Toward Scalable Verifiable Reward: Proxy State-Based Evaluation for Multi-turn Tool-Calling LLM Agents
arXiv:2602.16246v1 Announce Type: new Abstract: Interactive large language model (LLM) agents operating via multi-turn dialogue and multi-step tool calling are increasingly used in production. Benchmarks for these agents must both reliably compare models and yield on-policy training data. Prior agentic...
Multi-agent cooperation through in-context co-player inference
arXiv:2602.16301v1 Announce Type: new Abstract: Achieving cooperation among self-interested agents remains a fundamental challenge in multi-agent reinforcement learning. Recent work showed that mutual cooperation can be induced between "learning-aware" agents that account for and shape the learning dynamics of their...
Verifiable Semantics for Agent-to-Agent Communication
arXiv:2602.16424v1 Announce Type: new Abstract: Multiagent AI systems require consistent communication, but we lack methods to verify that agents share the same understanding of the terms used. Natural language is interpretable but vulnerable to semantic drift, while learned protocols are...
Causally-Guided Automated Feature Engineering with Multi-Agent Reinforcement Learning
arXiv:2602.16435v1 Announce Type: new Abstract: Automated feature engineering (AFE) enables AI systems to autonomously construct high-utility representations from raw tabular data. However, existing AFE methods rely on statistical heuristics, yielding brittle features that fail under distribution shift. We introduce CAFE,...
EdgeNav-QE: QLoRA Quantization and Dynamic Early Exit for LAM-based Navigation on Edge Devices
arXiv:2602.15836v1 Announce Type: cross Abstract: Large Action Models (LAMs) have shown immense potential in autonomous navigation by bridging high-level reasoning with low-level control. However, deploying these multi-billion parameter models on edge devices remains a significant challenge due to memory constraints...
Language Model Representations for Efficient Few-Shot Tabular Classification
arXiv:2602.15844v1 Announce Type: cross Abstract: The Web is a rich source of structured data in the form of tables, from product catalogs and knowledge bases to scientific datasets. However, the heterogeneity of the structure and semantics of these tables makes...
Do Personality Traits Interfere? Geometric Limitations of Steering in Large Language Models
arXiv:2602.15847v1 Announce Type: cross Abstract: Personality steering in large language models (LLMs) commonly relies on injecting trait-specific steering vectors, implicitly assuming that personality traits can be controlled independently. In this work, we examine whether this assumption holds by analysing the...
Artificial Intelligence and Justice in Family Law: Addressing Bias and Promoting Fairness
Artificial Intelligence (AI) plays a crucial role in the legal field today, carrying out processes such as predictive analysis, data interpretation, and decision making. AI is valued for its efficiency and accuracy along with its affordability. However, one problem that...
Transformative Potential of AI in Healthcare: Definitions, Applications, and Navigating the Ethical Landscape and Public Perspectives
Artificial intelligence (AI) has emerged as a crucial tool in healthcare with the primary aim of improving patient outcomes and optimizing healthcare delivery. By harnessing machine learning algorithms, natural language processing, and computer vision, AI enables the analysis of complex...
6 days left to lock in the lowest TechCrunch Disrupt 2026 rates
Super Early Bird pricing for TechCrunch Disrupt 2026 ends February 27 at 11:59 p.m. PT. That means you have just 6 days left to secure up to $680 of ticket savings.
Narrative Theory-Driven LLM Methods for Automatic Story Generation and Understanding: A Survey
arXiv:2602.15851v1 Announce Type: cross Abstract: Applications of narrative theories using large language models (LLMs) deliver promising use-cases in automatic story generation and understanding tasks. Our survey examines how natural language processing (NLP) research engages with fields of narrative studies, and...
A Lightweight Explainable Guardrail for Prompt Safety
arXiv:2602.15853v1 Announce Type: cross Abstract: We propose a lightweight explainable guardrail (LEG) method for the classification of unsafe prompts. LEG uses a multi-task learning architecture to jointly learn a prompt classifier and an explanation classifier, where the latter labels prompt...
Decoupling Strategy and Execution in Task-Focused Dialogue via Goal-Oriented Preference Optimization
arXiv:2602.15854v1 Announce Type: cross Abstract: Large language models show potential in task-oriented dialogue systems, yet existing training methods often rely on token-level likelihood or preference optimization, which poorly align with long-horizon task success. To address this, we propose Goal-Oriented Preference...
Kalman-Inspired Runtime Stability and Recovery in Hybrid Reasoning Systems
arXiv:2602.15855v1 Announce Type: cross Abstract: Hybrid reasoning systems that combine learned components with model-based inference are increasingly deployed in tool-augmented decision loops, yet their runtime behavior under partial observability and sustained evidence mismatch remains poorly understood. In practice, failures often...
Rethinking Soft Compression in Retrieval-Augmented Generation: A Query-Conditioned Selector Perspective
arXiv:2602.15856v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) effectively grounds Large Language Models (LLMs) with external knowledge and is widely applied to Web-related tasks. However, its scalability is hindered by excessive context length and redundant retrievals. Recent research on soft...
Not the Example, but the Process: How Self-Generated Examples Enhance LLM Reasoning
arXiv:2602.15863v1 Announce Type: cross Abstract: Recent studies have shown that Large Language Models (LLMs) can improve their reasoning performance through self-generated few-shot examples, achieving results comparable to manually curated in-context examples. However, the underlying mechanism behind these gains remains unclear,...
NLP Privacy Risk Identification in Social Media (NLP-PRISM): A Survey
arXiv:2602.15866v1 Announce Type: cross Abstract: Natural Language Processing (NLP) is integral to social media analytics but often processes content containing Personally Identifiable Information (PII), behavioral cues, and metadata raising privacy risks such as surveillance, profiling, and targeted advertising. To systematically...
Playing With AI: How Do State-Of-The-Art Large Language Models Perform in the 1977 Text-Based Adventure Game Zork?
arXiv:2602.15867v1 Announce Type: cross Abstract: In this positioning paper, we evaluate the problem-solving and reasoning capabilities of contemporary Large Language Models (LLMs) through their performance in Zork, the seminal text-based adventure game first released in 1977. The game's dialogue-based structure...
Genetic Generalized Additive Models
arXiv:2602.15877v1 Announce Type: cross Abstract: Generalized Additive Models (GAMs) balance predictive accuracy and interpretability, but manually configuring their structure is challenging. We propose using the multi-objective genetic algorithm NSGA-II to automatically optimize GAMs, jointly minimizing prediction error (RMSE) and a...
IT-OSE: Exploring Optimal Sample Size for Industrial Data Augmentation
arXiv:2602.15878v1 Announce Type: cross Abstract: In industrial scenarios, data augmentation is an effective approach to improve model performance. However, its benefits are not unidirectionally beneficial. There is no theoretical research or established estimation for the optimal sample size (OSS) in...
NeuroSleep: Neuromorphic Event-Driven Single-Channel EEG Sleep Staging for Edge-Efficient Sensing
arXiv:2602.15888v1 Announce Type: cross Abstract: Reliable, continuous neural sensing on wearable edge platforms is fundamental to long-term health monitoring; however, for electroencephalography (EEG)-based sleep monitoring, dense high-frequency processing is often computationally prohibitive under tight energy budgets. To address this bottleneck,...
Evidence for Daily and Weekly Periodic Variability in GPT-4o Performance
arXiv:2602.15889v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used in research both as tools and as objects of investigation. Much of this work implicitly assumes that LLM performance under fixed conditions (identical model snapshot, hyperparameters, and prompt)...
Surrogate Modeling for Neutron Transport: A Neural Operator Approach
arXiv:2602.15890v1 Announce Type: cross Abstract: This work introduces a neural operator based surrogate modeling framework for neutron transport computation. Two architectures, the Deep Operator Network (DeepONet) and the Fourier Neural Operator (FNO), were trained for fixed source problems to learn...
Egocentric Bias in Vision-Language Models
arXiv:2602.15892v1 Announce Type: cross Abstract: Visual perspective taking--inferring how the world appears from another's viewpoint--is foundational to social cognition. We introduce FlipSet, a diagnostic benchmark for Level-2 visual perspective taking (L2 VPT) in vision-language models. The task requires simulating 180-degree...
Doc-to-LoRA: Learning to Instantly Internalize Contexts
arXiv:2602.15902v1 Announce Type: cross Abstract: Long input sequences are central to in-context learning, document understanding, and multi-step reasoning of Large Language Models (LLMs). However, the quadratic attention cost of Transformers makes inference memory-intensive and slow. While context distillation (CD) can...
Fairness, accountability and transparency: notes on algorithmic decision-making in criminal justice
AbstractOver the last few years, legal scholars, policy-makers, activists and others have generated a vast and rapidly expanding literature concerning the ethical ramifications of using artificial intelligence, machine learning, big data and predictive software in criminal justice contexts. These concerns...
AIdentifyAGE Ontology for Decision Support in Forensic Dental Age Assessment
arXiv:2602.16714v1 Announce Type: new Abstract: Age assessment is crucial in forensic and judicial decision-making, particularly in cases involving undocumented individuals and unaccompanied minors, where legal thresholds determine access to protection, healthcare, and judicial procedures. Dental age assessment is widely recognized...
Simple Baselines are Competitive with Code Evolution
arXiv:2602.16805v1 Announce Type: new Abstract: Code evolution is a family of techniques that rely on large language models to search through possible computer programs by evolving or mutating existing code. Many proposed code evolution pipelines show impressive performance but are...
Node Learning: A Framework for Adaptive, Decentralised and Collaborative Network Edge AI
arXiv:2602.16814v1 Announce Type: new Abstract: The expansion of AI toward the edge increasingly exposes the cost and fragility of cen- tralised intelligence. Data transmission, latency, energy consumption, and dependence on large data centres create bottlenecks that scale poorly across heterogeneous,...
IndicJR: A Judge-Free Benchmark of Jailbreak Robustness in South Asian Languages
arXiv:2602.16832v1 Announce Type: new Abstract: Safety alignment of large language models (LLMs) is mostly evaluated in English and contract-bound, leaving multilingual vulnerabilities understudied. We introduce \textbf{Indic Jailbreak Robustness (IJR)}, a judge-free benchmark for adversarial safety across 12 Indic and South...