ROBOMARKET
Stay Informed
Daily coverage from 5892 trusted sources — robotics, AI agents, and industry analysis for the GCC.
Last Updated: 10:00 AM (1h ago)
Auto-refresh every 2 hours
Beyond Right and Wrong: Evaluating Second-order Social Reasoning in Large Language Models
arXiv:2609.05437v1 Announce Type: new Abstract: Previous AI alignment efforts have focused primarily on first-order social norms -- teaching models what is socially acceptable or unacceptable (e.g., `do not steal'). However, social intelligence depends not only on norm recognition, but also on anticipating who will enforce it and how (e.g., public shame or even imprisonment). These second-order expectations, known as metanorms, govern how people respond when social rules are broken. We introduce a novel framework for evaluating metanorm reasoning in Large Language Models (LLMs) along two dimensions: emotional appraisal and behavioral response, and propose new classification tasks, namely, predicting self-regulation in violators, and other-regulation in observers. We release a multi-perspective dataset, NormReact, of 450 norm violation scenarios, hand-annotated for emotions and behavioral responses across norm violators' gender and observers' social closeness. Current LLMs portray a har
AhaBench: Do Agents Learn from Prior Experience? A Benchmark for Long-Horizon Continual Learning
arXiv:2609.05435v1 Announce Type: new Abstract: Modern language agents are expected to operate over long horizons: they ask follow-up questions, reuse worked examples, handle tool feedback, and adapt to delayed consequences. Most evaluations still reset the agent after a prompt or score only the final state of one trajectory. AhaBench asks a more operational question: when a fixed model receives useful experience, does its later behavior improve under a related evaluation condition where the obvious support has been removed, changed, or delayed? The suite contains three components. Aha-Puzzle tests no-hint exploration after solved hidden-state puzzles; Aha-Euler turns Project-Euler-style mathematical ideas into generated taught/held-out tasks with exact validators; and Aha-Vending, an open-source implementation inspired by Vending-Bench, tests whether a simulated vending agent remains profitable while handling delayed feedback and operational incidents. AhaBench reports a three-part sc
Geometry Conditioning in an Embodied SLM: Training Controls and Robustness Diagnostics in a 0.8B Hybrid Model
arXiv:2609.09213v1 Announce Type: new Abstract: We study how physical-state inputs affect a 0.8B hybrid language model adapted for manipulation with 6.2M trainable parameters. Six conditions are trained on three LIBERO-Spatial tasks and evaluated over three seeds and 540 held-out rollouts. Conditioning recurrent decay gates on geometric increments yields 28.9% success, compared with 36.7% when those increments are shuffled during training and 24.4% without explicit object/goal geometry. Both geometry policies receive correct inputs at evaluation. A token adapter using the same increments scores 27.8%; differences vary across seeds and remain inconclusive. Token-clock conditioning scores 11.1%, including one seed that fails to converge. In separate robustness tests, a state-only relative-coordinate policy retains 7/10 success under frame relabeling, whereas all four tested visual policies fall to at most 3/20 after a 5 cm object displacement. These results show no reliable advantage fro
Identifying Habit, Physics, and Nuisance in Robot World Models
arXiv:2609.09210v1 Announce Type: new Abstract: Teleoperated demonstrations are often multimodal even when the underlying dynamics are nearly deterministic given the executed action. We argue that this multimodality typically mixes three factors--operator habit in action selection, shared physics, and observation nuisance--and that entangled next-observation predictors absorb all three. We formalize the split with a structural causal model a=g(h,z,u), z'=f(z,a), o=r(z,c), and test it with complementary interventions: replacing or shuffling actions at fixed state sharply increases next-state error, whereas appearance and camera changes should not; habit-aware reverse scoring improves ranking of feasible pasts without rewriting the dynamics. The associated adaptation rule is to freeze a shared physics readout and update only a thin interface. On StackCube, DROID, and RH20T this rule improves low-shot transfer relative to training from scratch, retains cleaner dynamics under corrupted ada
CriticGen: Generation-Aware Evaluation as Actionable Feedback
arXiv:2609.05439v1 Announce Type: new Abstract: Current evaluation methods for large language models are coarse-grained and decoupled from generation, producing generic explanations that fail to provide actionable feedback for model improvement. We propose CriticGen, a fine-grained, generation-aware evaluation framework that turns evaluation into actionable control for answer improvement. CriticGen first generates sample-specific evaluation dimensions and scoring criteria under high-level categories such as subjective, objective, and self-derived constraints. These criteria then serve as a dynamic rubric for jointly producing a score, a reason, an executable refinement suggestion, and a refined answer. This rubric-conditioned refinement process enables models to diagnose flaws and perform targeted answer improvement. Experimental results show that fine-grained evaluation should be both instance-specific and actionable. CriticGen induces higher-quality rubrics, improving relevance/cover
Getting started with dbt
A practical guide to building, testing, and documenting SQL transformations The post Getting started with dbt appeared first on Towards Data Science.
The Symmetry That Breaks Neural Network Averaging
Understanding permutation symmetry in deep learning, and what it means for weight averaging and model merging The post The Symmetry That Breaks Neural Network Averaging appeared first on Towards Data Science.
When One Process Becomes Too Much: Splitting a Pipeline into MCP Services
How we split a tightly coupled Python pipeline into independently deployable services The post When One Process Becomes Too Much: Splitting a Pipeline into MCP Services appeared first on Towards Data Science.
10 Statistical Traps We Often Overlook
Statistical thinking beyond formulas The post 10 Statistical Traps We Often Overlook appeared first on Towards Data Science.
How to Maximize GPT-6 Astra
My first impressions of OpenAI's new frontier model The post How to Maximize GPT-6 Astra appeared first on Towards Data Science.
The Model Validation Playbook for GenAI: Lessons from Banking
How model validation standards are changing for LLM-based systems: what breaks, what carries over, and how to test output quality The post The Model Validation Playbook for GenAI: Lessons from Banking appeared first on Towards Data Science.
A Beginner’s Guide to World Models
Learn how to simulate reality with Python The post A Beginner’s Guide to World Models appeared first on Towards Data Science.