Semantic XPath: Structured Agentic Memory Access for Conversational AI
arXiv:2603.01160v1 Announce Type: new Abstract: Conversational AI (ConvAI) agents increasingly maintain structured memory to support long-term, task-oriented interactions. In-context memory approaches append the growing history to the model input, which scales poorly under context-window limits. RAG-based methods retrieve request-relevant information,...
Incremental LTLf Synthesis
arXiv:2603.01201v1 Announce Type: new Abstract: In this paper, we study incremental LTLf synthesis -- a form of reactive synthesis where the goals are given incrementally while in execution. In other words, the protagonist agent is already executing a strategy for...
How Well Does Agent Development Reflect Real-World Work?
arXiv:2603.01203v1 Announce Type: new Abstract: AI agents are increasingly developed and evaluated on benchmarks relevant to human work, yet it remains unclear how representative these benchmarking efforts are of the labor market as a whole. In this work, we systematically...
From Global to Local: Learning Context-Aware Graph Representations for Document Classification and Summarization
arXiv:2603.00021v1 Announce Type: new Abstract: This paper proposes a data-driven method to automatically construct graph-based document representations. Building upon the recent work of Bugue\~no and de Melo (2025), we leverage the dynamic sliding-window attention module to effectively capture local and...
Noise reduction in BERT NER models for clinical entity extraction
arXiv:2603.00022v1 Announce Type: new Abstract: Precision is of utmost importance in the realm of clinical entity extraction from clinical notes and reports. Encoder Models fine-tuned for Named Entity Recognition (NER) are an efficient choice for this purpose, as they don't...
TAB-PO: Preference Optimization with a Token-Level Adaptive Barrier for Token-Critical Structured Generation
arXiv:2603.00025v1 Announce Type: new Abstract: Direct Preference Optimization is an offline post-SFT method for aligning language models from preference pairs, with strong results in instruction following and summarization. However, DPO's sequence-level implicit reward can be brittle for token-critical structured prediction...
Stepwise Penalization for Length-Efficient Chain-of-Thought Reasoning
arXiv:2603.00296v1 Announce Type: new Abstract: Large reasoning models improve with more test-time computation, but often overthink, producing unnecessarily long chains-of-thought that raise cost without improving accuracy. Prior reinforcement learning approaches typically rely on a single outcome reward with trajectory-level length...
From Prerequisites to Predictions: Validating a Geometric Hallucination Taxonomy Through Controlled Induction
arXiv:2603.00307v1 Announce Type: new Abstract: We test whether a geometric hallucination taxonomy -- classifying failures as center-drift (Type~1), wrong-well convergence (Type~2), or coverage gaps (Type~3) -- can distinguish hallucination types through controlled induction in GPT-2. Using a two-level statistical design...
Federated Inference: Toward Privacy-Preserving Collaborative and Incentivized Model Serving
arXiv:2603.02214v1 Announce Type: new Abstract: Federated Inference (FI) studies how independently trained and privately owned models can collaborate at inference time without sharing data or model parameters. While recent work has explored secure and distributed inference from disparate perspectives, a...
Can machines be uncertain?
arXiv:2603.02365v1 Announce Type: new Abstract: The paper investigates whether and how AI systems can realize states of uncertainty. By adopting a functionalist and behavioral perspective, it examines how symbolic, connectionist and hybrid architectures make room for uncertainty. The paper distinguishes...
COOL-MC: Verifying and Explaining RL Policies for Platelet Inventory Management
arXiv:2603.02396v1 Announce Type: new Abstract: Platelets expire within five days. Blood banks face uncertain daily demand and must balance ordering decisions between costly wastage from overstocking and life-threatening shortages from understocking. Reinforcement learning (RL) can learn effective ordering policies for...
VL-KGE: Vision-Language Models Meet Knowledge Graph Embeddings
arXiv:2603.02435v1 Announce Type: new Abstract: Real-world multimodal knowledge graphs (MKGs) are inherently heterogeneous, modeling entities that are associated with diverse modalities. Traditional knowledge graph embedding (KGE) methods excel at learning continuous representations of entities and relations, yet they are typically...
LiveAgentBench: Comprehensive Benchmarking of Agentic Systems Across 104 Real-World Challenges
arXiv:2603.02586v1 Announce Type: new Abstract: As large language models grow more capable, general AI agents have become increasingly prevalent in practical applications. However, existing benchmarks face significant limitations, failing to represent real-world user tasks accurately. To address this gap, we...
SorryDB: Can AI Provers Complete Real-World Lean Theorems?
arXiv:2603.02668v1 Announce Type: new Abstract: We present SorryDB, a dynamically-updating benchmark of open Lean tasks drawn from 78 real world formalization projects on GitHub. Unlike existing static benchmarks, often composed of competition problems, hillclimbing the SorryDB benchmark will yield tools...
EvoSkill: Automated Skill Discovery for Multi-Agent Systems
arXiv:2603.02766v1 Announce Type: new Abstract: Coding agents are increasingly used as general-purpose problem solvers, but their flexibility does not by itself confer the domain expertise needed for specialized tasks. Recent work addresses this through \textit{agent skills}: reusable workflows, and code,...
Agentified Assessment of Logical Reasoning Agents
arXiv:2603.02788v1 Announce Type: new Abstract: We present a framework for evaluating and benchmarking logical reasoning agents when assessment itself must be reproducible, auditable, and robust to execution failures. Building on agentified assessment, we use an assessor agent to issue tasks,...
Retrievit: In-context Retrieval Capabilities of Transformers, State Space Models, and Hybrid Architectures
arXiv:2603.02874v1 Announce Type: new Abstract: Transformers excel at in-context retrieval but suffer from quadratic complexity with sequence length, while State Space Models (SSMs) offer efficient linear-time processing but have limited retrieval capabilities. We investigate whether hybrid architectures combining Transformers and...
SpatialText: A Pure-Text Cognitive Benchmark for Spatial Understanding in Large Language Models
arXiv:2603.03002v1 Announce Type: new Abstract: Genuine spatial reasoning relies on the capacity to construct and manipulate coherent internal spatial representations, often conceptualized as mental models, rather than merely processing surface linguistic associations. While large language models exhibit advanced capabilities across...
AI Space Physics: Constitutive boundary semantics for open AI institutions
arXiv:2603.03119v1 Announce Type: new Abstract: Agentic AI deployments increasingly behave as persistent institutions rather than one-shot inference endpoints: they accumulate state, invoke external tools, coordinate multiple runtimes, and modify their future authority surface over time. Existing governance language typically specifies...
FEAST: Retrieval-Augmented Multi-Hierarchical Food Classification for the FoodEx2 System
arXiv:2603.03176v1 Announce Type: new Abstract: Hierarchical text classification (HTC) and extreme multi-label classification (XML) tasks face compounded challenges from complex label interdependencies, data sparsity, and extreme output dimensions. These challenges are exemplified in the European Food Safety Authority's FoodEx2 system-a...
No Memorization, No Detection: Output Distribution-Based Contamination Detection in Small Language Models
arXiv:2603.03203v1 Announce Type: new Abstract: CDD, or Contamination Detection via output Distribution, identifies data contamination by measuring the peakedness of a model's sampled outputs. We study the conditions under which this approach succeeds and fails on small language models ranging...
NeuroSkill(tm): Proactive Real-Time Agentic System Capable of Modeling Human State of Mind
arXiv:2603.03212v1 Announce Type: new Abstract: Real-time proactive agentic system, capable of modeling Human State of Mind, using foundation EXG model and text embeddings model, running fully offline on the edge. Unlike all previously known systems, the NeuroSkill(tm) system leverages SKILL.md...
Density-Guided Response Optimization: Community-Grounded Alignment via Implicit Acceptance Signals
arXiv:2603.03242v1 Announce Type: new Abstract: Language models deployed in online communities must adapt to norms that vary across social, cultural, and domain-specific contexts. Prior alignment approaches rely on explicit preference supervision or predefined principles, which are effective for well-resourced settings...
A Zipf-preserving, long-range correlated surrogate for written language and other symbolic sequences
arXiv:2603.02213v1 Announce Type: new Abstract: Symbolic sequences such as written language and genomic DNA display characteristic frequency distributions and long-range correlations extending over many symbols. In language, this takes the form of Zipf's law for word frequencies together with persistent...
Universal Conceptual Structure in Neural Translation: Probing NLLB-200's Multilingual Geometry
arXiv:2603.02258v1 Announce Type: new Abstract: Do neural machine translation models learn language-universal conceptual representations, or do they merely cluster languages by surface similarity? We investigate this question by probing the representation geometry of Meta's NLLB-200, a 200-language encoder-decoder Transformer, through...
Characterizing Memorization in Diffusion Language Models: Generalized Extraction and Sampling Effects
arXiv:2603.02333v1 Announce Type: new Abstract: Autoregressive language models (ARMs) have been shown to memorize and occasionally reproduce training data verbatim, raising concerns about privacy and copyright liability. Diffusion language models (DLMs) have recently emerged as a competitive alternative, yet their...
RO-N3WS: Enhancing Generalization in Low-Resource ASR with Diverse Romanian Speech Benchmarks
arXiv:2603.02368v1 Announce Type: new Abstract: We introduce RO-N3WS, a benchmark Romanian speech dataset designed to improve generalization in automatic speech recognition (ASR), particularly in low-resource and out-of-distribution (OOD) conditions. RO-N3WS comprises over 126 hours of transcribed audio collected from broadcast...
GLoRIA: Gated Low-Rank Interpretable Adaptation for Dialectal ASR
arXiv:2603.02464v1 Announce Type: new Abstract: Automatic Speech Recognition (ASR) in dialect-heavy settings remains challenging due to strong regional variation and limited labeled data. We propose GLoRIA, a parameter-efficient adaptation framework that leverages metadata (e.g., coordinates) to modulate low-rank updates in...
CoDAR: Continuous Diffusion Language Models are More Powerful Than You Think
arXiv:2603.02547v1 Announce Type: new Abstract: We study why continuous diffusion language models (DLMs) have lagged behind discrete diffusion approaches despite their appealing continuous generative dynamics. Under a controlled token--recovery study, we identify token rounding, the final projection from denoised embeddings...
GPUTOK: GPU Accelerated Byte Level BPE Tokenization
arXiv:2603.02597v1 Announce Type: new Abstract: As large language models move toward million-token context windows, CPU tokenizers become a major slowdown because they process text one step at a time while powerful GPUs sit unused. We built a GPU-based byte-level BPE...