Large language model and reinforcement learning based autonomous construction and progress updates
arXiv:2610.26899v1 Announce Type: new
Abstract: Due to the rapid growth of the global population, traditional construction methods are gradually unable to meet the current housing demand. The advancement of machine learning algorithms has encouraged researchers to explore their applications in the ...
High-dimensional layer-state trajectories reveal the internal dynamics of transformer inference
arXiv:2610.26866v1 Announce Type: new
Abstract: Mechanistic studies of large language models localize function in parameters, attention heads or neurons, but those parts do not specify how one inference unfolds. We treat the ordered layer-state trajectory as the empirical process and test whether l...
Steerable Pluralistic Policy Alignment from Anonymized Crowd Feedback
arXiv:2610.26914v1 Announce Type: new
Abstract: Pluralistic alignment requires AI systems to learn from diverse populations whose preferences may reflect heterogeneous or even conflicting objectives, and to personalize their behavior to individual users. Existing approaches in pluralistic alignment...
Dynamic System Inspired Continuous Large Language Model for AI4Science Tasks
arXiv:2610.26959v1 Announce Type: new
Abstract: Scientific foundation models increasingly operate on continuous phenomena, yet still use discrete residual computation. We ask whether pretrained residual transformations can support additional latent computation without expanding the backbone. To tes...
Navalia: Advancing Cowork Agents through Verifiable Task Synthesis and Long-Horizon Post-Training
arXiv:2610.26887v1 Announce Type: new
Abstract: Large language model (LLM) agents are evolving from conversational assistants into Cowork Agents capable of autonomous planning, tool use, and complex task execution. Financial analysis requires these agents to integrate cross-document evidence and pe...
DataPraxis: Scaling Analytics Tasks via Verified Workspace Evolution
arXiv:2610.26924v1 Announce Type: new
Abstract: General-purpose agents are increasingly expected to perform professional analytics work, which requires sustained reasoning, iterative investigation, and reliable evidence. Training these capabilities requires diverse and challenging tasks. However, g...
Beyond Explicit Intent: Discovering and Shaping Artistic Intent through Human-AI Co-Creation
arXiv:2610.24010v1 Announce Type: new
Abstract: Generative AI is becoming an important medium for artistic creation, yet existing interactions often assume that creators can specify intentions in advance and accurately communicate them through text prompts. Artistic intentions, however, may be vagu...
A Controlled LLM Workflow for Evidence-Grounded Diagnosis of Risk Score Differences
arXiv:2610.23962v1 Announce Type: new
Abstract: We propose a controlled Large Language Model (LLM) workflow for explaining risk score differences using similar historical transactions. The workflow combines reference retrieval and contrastive SHapley Additive exPlanations (SHAP) evidence with refer...
Doing Less with More: A First-Principles Exploration of the Suitability of Agentic Computing over Alternative Architectural Choices
arXiv:2610.23921v1 Announce Type: new
Abstract: There is growing interest in automating business activities with Agentic Artificial Intelligence (AI) due to latter's seeming ease of use. Never has it been easier, or costlier, to do less with more. However, little is known about when agents are pref...
GardenBench: A lightweight, daily evaluation of LLM capabilities
arXiv:2610.23866v1 Announce Type: new
Abstract: We introduce GardenBench, a benchmark with 11 test suites that evaluate the capabilities of Large Language Models (LLMs) across a range of tasks. By systematically prompting LLMs with various lightweight queries, we document day-to-day changes in mode...
How deeptech companies can use AI for smarter R&D bets
Raising a big round is the easy part. A deeptech founder explains how project-level budgets, evidence-based milestones, and AI-assisted analysis help every pound of R&D capital buy down real risk.
Binding-Specific Relearning Savings for Test-Time Continual Learning
arXiv:2610.22381v1 Announce Type: new
Abstract: When a fact becomes harder to elicit from a language model, has the model lost it, or has it merely become less accessible? Parameter-updating test-time continual learning agents are usually evaluated by current output accuracy; we ask whether that me...
When is a large language model a good calibration agent? Physics-labeled prompting for budgeted engineering simulator calibration
arXiv:2610.22379v1 Announce Type: new
Abstract: Calibrating expensive engineering simulators requires tuning model parameters to match reference data, a process heavily constrained by computational costs. This study investigates whether Large Language Models (LLMs), conditioned on physical diagnost...
AlphaDiana: A Measurement System for Agents in Verifiable Reasoning Tasks
arXiv:2610.20675v1 Announce Type: new
Abstract: Agents pair reasoning models with harnesses that organize model calls, execute tools, load skill instructions, and retain history in memory. Understanding agent performance requires linking execution conditions to outcomes, behavior, and resource use....
FlowBudget: Training-Free Sampling-Budget Estimation for Flow Matching Models
arXiv:2610.20636v1 Announce Type: new
Abstract: Sampling from continuous flow-based generators such as flow matching models requires numerical ODE or SDE integration, making inference cost depend on the number of function evaluations (NFEs). In practice, the sampling budget is inherited from prior ...
Feature Elicitation for SAE Steering of Deceptive Behaviour in Small LLMs
arXiv:2610.20638v1 Announce Type: new
Abstract: Research on deceptive alignment is becoming increasingly urgent as frontier-model capabilities advance and their risk of causing catastrophic harm increases. Alignment faking is a form of deceptive alignment, with the compliance gap serving as a key b...
Same Answer, New Box: How Much of RLVR's Out-of-Domain Gain Is Answer Format?
arXiv:2610.20639v1 Announce Type: new
Abstract: Reinforcement learning with verifiable rewards (RLVR) is credited with gains beyond the domain its rewards check, such as higher MMLU accuracy after training on mathematics. Such accuracies are usually read out of the model's text by an answer extract...
KNOU-Flood: Advancing global streamflow forecasting with lead-aware probabilistic machine learning
arXiv:2610.20640v1 Announce Type: new
Abstract: Global streamflow forecasting supports flood preparedness, yet data-driven models trained on reanalysis lose skill when driven by operational forecasts, increasingly so with lead time. AIFL addresses this shift with a two-stage transfer-learning recip...
Evaluating Model Capabilities After Benchmark Saturation
arXiv:2610.20667v1 Announce Type: new
Abstract: Rapid advances in AI capabilities are causing benchmarks to saturate. Once several models approach perfect scores, a benchmark loses its power to differentiate between them, and with it its utility for informing AI safety cases and frontier policies. ...
The World Won't Wait: Evaluating and Teaching Agents Under a Live Clock
arXiv:2610.20665v1 Announce Type: new
Abstract: Large language model (LLM) agents can solve complex interactive tasks, yet reasoning and tool calls take time. In continuously changing environments, an otherwise correct action may arrive too late. We introduce RealtimeBench, with 180 tasks across si...
Value-Informed Schedule Trimming for Accelerated Sequential Monte Carlo Guidance in Discrete Diffusion
arXiv:2610.20669v1 Announce Type: new
Abstract: Reward-guided discrete diffusion enables test-time alignment with downstream objectives, but applying Sequential Monte Carlo (SMC) guidance at every denoising step is computationally expensive. Active guidance steps require additional reward evaluatio...