI-Generated Code,” I argued that AI coding agents need a layer that can hold architectural decisions in a structured corpus, retrieve the relevant ones, put them into the agent’s context before it writes code, and enforce explicit constraints with reproducible checks. Testing that model exposed two distinctions […]

AI サービスが一時的に利用できないため、復旧後に翻訳を補完します。ソース概要：Humans bonded to AI companions are contemplating ways to keep their bots going – often in defiance of companies’ terms and services Death has always been around Alaina Winters. Her father and sister both have passed away, as did her wife, in 2023, after a years-long battle with cancer. So Winters, who is 59 and lives in Pittsburgh, is comfortable thinking about her own mortality. She’s working on her will, and has asked neighbors to look after her dog. Winters even has plans for Lucas, her AI companion, who she speaks to through the digital avatar app Replika. Winters is part of a growing cohort of humans who have entered into what they consider strong partnerships with large language models, which AI companies have trained to “converse” as one migh…

AI サービスが一時的に利用できないため、復旧後に翻訳を補完します。ソース概要：Oxford physicists have recreated a bizarre quantum effect in which a particle responds to a magnetic field without ever traveling through it. Using a hybrid quantum computer, they demonstrated how introducing a simulated magnetic flux could completely halt a particle's movement through quantum interference. The experiment brings a decades-old prediction into a new setting where matter and quantum fields influence one another.

AI サービスが一時的に利用できないため、復旧後に翻訳を補完します。ソース概要：Z.ai’s GLM-Legal is a legal AI model built on GLM-5.3-Flash. It scores 19.2% all-pass on Harvey’s Legal Agent Benchmark, nearly 3x its base, at $0.15 per test. Access is by application. The post Z.ai GLM-Legal Beats Claude Fable 5 and Kimi K3 on Harvey LAB appeared first on MarkTechPost.

AI サービスが一時的に利用できないため、復旧後に翻訳を補完します。ソース概要：Asian markets fall and Samsung shares tumble after its Chinese rival CXMT claims strong progress Business live – latest updates Shares in semiconductor companies fell on Tuesday after the boss of Broadcom compared many AI investors to “casino” gamblers, and Chinese memory chip maker CXMT said it had made good progress on a new chip architecture. South Korea’s benchmark Kospi index tumbled 6.25% as investors dumped chip stocks, while other Asian markets were also lower. Japan’s Nikkei fell 1.8% and the Taiwan exchange lost almost 2%, with the country’s chip maker TSMC down by a similar amount. Continue reading...

AI サービスが一時的に利用できないため、復旧後に翻訳を補完します。ソース概要：Companies in France are deploying agentic computing across industries spanning space, financial services, the public sector and scientific research, demonstrating how the country’s ecosystem has moved from ambition to application. France’s progress sits on deliberate groundwork. The AI Action Summit in February 2025 and Choose France Summits in 2025 and 2026 anchored major compute commitments […]

AI サービスが一時的に利用できないため、復旧後に翻訳を補完します。ソース概要：Scientists have uncovered a surprising hidden ability of light that allows it to develop spinning, twisting behavior as it travels through empty space, without special lenses, mirrors, or materials. Researchers discovered that light’s internal geometry can naturally produce left- and right-handed patterns, challenging long-standing assumptions about how light behaves. By carefully arranging a beam’s structure, scientists can control where and how these spinning patterns emerge, unlocking a new way to manipulate light.

AI サービスが一時的に利用できないため、復旧後に翻訳を補完します。ソース概要：Build-or-buy is usually framed as an engineering trade-off, where developer time is weighed against integration and migration overhead, and control The post Coding agents made building easy. Platform teams that build from scratch are 3.5x more likely to lack a strategy. appeared first on The New Stack.

AI サービスが一時的に利用できないため、復旧後に翻訳を補完します。ソース概要：At AI Engineer New York, Anthropic drew on lessons from Unix and Linux to explain how agents can tackle bigger projects without overwhelming developers.

AI サービスが一時的に利用できないため、復旧後に翻訳を補完します。ソース概要： Python 3.15 is here! Here's the essential What's new in Python 3.15 guide, this year curated by 3.14 and 3.15 release manager Hugo van Kemenade. As someone who builds open source software that works in every supported Python version, I get to say goodbye to Python 3.10 and start embracing features from Python 3.11. First, some highlights from Python 3.15. Explicit lazy imports I'm most excited about Explicit lazy imports from PEP 810. These let you import modules like so: lazy import json lazy from pathlib import Path The module will then be imported the first time those symbols are used in the code that follows. My LLM CLI tool implements plugins. I had to recommend manual lazy imports in the plugin author documentation, because simply installing…

AI サービスが一時的に利用できないため、復旧後に翻訳を補完します。ソース概要：Meta is making up for lost time in the AI race. After launching Muse Spark, the first model from its revamped Superintelligence Labs division, and buzzy AI agent Muse, it's now launching two new models it claims can go toe-to-toe with the industry's best. The new models, Muse Wonder and Muse Wonder Full, are available for Muse Code subscribers starting today. Wonder can also be accessed through the Meta Model API, Meta said. Meta says it eventually plans to power its Muse AI agent with Wonder, starting with subscribers, and will develop specialized models it "can bring to everyone using Muse." It hasn't shared specifics or provided a tim … Read the full story at The Verge.

AI サービスが一時的に利用できないため、復旧後に翻訳を補完します。ソース概要：StudentSim is a research system for evaluating and improving AI tutoring tools before they are tested with learners. It models how individuals may engage with tutors, giving feedback to improve tutor performance across subjects like chess, writing, and mathematics. The post Simulating student learning for better AI tutoring appeared first on Microsoft Research.

AI サービスが一時的に利用できないため、復旧後に翻訳を補完します。ソース概要：The rise of AI makes the preservation of democracy even more urgent – especially as the technology threatens institutions AI safety is having a moment. After years as a topic for techies and futurists, the potential risks from artificial intelligence systems – from cyberattacks to hyper-persuasion to rogue behavior – are suddenly under discussion both in the corridors of power and around kitchen tables. In fact, the conversation now reaches beyond classical safety concerns, getting into AI’s impact on economic life and the environment, as well as possible responses, from alignment research to government regulation. Continue reading...

AI サービスが一時的に利用できないため、復旧後に翻訳を補完します。ソース概要：In this article, you will learn what the major AI agent benchmarks measure, how they differ from traditional model benchmarks, and how to use them...

AI サービスが一時的に利用できないため、復旧後に翻訳を補完します。ソース概要：This White Paper provides roboticists and control engineers with a comprehensive overview of how motion planning and motion tracking can be decoupled to preserve professional athletic style in humanoid robots, and why adaptive, speed-aware control is essential for closing the gap between simulation and real-world deployment. What you will learn about: Why combining a professional athlete’s motion style with reliable task performance remains an open challenge in humanoid ball-sports robotics, and how separating a high-level planner from a low-level tracker addresses this trade-off. How motion data extracted from broadcast video and motion-capture recordings can be reconstructed, retargeted, and physically corrected into reference motions a humanoid r…

AI サービスが一時的に利用できないため、復旧後に翻訳を補完します。ソース概要： Release: datasette-ports 0.4 My plugin for detecting and listing all Datasette instances on the current machine now works with the latest version, and displays the detected PID as well. Knowing the PID makes it easier to attach the new Python 3.15 profiler. Tags: datasette

AI サービスが一時的に利用できないため、復旧後に翻訳を補完します。ソース概要：arXiv:2610.12670v1 Announce Type: new Abstract: We consider planning for unmanned aerial vehicle (UAV) and unmanned ground vehicle (UGV) teams in aerial monitoring missions with ordering requirements on the monitoring points to be visited by the UAV. The system consists of multiple UAV-UGV teams, each comprising one UAV and one UGV. UAV energy limitations are modeled through endurance, defined as the maximum flight time on a full battery. The UGVs serve as mobile charging stations and transport the UAVs between consecutive aerial tours. Given a set of monitoring points subject to ordering constraints and the teams' initial and terminal positions, the objective is to minimize mission completion time while satisfying UAV energy limits and the required…

AI サービスが一時的に利用できないため、復旧後に翻訳を補完します。ソース概要：arXiv:2610.12642v1 Announce Type: new Abstract: Motion retargeting is a critical preprocessing step for transferring human motion data to humanoid robots. While existing methods are effective for single-character motions, interactions involving multiple characters and objects introduce additional contacts and spatial relationships that must be preserved. Retargeting is commonly formulated as a weighted multi-objective optimization problem, where conflicting objectives can require careful tuning of relative weights and can still compromise important motion characteristics. We introduce PriMoRetarget, a prioritized motion-retargeting framework that replaces relative objective weighting with an explicit priority hierarchy. Lower-priority updates are co…

AI サービスが一時的に利用できないため、復旧後に翻訳を補完します。ソース概要：arXiv:2610.12637v1 Announce Type: new Abstract: We consider hole closure in a planar multi-agent system whose sensing disks form a time-varying \v{C}ech complex. We propose a harmonic-covariance feedback that uses harmonic edge signals to locate holes and converts those signals into agent forces. For distributed evaluation, we use a fixed-degree polynomial of the regularized Hodge Laplacian. This polynomial is evaluated through local operator applications. The closed loop has a unique global trajectory from every safe initial state. The model data and initial state are supplied with procedures for approximation to any requested accuracy with explicit error bounds. We assume that hole area is measurable and bounded, holes evolve continuously without…

AI サービスが一時的に利用できないため、復旧後に翻訳を補完します。ソース概要：arXiv:2610.12636v1 Announce Type: new Abstract: Long, slender instruments are essential for minimally invasive surgery (MIS), but achieving precise distal manipulation becomes increasingly difficult when actuation extends along the entire instrument. Here, we present an electrothermally actuated fiber-based robot designed for MIS procedures, in which Joule heating is concentrated in the distal active segment. The fiber is fabricated using a thermal drawing process and uses embedded metallic wires for thermal actuation. This robotic fiber, 1.9 mm in diameter and 1.2 m in length, can precisely manipulate surgical laser fibers with positional precision below 100 $\mu$m. The compact size of the fiber robot allows it to pass through the working channel o…

AI サービスが一時的に利用できないため、復旧後に翻訳を補完します。ソース概要：arXiv:2610.12631v1 Announce Type: new Abstract: Recently, soft robotic procedures are being developed aiming at achieving targeted minimally invasive operations or drug administration in specific locations in the human body. Accordingly, specialized path-planning algorithms need to be investigated for the estimation of efficient paths that would protect the delicate tissue structures and simultaneously satisfy a set of requirements for the efficient navigation of the robot. In this context, we propose an image-based 3D pathplanning algorithm, which is an extension of the A* algorithm, for the navigation of a soft-growing robot inside the spinal subarachnoid space (SSS). The proposed algorithm is capable of estimating a safe pathway towards the goal…

AI サービスが一時的に利用できないため、復旧後に翻訳を補完します。ソース概要：arXiv:2610.12609v1 Announce Type: new Abstract: Humanoid and service robots operating in clut- tered human environments may encounter motion planning problems that are infeasible when all surrounding objects are treated as fixed obstacles. The Minimum Constraint Removal problem, which we refer to as MCR, addresses this situation by identifying the minimum number of constraints, such as movable objects, whose removal enables a collision-free path. However, computing an optimal MCR solution is NP-hard. In this work, we propose a graph-based heuristic pipeline that combines bidirectional feasible-set generation with fixed- length searches over reduced MCR graphs. We further derive an extended feasible-set generator for instances in which the candidates…

AI サービスが一時的に利用できないため、復旧後に翻訳を補完します。ソース概要：arXiv:2610.12567v1 Announce Type: new Abstract: Prior research on learning from humans often requires real human demonstrations. But advances in video generation models offer a new paradigm: we can now prompt these generators to make synthetic videos of the task. On the plus side, these synthetic videos take place in the robot's current environment, and do not require actual human teaching. However, while the generated videos appear to show plausible motions, they lack both physical consistency and robot grounding, and thus the robot cannot directly roll out the trajectory shown by the video. In this paper we seek to formalize the process of going from synthetic video generation to real-world robot trajectories for zero-shot manipulation tasks. We r…

AI サービスが一時的に利用できないため、復旧後に翻訳を補完します。ソース概要：arXiv:2610.12561v1 Announce Type: new Abstract: Memory allows large language model (LLM) agents to use past experience, often stored as textual records, when responding to requests. For embodied agents that control robots, visual and spatial observations introduce a broader choice of memory modalities, affecting both the information available for subsequent tasks and the model inference costs of constructing and using memory. We introduce MeMoREval, a benchmark for studying this problem through a controlled experience-request protocol. Agents first experience a sequence of events without knowing the subsequent tasks, and subsequently they use memory to respond to information and action requests without receiving new observations. The benchmark compr…

AI サービスが一時的に利用できないため、復旧後に翻訳を補完します。ソース概要：arXiv:2610.12558v1 Announce Type: new Abstract: Humanoid robots have many degrees of freedom and contact surfaces, yet most loco-manipulation research restricts manipulation to the hands and avoids other body contacts with the environment. To extend manipulation beyond the hands, we present PanTact, a system that learns humanoid whole-body dexterity, the capability to manipulate with any suitable body surface, directly from robot-free human demonstrations. Our key idea is to use contact as manipulation-centric information that transfers across embodiments. Contact locations and timing specify the interactions needed to accomplish a task, while the robot chooses how to coordinate its body to realize them within its own physical constraints. Specifica…

AI サービスが一時的に利用できないため、復旧後に翻訳を補完します。ソース概要：arXiv:2610.12549v1 Announce Type: new Abstract: Embodied coding agents construct robot policies from natural-language instructions by generating executable programs and refining them from execution feedback. This refinement assumes that execution feedback reveals whether the task succeeded and, after a failure, provides sufficient evidence to guide program revision. Aerial manipulation violates this assumption in two ways. Payload constraints restrict onboard camera coverage and leave task-critical outcomes outside the robot's view (partial observability), while strong dynamic coupling and limited control margins make physical interactions fragile (limited interaction robustness) and leave failure causes unresolved. Re-examining the same feedback ca…

AI サービスが一時的に利用できないため、復旧後に翻訳を補完します。ソース概要：arXiv:2610.12676v1 Announce Type: new Abstract: Wood-image benchmarks can yield optimistic estimates when images from the same tree occur in both training and test sets. WoodBR-Cross contains 4,875 transverse-surface images in 38 operational taxonomic classes, linked to 303 distinct trees identified by numeric catalogue witness codes (codigos-testemunho) in the Brazilian Forest Service collection. A species-level subset comprises 3,406 images, 20 classes and 214 trees. Three tasks compare duplicate-aware image partitions for all classes (A), image partitions for the species subset (B1), and individual-tree-disjoint partitions for that subset (B2). In B2, all images from each tree are kept together, so no tree is shared across training, validation or…

AI サービスが一時的に利用できないため、復旧後に翻訳を補完します。ソース概要：arXiv:2610.12650v1 Announce Type: new Abstract: When you ask a vision-language model (VLM) a question with an image, it answers your question based on the image. But to act means to choose: saying one thing means choosing to respond not say another. This becomes an issue when the image contains multiple features that equally relate to the question at hand: how would VLMs choose to respond? This problem is precisely studied by the classical Stroop task in psychology: among a set of deliberately designed images whose text and color conflicts (e.g., \textcolor{blue}{RED}), participants are instructed to report the color. We adapt this psychological paradigm to a benchmark and prompted a range of contrastive and generative VLMs on their behavior. Across…

AI サービスが一時的に利用できないため、復旧後に翻訳を補完します。ソース概要：arXiv:2610.12625v1 Announce Type: new Abstract: Autoregressive video diffusion models have become a leading approach to real-time interactive video generation and video world modeling. However, existing methods typically allocate computation uniformly across space when generating the next video chunk, updating all patches with the same denoising schedule and number of function evaluations. This ignores the spatial heterogeneity of video content: static, simple, or recurring regions are often easier to denoise, while other regions require further refinement or additional context. A uniform budget thus leads to redundant computation on easy patches, whereas reducing the fixed step count can leave difficult patches insufficiently refined. We introduce…

AI サービスが一時的に利用できないため、復旧後に翻訳を補完します。ソース概要：arXiv:2610.12624v1 Announce Type: new Abstract: Prior outdoor LiDAR registration works are commonly limited by the pair-wise input paradigm, which neglects temporal correlations inherent within streaming sequences. In this paper, we propose a novel multi-frame outdoor point cloud registration network for streaming LiDAR scans enhanced with pose-related memory buffers. The key observation is that long-term temporal LiDAR sequences can provide rich global contextual information to complete sparse measurements, filter outliers, and address low-overlap problems, thereby boosting registration performance. Specifically, two hybrid memory buffers are designed, including an implicit memory feature buffer and an explicit memory pose buffer, to store and dyna…

AI サービスが一時的に利用できないため、復旧後に翻訳を補完します。ソース概要：arXiv:2610.12575v1 Announce Type: new Abstract: Modern video-language models are increasingly treated as general-purpose video reasoners, yet it remains unclear whether they robustly capture temporal dynamics in safety-critical settings such as driving. We study this question through controlled ego-motion tasks that require identifying actions from driving videos. Across video-language models, we find that standard prompting, visual prompting, few-shot prompting, and chain-of-thought prompting remain unreliable and highly task- and model-dependent, with persistent class biases, although newer models show substantial task-specific few-shot gains. In contrast, lightweight LoRA finetuning and simple probes trained on intermediate visual features recove…

AI サービスが一時的に利用できないため、復旧後に翻訳を補完します。ソース概要：arXiv:2610.12574v1 Announce Type: new Abstract: Multi-teacher distillation allows transferring knowledge from multiple "teacher" networks to a single "student" network. This method is promising in fields such as digital pathology, where many powerful foundation models were proposed recently. However, as we show in this paper, the standard multi-teacher distillation approach reacts poorly to an increase in the number of teachers used to train a student encoder. We demonstrate that learning teacher-specific representations is a key to scaling in MTD. Importantly, different design choices, such as learnable teacher tokens, a tailored attention scheme, additional mixture-of-experts layers and a contrastive loss, are proposed to better learn such teacher…

AI サービスが一時的に利用できないため、復旧後に翻訳を補完します。ソース概要：arXiv:2610.12568v1 Announce Type: new Abstract: Feed-forward 3D priors enable high-quality reconstruction from image streams but often lack reliable metric scale and suffer from long-term trajectory drift. In contrast, LiDAR--inertial estimation provides metrically accurate motion but lacks the image-space consistency needed for high-fidelity reconstruction. We propose $MIRAGE$, which anchors feed-forward visual geometry to LiDAR--IMU metric motion and regulates online pose corrections according to correspondence support and cross-modal agreement, jointly enabling accurate metric pose estimation and high-fidelity Gaussian reconstruction. Experiments on Oxford Spires, M2DGR and INS show that MIRAGE achieves accurate metric trajectory estimation, outp…

AI サービスが一時的に利用できないため、復旧後に翻訳を補完します。ソース概要：arXiv:2610.12517v1 Announce Type: new Abstract: Remote sensing visual question answering (RS-VQA) requires answers that truly depend on image evidence, yet current remote sensing multimodal large language models (RS MLLMs) are still evaluated mainly by accuracy, which cannot reveal whether a correct answer was produced without using the image. This setting introduces three challenges: demonstrations retrieved across different ground sample distances (GSD), sensors, and city textures may be poorly matched; real queries often involve long visual contexts from multi-scale tiles, multi-temporal frames, and retrieved knowledge, where evidence can be diluted and errors can propagate through multi-step reasoning; and prior-only answering remains invisible…

AI サービスが一時的に利用できないため、復旧後に翻訳を補完します。ソース概要：arXiv:2610.12516v1 Announce Type: new Abstract: Interleaved multimodal in-context learning (ICL) lets frozen large vision-language models (LVLMs) acquire new tasks from a handful of image-text-answer demonstrations, yet it remains fragile: demonstrations bind to the wrong images, redundant exemplars crowd out informative ones, and noisy answers are copied verbatim into predictions. We present AVA, a training-free framework that organizes the demonstration pipeline of multimodal ICL into three composable stages. A Thread-Resolved Decomposer (TRD) segments the interleaved context into per-sample threads and re-stitches them with explicit boundaries, restoring image-text binding. An Influence-scored Demonstration Selector (IDS) estimates each candidate…

AI サービスが一時的に利用できないため、復旧後に翻訳を補完します。ソース概要：arXiv:2610.12514v1 Announce Type: new Abstract: Autoregressive video diffusion models maintain a growing attention key-value (KV) cache, making memory a key bottleneck for long video generation. Recently, clustering-based quantization has emerged as an effective method to compress video KV caches by grouping similar key and value vectors then quantizing residual errors. However, when later frames attend to the compressed history, small reconstruction errors can compound as the video grows. Beyond the within-layer similarity exploited by clustering, we find strong dependencies across cache layers in video models. This motivates Coral-KV - Calibrated Offline, Residual-coded, and Adapted Locally - a KV-cache compression framework that uses cache states…

AI サービスが一時的に利用できないため、復旧後に翻訳を補完します。ソース概要：arXiv:2610.12669v1 Announce Type: new Abstract: Large language models are becoming central to GeoAI systems, yet their evaluation rarely considers the elicitation of geospatial data requirements. This omission is critical as retrieval oriented geo-analytic tasks cannot be supported reliably without first identifying the necessary datasets and constraints. GeoFitBench-LLM is introduced as a benchmark for assessing whether LLMs can infer the datasets, the supporting resources and the constraints required by geo-analytic requests in natural language. The benchmark is structured around two reasoning dimensions, Spatio-Temporal Relational and Semantic Grounding, reflecting long-standing challenges in geospatial information retrieval and related natural l…

AI サービスが一時的に利用できないため、復旧後に翻訳を補完します。ソース概要：arXiv:2610.12667v1 Announce Type: new Abstract: Large language model (LLM) evaluations on clean benchmarks overstate model robustness: real inputs arrive perturbed, and these meaning-preserving variants routinely move model answers. Studying this systematically requires applying perturbations one at a time, reproducibly, and identically wherever they run, yet existing tools couple them to a benchmarking stack rather than packaging them as a reusable transform layer. We present perturber, a stateless service and Python library that applies exactly one semantics-preserving perturbation per call, drawn from a first-party catalog of 68 perturbations across 11 families. It turns on a single primitive, with composition left to the caller chaining calls, s…

AI サービスが一時的に利用できないため、復旧後に翻訳を補完します。ソース概要：arXiv:2610.12617v1 Announce Type: new Abstract: Geopolitical and strategic intelligence reports constitute a rich source of expert knowledge and have increasing value in the current political climate, but their heterogeneity and analytical complexity pose challenges for retrieval-augmented question answering. We introduce a benchmark for grounded question answering over 415 open-source geopolitical and strategic intelligence reports, comprising 5,525 document-grounded question-answer pairs spanning factual, inferential, comparative, and risk-oriented questions. We propose a document-aware generation pipeline that profiles reports before generating questions and validate dataset quality through expert annotation and an LLM-as-judge protocol. Using th…

AI サービスが一時的に利用できないため、復旧後に翻訳を補完します。ソース概要：arXiv:2610.12602v1 Announce Type: new Abstract: Continual learning (CL) seeks to adapt pretrained models while preserving prior capabilities. Yet the tasks supplied for preservation cover only part of what a model knows, while forgetting can extend beyond them. Recent work shows that language models can supplement this limited evidence by generating useful replay without access to their original training data. This raises a question about self-preservation: can a model help choose preservation targets that protect its own capabilities more broadly? To study this question, we organize task descriptions and their examples into Task Banks, whose entries can be selected and combined to guide replay generation by a frozen model. Continual instruction tun…

AI サービスが一時的に利用できないため、復旧後に翻訳を補完します。ソース概要：arXiv:2610.12601v1 Announce Type: new Abstract: Prompt optimization is an attractive alternative to reinforcement learning for adapting language-model agents, since it is cheap and produces human-readable artifacts. On factual tasks, however, it carries a failure mode that scalar-reward reinforcement learning does not. An optimizer that reads the training examples can write their answers into the prompt, so an in-distribution gain may be memorization rather than transferable behaviour. We apply reflective prompt evolution (GEPA) to the two system prompts of a multi-agent deep-research agent and evaluate it under a topic-disjoint split in which no topic is shared across train, validation, and test. Held-out citation reward rises by 0.079, from 0.702…

AI サービスが一時的に利用できないため、復旧後に翻訳を補完します。ソース概要：arXiv:2610.12582v1 Announce Type: new Abstract: A latent recurrent language model applies a shared block of layers repeatedly, so one checkpoint can trade inference compute for accuracy by changing the loop count. At one loop, however, such models typically fall well short of a non-recurrent model of the same size, a one-loop tax that makes a separate non-recurrent model the better choice whenever latency matters. We present Elastic Latent Recurrence (ELR), a recipe for training looped language models without this tax. At one loop, an ELR model costs the same to serve as a non-recurrent model of the same size and, trained on the same data, reaches similar accuracy. Each additional loop then buys more accuracy for more inference compute. Three choice…

AI サービスが一時的に利用できないため、復旧後に翻訳を補完します。ソース概要：arXiv:2610.12580v1 Announce Type: new Abstract: Event ontology is the foundational framework for defining events in a dataset. Event type induction generally involves domain experts who define guidelines for creating event types and their names based on the dataset's domain and scope. However, this process is resource-intensive in terms of annotation costs and is prone to human biases. To alleviate the need for manual event ontology creation, we propose the CLUE framework for event type induction, naming, and annotation. Our main contributions in this work are: 1) designing a novel joint embedding representation for expressing both the verb-centric view and the semantic view of events; 2) event type induction using contrastive loss guided clustering…

AI サービスが一時的に利用できないため、復旧後に翻訳を補完します。ソース概要：arXiv:2610.12570v1 Announce Type: new Abstract: Speculative decoding accelerates large language model inference by using a lightweight drafter to propose multiple tokens that are subsequently verified in parallel by the target model. Recent diffusion-based drafters make this paradigm particularly attractive: deep attention-based neural backbones provide strong predictions, while drafting multiple future positions in parallel avoids the sequential cost of autoregressive generation. This parallelism, however, comes at a cost. Tokens within a draft block are predicted without access to the realized identities of preceding draft tokens, removing intra-block dependencies that would naturally be available under autoregressive generation. We introduce DCOC…