Plan Before Search: Search Agents Need Plan
arXiv:2605.28354v1 Announce Type: new Abstract: Training large language models as retrieval-augmented reasoning agents typically combines reinforcement learning with an SFT cold start distilled from a
Knowledge catalogue
arXiv:2605.28354v1 Announce Type: new Abstract: Training large language models as retrieval-augmented reasoning agents typically combines reinforcement learning with an SFT cold start distilled from a
arXiv:2605.28283v1 Announce Type: cross Abstract: Feed-forward networks (FFNs) dominate the parameter count and computation of modern language models, yet existing pruning methods often struggle to co
arXiv:2605.27402v1 Announce Type: cross Abstract: Open-ended grading is central to equitable and personalized education, yet manual grading remains time-consuming and costly, underscoring the need for
arXiv:2605.28153v1 Announce Type: cross Abstract: Accurate and timely weather forecasts are critical for high-impact decisions in modern society. Machine-learning-based weather prediction is emerging
arXiv:2605.28084v1 Announce Type: cross Abstract: Laughter is a complex social signal that conveys communicative intent beyond amusement. While prior work has focused on isolated laughter analysis tas
arXiv:2605.27747v1 Announce Type: cross Abstract: Existing training approaches for large language models learn a single set of parameters, based on large volumes of data, which is typically heterogene
arXiv:2605.28490v1 Announce Type: cross Abstract: 3D object grounding localizes referred objects in a 3D scene from natural language. Unified instance-centric 3D-LLMs aim to solve grounding together w
arXiv:2605.27431v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) presents a naturally compatible and scalable framework for multimodal learning, demonstrating strong adaptability across dive
arXiv:2605.27850v1 Announce Type: new Abstract: Effective multi-agent systems cannot be designed by selecting prompts or communication graphs in isolation. Agent behavior depends on the information an
arXiv:2605.28639v1 Announce Type: cross Abstract: Instruction-based suppression is widely used to prevent language models from generating prohibited content, yet it remains unclear whether suppression
arXiv:2605.28464v1 Announce Type: cross Abstract: Legal Judgment Prediction (LJP) has become a core benchmark for evaluating AI in the criminal legal domain, but it only sees criminal cases that have
arXiv:2605.27817v1 Announce Type: cross Abstract: Video generative models have emerged as a promising robotics backbone, capable of generating videos that depict the completion of complex tasks across
arXiv:2605.28023v1 Announce Type: cross Abstract: Visual captioning requires models to capture visual content faithfully while minimizing both omission and hallucination. As the dominant paradigm for
arXiv:2601.18381v2 Announce Type: replace Abstract: To facilitate the transformation of legacy finite difference implementations into the Devito environment, this study develops an integrated AI agent
Behind the MiMo API Price Reduction: The deepest price cut, up to 99%, is for Input (Cache Hit). The core reason is our inference framework now supports hierarchical KV cache optimization for SWA. Pro
arXiv:2605.26645v1 Announce Type: new Abstract: LLM-based knowledge-graph question answering (KGQA) delegates graph traversal to language models, turning each question into a sequence of local relatio
Completely agree, @hwchase17 ! This is the meta-level breakthrough we've all been waiting for. Self-optimizing loops finally feel production-ready because LangSmith Engine turns evaluation from a manu
arXiv:2605.26496v1 Announce Type: cross Abstract: The Mixture of Experts MoE architecture is highly promising for resource constrained on device deployments yet training these models from scratch incu
In this post, we share how we built NarrateAI using Amazon Bedrock AgentCore to deliver business intelligence at scale for the AWS SMGS (Sales, Marketing and Global Services) organization. You will le
aside_block <ListValue: [StructValue([('title', 'Summary of today’s news'), ('body', <wagtail.rich_text.RichText object at 0x7fb0f516f910>), ('btn_text', ''), ('href', ''), ('image', None)])]> AI-powe
arXiv:2603.01131v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have shown promise in clinical diagnosis but remain limited by unreliable report generation, weak evidence ground
arXiv:2605.27361v1 Announce Type: new Abstract: Modern retrieval agents expose many configuration choices -- LLM, retriever, number of documents, number of hops, and synthesis strategy -- each shaping
arXiv:2605.27081v1 Announce Type: cross Abstract: Fine-grained Mixture-of-Experts (MoE) models sparsely activate only a subset of experts per token, reducing activated computation while maintaining hi
arXiv:2605.26856v1 Announce Type: cross Abstract: Cognitive science remains split between cognitivism - which accounts for recursion and language but cannot ground formal symbols in meaning - and 4E a
arXiv:2605.26759v1 Announce Type: new Abstract: Causal discovery from time series is critical for many real-world applications, such as tracing the root causes of anomalies. Existing approaches typica
arXiv:2605.27071v1 Announce Type: new Abstract: Key knowledge for steel-industry volatile organic compounds (VOCs) governance is scattered across unstructured scientific literature, making it difficul
A post about Pope Leo XIV's encyclical on AI. Why the Pope is right, but perhaps not right enough. Artificial intelligence is reshaping the world in front of our eyes: how we communicate, how we acces
arXiv:2605.24600v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for qualitative data analysis (QDA), yet their outputs often miss the depth and nuance of human analy
arXiv:2605.24583v1 Announce Type: cross Abstract: We audit alignment-induced shifts in residual-stream activations of three open-weight instruction-tuned LLMs (Llama-3.1-8B-Instruct, Gemma-2-9B-it, Qw
arXiv:2605.24381v1 Announce Type: cross Abstract: Time series forecasting drives operational decisions in areas like finance, transportation, and energy. While supervised learning approaches achieve s
arXiv:2605.25352v1 Announce Type: cross Abstract: Deep learning models are vulnerable to adversarial perturbations, raising important concerns for safety-critical deployment. Empirical defenses can ac
arXiv:2605.25662v1 Announce Type: new Abstract: Graph neural networks for node classification are typically trained by gradient descent over hundreds or thousands of epochs. Recent work has shown that
arXiv:2605.25378v1 Announce Type: cross Abstract: Customized image editing aims to equip pre-trained diffusion models with specific visual effects using limited paired data, typically via Low-Rank Ada
arXiv:2604.18179v2 Announce Type: replace-cross Abstract: Hosted-LLM providers have a silent-substitution incentive: advertise a stronger model while serving cheaper replies. Probe-after-return scheme
arXiv:2605.25781v1 Announce Type: new Abstract: Evaluating structured-information extraction from historical documents at scale requires high-precision ground-truth annotations, yet traditional manual
arXiv:2605.23939v1 Announce Type: new Abstract: Web agents require both high-level reasoning (for task decomposition) and low-level interactions (for page elements manipulation) to conduct different t
arXiv:2605.25379v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) has become the standard way to ground large language models in external knowledge, but many systems still organize
arXiv:2605.25477v1 Announce Type: cross Abstract: The ability to efficiently and reliably learn new tasks has been a foundational challenge in robotics. Vision-Language-Action (VLA) models have demons
arXiv:2605.24911v1 Announce Type: cross Abstract: Time series foundation models (TSFMs) have recently achieved strong zero-shot forecasting performance through large-scale pretraining and retrieval-au
arXiv:2605.25939v1 Announce Type: cross Abstract: We here study whether training biases can make hidden neurons specialize in minimal one-hidden-layer MLPs, and whether such specialization improves pr
arXiv:2605.25459v1 Announce Type: cross Abstract: Language models are pretrained as passive predictors with no incentive to model the consequences of their own outputs. Post-training changes this: a m
arXiv:2505.11758v2 Announce Type: replace-cross Abstract: Few-shot adaptation of vision-language models remains fundamentally limited by how negative class signals are handled at inference. Existing m
arXiv:2604.04453v2 Announce Type: replace-cross Abstract: Granular flows govern many natural and industrial processes, yet their interior kinematics and mechanics remain largely unobservable, as exper
arXiv:2602.04139v2 Announce Type: replace Abstract: Neural operators provide a powerful framework for learning discretization invariant mappings between function spaces, but standard deterministic mod
arXiv:2605.24930v1 Announce Type: new Abstract: Transformer-based LLMs achieve strong results on many language tasks; however, long inputs remain challenging because context windows are finite, and pr
arXiv:2605.24598v1 Announce Type: new Abstract: Large language model (LLM) agents excel at solving complex long-horizon tasks through autonomous interaction with environments. However, their real-worl
arXiv:2605.25198v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has become a powerful paradigm for improving language models on reasoning-intensive tasks, but i
arXiv:2605.24728v1 Announce Type: new Abstract: Foundation models can increasingly describe, reconstruct, and generate 3D objects, assemblies, scenes, and environments, but visually plausible spatial
arXiv:2605.24584v1 Announce Type: cross Abstract: Fast linear algebra in deep learning usually comes with a choice: fixed geometry and exact computation, as in the Fourier transform, or adaptive geome
arXiv:2605.25581v1 Announce Type: new Abstract: Single-cell perturbation prediction aims to infer how cells respond to unseen interventions and to achieve out-of-distribution (OOD) generalization, pro
arXiv:2605.25551v1 Announce Type: new Abstract: Many learning problems require uncovering a hidden ordering that reveals structure in unordered data, such as monotonicity in sorting or spatial continu
arXiv:2602.02009v2 Announce Type: replace Abstract: Neuro-symbolic systems aim to combine the expressive structure of symbolic logic with the flexibility of neural learning; yet, generative models typ
arXiv:2605.25665v1 Announce Type: cross Abstract: AI-native software development is often evaluated at the level of individual models, prompts, or generated artifacts. This framing is insufficient for
arXiv:2605.25869v1 Announce Type: new Abstract: Long-term memory is essential for persistent LLM agents, yet prevailing architectures store historical interactions as unstructured, flat text. This unc
arXiv:2605.24681v1 Announce Type: cross Abstract: Large Language Models (LLMs) have shown great promise in multilingual machine translation (MT), even with limited bilingual supervision. However, fine
arXiv:2605.25929v1 Announce Type: cross Abstract: The effectiveness of multi-agent LLM deliberation depends not only on the agents' individual predictions, but also on how they communicate and collabo
arXiv:2603.00857v2 Announce Type: replace-cross Abstract: MultiPUFFIN is a domain-informed multimodal foundation model for predicting thermophysical properties of small molecules, addressing a critica
arXiv:2506.09084v2 Announce Type: replace-cross Abstract: Whole-page optimization (WPO) decides how search and recommendation results are surfaced to users, and large language models (LLMs) open a new
arXiv:2601.20539v3 Announce Type: replace Abstract: Large Language Models (LLMs) have enabled automated heuristic design (AHD) for combinatorial optimization problems (COPs), but existing frameworks'
arXiv:2605.25682v1 Announce Type: cross Abstract: Distributing Transformer inference across embedded edge devices can alleviate individual memory and compute constraints, yet practical benefits on rea