The classic paradigm of language identification in the limit models learning as a game between an adversary, who reveals strings from an unknown target language, and a learner tasked with identifying that language. The recently introduced framework of language generation in the limit shifted the objective to better reflect modern language modeling, requiring the learner to produce valid, unseen strings from the target language. Related work highlighted a fundamental tension: a broad coverage of the target often comes at the cost of validity. We introduce a new notion of precision and recast this problem as the classic recall-precision trade-off. We analyze generation in the limit under varying constraints on enumeration, novelty, and validity, aimed at reflecting settings closer to those…

This research demonstrates how emotional valence influences the order-dependent structure of children's recognition memory. Correct recall of a sequence of emotionally-valenced toys depended not only on the valence of the toy itself but also on the valence of toys shown before and after it. While standard psychological models show low accuracy, a classical tensor network model incorporating valence achieves 77.98% accuracy, highlighting the value of quantum-inspired methods for modelling order-dependent phenomena like emotional memory. The study also introduces a novel protocol for exploring emotional temporal memory in children.

This paper proposes an end-to-end agentic pipeline combining deep time-series forecasting, variational anomaly detection, and LLM reasoning to generate prioritized, actionable maintenance recommendations for office building appliance-level energy monitoring. The system uses a hybrid SSA-LSTM forecasting model and per-appliance LSTM VAE with attention for anomaly detection, with a three-stage LangChain pipeline (Context, Diagnosis, Report agents) featuring dynamic retrieval. Evaluated on a 16-scenario benchmark, the best backend scores 90.4/100 and a local 7B model passes all scenarios.

A new paper applies singular learning theory to deep monomial networks, showing that critical points correspond to subnetworks, providing a mathematical explanation for neural networks' implicit bias towards simpler functions.

Proposes Counterfactual Residual Data Augmentation (CRDA) for tabular regression, leveraging residual invariance under feature perturbations to generate realistic training samples. Experiments show average MSE reduction of 22.9% for MLP and 6.4% for XGBoost, outperforming existing methods.

Classical universal approximation theorems ensure sigmoidal MLPs can represent any function, but do not guide weight initialization to encode data geometry. This paper proposes S-GAI, a spectral geometry-aware initialization framework for one-hidden-layer sigmoidal MLPs. It uses SVD to estimate class-wise spectral geometry from images: mean, principal directions, and spectral scales. An energy threshold selects retained directions, each represented by two sigmoid gates. These class-specific gates form a shared hidden layer initialized from the training set. Experiments on MNIST, Fashion-MNIST, and CIFAR-10 show S-GAI yields more informative hidden states than Xavier initialization, with comparable final accuracy under full training. Freezing the hidden layer and training only the output l…

A novel online distributed sensing framework combining partial domain knowledge with deep neural networks for latent state estimation without requiring noise statistics. The proposed CA-NKCF outperforms traditional filters and model-free DNNs across linear, chaotic, and wireless environments, demonstrating robustness to model misspecification.

This position paper argues that reinforcement learning researchers often conflate two distinct uses of simulators: solving the simulator as an end in itself, and using it as a proxy for real-world deployment. Through experiments and examples, the authors show that failing to distinguish these settings can lead to misleading conclusions, and call for clearer empirical practices.

A preprint proves that in a mesh of sovereign agents without central coordination, the substrate for each agent must belong to the continuous-time liquid class to optimally process irregular, asynchronous observations. Two necessary conditions are identified: an adaptive timescale and sensitivity to elapsed inter-arrival times, which scale cannot compensate.

Existing image-generation benchmarks fail to assess the usability of scientific figures. SciDraw-Bench introduces 32 tasks across 8 figure types and 10 disciplines, with a four-dimensional evaluation protocol. Experiments show that a domain-specific system, SciDraw AI, outperforms general-purpose models across all dimensions, while text fidelity remains the hardest challenge.

This paper uses evolutionary game theory to model when a harm-minimizing AI agent can displace an approval-seeking (RLHF) agent in a competitive market, and whether that policy suffices to prevent community harm. It shows adoption is favored under certain prior distributions, a critical adoption level exists, and self-audit alone is insufficient without alignment of values and proper evaluation timeframe.

Critic-free RL with verifiable rewards (RLVR) like GRPO avoids training a value function but can be unstable when all rollouts in a group receive identical rewards. BV-Blend stabilizes advantage estimation by combining prompt-local statistics with historical moments from semantic clusters, using a confidence weight derived from a standard error of the mean proxy. Experiments show improved stability and performance on verifiable reasoning benchmarks.

COMPASS is the first unified multimodal framework that grounds composition-intent control in a single system, using a shared expert token τ_c for both perception and generation. It injects composition expertise into an MoE backbone, distills intent into τ_c, and reuses it as a conditioning signal for layout control. The companion Comp-11 dataset features an 11-class taxonomy and reasoning-augmented annotations. Experiments show significant improvements in composition understanding and generation consistency.

Researchers introduce ATHENA-R1, an AI agent trained via reinforcement learning to perform treatment reasoning across 212 biomedical tools. It outperforms GPT-5 on benchmarks and is preferred by experts and physicians.

VirtueMap is a framework that profiles Large Language Models using Aristotelian virtue ethics. It presents seven general ethical dilemmas, each with five possible responses, and asks humans or LLMs to rank them by virtue. Reference orderings are validated by over 100 respondents with at least 95% agreement. Applied to nine LLM families, it finds 90.3% mean rank consistency, with largest differences in Courage, Temperance, and Justice.

Current methods to enhance LLM reasoning, such as Chain-of-Thought and "Wait" prompts, mainly encourage models to think more but often fail to guide them toward truth. This paper investigates the geometry of truth within reasoning chains and proposes DynaSteer, a dynamic representation editing framework. It uses pattern clustering and Fisher-LDA to purify truth and dynamically monitors lookahead entropy to selectively steer and roll back trajectories, achieving strong results on MATH benchmarks and out-of-domain coding tasks.

IMCBench is a new benchmark for evaluating multimodal LLMs in image-grounded medical conversations. It combines real clinical images with synthetic patient profiles to simulate multi-turn doctor-patient interactions, assessing safety, accuracy, and appropriate use of uncertainty. Results show Claude Opus 4.6 leads with 3.61/5, but all models degrade in safety for malignant or rare conditions, and both visual input and EHR context are crucial for safe guidance.

Researchers introduce GPTNT, a benchmark built on the cooperative game Keep Talking and Nobody Explodes, to evaluate multimodal AI agents in real-time collaboration. Tests reveal that state-of-the-art models fail to defuse a single bomb in real time, unlike human players. The benchmark separates collaboration from memorized solutions by controlling access to the instruction manual and partner, and identifies critical weaknesses in state tracking, time-pressured action, ambiguity handling, and error recovery.

A new method called the 'capability slice' bridges the gap between evaluation and data in LLM pre-training, enabling targeted data interventions from benchmark failures. Tested on two case studies, it correctly distinguished a masked loss artifact from a genuine data issue.

Researchers introduce RSEA, a recursive self-evolving agent that improves LLM agents by evolving a compact natural-language state without weight updates. Using a strict held-out selection gate, RSEA outperforms baselines on some benchmarks while maintaining safety against performance collapse. The study finds no universally best artifact and warns against unguarded context evolution.