arXiv AI
Jul 15
Tracing Agentic Failure from the Flow of Success
arXiv:2607. 12747v1 Announce Type: new Abstract: Failure attribution for LLM-based agentic systems, i.
Large language models
Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.
arXiv AI
Jul 15
ReLope: KL-Regularized LoRA Probes for Multimodal LLM Routing
arXiv:2603. 24787v2 Announce Type: replace Abstract: Routing has emerged as a promising strategy for balancing performance and cost in large language model (LLM) systems that combine lightweight models with powerful but expensive large models.
arXiv AI
Jul 15
A Learning-Rate-Gated Failure of GRPO in a Small Language and Vision-Language Model Web Agent: A Controlled Null and Its Mechanism
arXiv:2607. 12640v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards, and Group Relative Policy Optimization (GRPO) in particular, is now run routinely on a supervised checkpoint in the hope of producing a stronger agent.
arXiv AI
Jul 15
Atomic Units of X: The Compression Layer of Intelligence
arXiv:2607. 12634v1 Announce Type: new Abstract: This paper proposes a theoretical framework for understanding intelligence as a process of atomic compression and compositional reuse.
arXiv AI
Jul 15
Do We Really Need Transformers for Global Spatial Information Extraction in Traffic Forecasting?
arXiv:2607. 12462v1 Announce Type: new Abstract: Existing traffic forecasting models commonly focus on extracting spatial dependencies, particularly global spatial information, which characterizes the representations obtained through interactions between each individual node and all nodes across the traffic network.
arXiv AI
Jul 15
The Model Knows Your Project, Not You: Measuring Recognition in LLMs with NameRank
arXiv:2607. 12520v1 Announce Type: new Abstract: What a frontier model recalls about a person or tool from its own weights -- before any retrieval step -- often shapes the first description a human sees, making that parametric corpus presence a measurement problem.
arXiv AI
Jul 15
Measurement Risk in Supervised Financial NLP: Rubric and Metric Sensitivity on JF-ICR
arXiv:2604. 27374v2 Announce Type: replace Abstract: As LLMs become credible readers of earnings calls, investor-relations Q\&A, guidance, and disclosure language, supervised financial NLP benchmarks increasingly function as decision evidence for model selection and deployment.
arXiv AI
Jul 15
Attractor Geometry of Transformer Memory: From Conflict Arbitration to Confident Hallucination
arXiv:2605. 05686v3 Announce Type: replace Abstract: Language models draw on two knowledge sources: facts baked into weights (parametric memory, PM) and information in context (working memory, WM).
arXiv AI
Jul 15
OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks
arXiv:2606. 29537v2 Announce Type: replace Abstract: Existing computer-use benchmarks fail to capture the realism, complexity, and long-horizon demands of real-world computer use, limiting their ability to reveal the limitations of frontier agents.
arXiv AI
Jul 15
TRACE: An Operational Reasoning Schema for Auditable Agentic Commitments
arXiv:2607. 12480v1 Announce Type: new Abstract: This paper defines TRACE (Typed Reasoning And Commitment Evidence): a typed, versioned schema for recording reasoning traces, a reference procedure for writing records against it, and one operating discipline, no durable state change without a record.
arXiv AI
Jul 15
Silent Alarm: A J-Space Protocol for Comparing Danger Recognition Across Models and Quantization Levels
arXiv:2607. 12792v1 Announce Type: cross Abstract: Jailbreak-robustness research typically evaluates safety through generated responses using an LLM-as-judge approach.
arXiv AI
Jul 15
Critic Experience Bank: Self-Evolving Step-Level Confidence Estimation for LLM Agents
arXiv:2607. 12397v1 Announce Type: new Abstract: LLM agents act in external environments where each action changes the state that later decisions condition on, and where a single wrong step can waste interaction budget or trigger irreversible side effects long before the final failure is observed.
arXiv AI
Jul 15
SheetMind: An End-to-End LLM-Powered Multi-Agent Framework for Spreadsheet Automation
arXiv:2506. 12339v2 Announce Type: replace-cross Abstract: We present SheetMind, a modular multi-agent framework powered by large language models (LLMs) for spreadsheet automation via natural language instructions.
arXiv AI
Jul 15
Cost-Governed RAG: Unified Per-Tenant Cost Attribution Across Retrieval and Generation in Multi-Tenant LLM Systems
arXiv:2607. 12188v1 Announce Type: new Abstract: Enterprise Retrieval-Augmented Generation (RAG) deployments face a critical governance gap: while LLM generation cost is metered per token, the retrieval layer - vector memory, similarity compute, and embedding API calls - remains an unattributed shared cost, enabling invisible cross-subsidization among tenants.
arXiv AI
Jul 15
A Threshold Exceedance Framework for CBRN Uplift Evaluation in Frontier Language Models
arXiv:2607. 12200v1 Announce Type: new Abstract: As frontier language models advance, policymakers and model developers need methods for assessing whether model access materially increases a non-expert actor's ability to plan high-consequence Chemical, Biological, Radiological, or Nuclear (CBRN) misuse relative to public tools alone.
arXiv AI
Jul 15
Efficiently Learning Branching Networks for Multitask Algorithmic Reasoning
arXiv:2512. 01113v2 Announce Type: replace-cross Abstract: Algorithmic reasoning -- the ability to perform step-by-step logical inference -- is a synthetic benchmark for evaluating multi-step reasoning abilities, designed for graph neural networks and also for transformer models.
arXiv AI
Jul 15
Operationalising Multi-Dimensional Evaluation for Conversational Agents: A Scalable, Governed Pipeline with Selective Re-evaluation and Model Benchmarking
arXiv:2607. 12085v1 Announce Type: new Abstract: Evaluating retail conversational agents requires methods beyond lexical-overlap metrics to assess intent alignment, factuality, helpfulness, clarity, tone, and overall response quality.
arXiv AI
Jul 15
The Sound of Absence: Audio-Language Embedding Models Struggle with Negation
arXiv:2607. 12290v1 Announce Type: cross Abstract: Audio-language embedding models such as CLAP are widely evaluated on matching present sound events, but rarely on negation.
arXiv AI
Jul 15
Declarative by Design, Assistable Only by Convention: Benchmarking Multi-Agent Frameworks for AI-Assistability
arXiv:2602. 11198v2 Announce Type: replace-cross Abstract: Multi-agent frameworks (MAFs) promise to simplify LLM-driven software development, yet no principled metric captures how well AI coding assistants can generate correct, framework-specific code.
arXiv AI
Jul 15
Self-Regulated Reading with AI Support: An Eight-Week Study with Students
arXiv:2602. 09907v2 Announce Type: replace-cross Abstract: College students increasingly use AI chatbots to support academic reading, yet we lack granular understanding of how these interactions shape their reading experience and cognitive engagement.