arXiv AI
Jul 9
AgentLens: Production-Assessed Trajectory Reviews for Coding Agent Evaluation
arXiv:2607. 06624v1 Announce Type: new Abstract: We present AgentLens, a production-assessed benchmark for interactive code agents.
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 Machine Learning
Jul 9
Multi-Class vs. Multi-Label BERT for CVE-to-CWE Mapping: How Taxonomy Structure Shapes the Errors
arXiv:2607. 07573v1 Announce Type: new Abstract: Assigning Common Weakness Enumeration (CWE) categories to Common Vulnerabilities and Exposures (CVE) records remains an important but largely manual step in vulnerability analysis.
arXiv AI
Jul 9
Diversity Without Fidelity: A Solver-Sampler Mismatch in Multi-Agent LLM Negotiation Simulation
arXiv:2604. 11840v3 Announce Type: replace-cross Abstract: Language models are increasingly used to simulate people: survey respondents, negotiators, stakeholders in policy exercises.
arXiv AI
Jul 9
From Content to Audience: A Multimodal Annotation Framework for Broadcast Television Analytics
arXiv:2603. 26772v2 Announce Type: replace-cross Abstract: Automated semantic annotation of broadcast television content presents distinctive challenges, combining structured audiovisual composition, domain-specific editorial patterns, and strict operational constraints.
arXiv AI
Jul 9
AnyPoC: Universal Proof-of-Concept Test Generation for Scalable LLM-Based Bug Detection
arXiv:2604. 11950v2 Announce Type: replace-cross Abstract: While recent LLM-based agents can identify many candidate bugs in source code, their reports remain static hypotheses that require manual validation, limiting the practicality of automated bug detection.
arXiv AI
Jul 9
Operational Reframing and Approval-Framed Delegation in Multi-Agent LLM Safety
arXiv:2607. 07097v1 Announce Type: new Abstract: Safety evaluations of multi-agent LLM systems often compare a direct prompt with a planner-executor pipeline and report the difference as a single "pipeline effect.
arXiv Machine Learning
Jul 9
MedPMC: A Systematic Framework for Scaling High-Fidelity Medical Multimodal Data for Foundation Models
arXiv:2607. 07673v1 Announce Type: cross Abstract: Medicine is inherently multimodal, requiring clinicians to synthesize information across diverse data streams.
arXiv AI
Jul 9
Framing Instability in LLM Ethical Stance: Auditing Negation Sensitivity in Moral Dilemmas
arXiv:2601. 21433v2 Announce Type: replace Abstract: Language models are increasingly consulted on ethically consequential questions, yet the stance a model expresses may not survive a change in framing.
arXiv Machine Learning
Jul 9
From system models to class models: An in-context learning paradigm
arXiv:2308. 13380v3 Announce Type: replace-cross Abstract: Is it possible to understand the intricacies of a dynamical system not solely from its input/output pattern, but also by observing the behavior of other systems within the same class?
arXiv AI
Jul 9
Exploration of Fast-Slow Latent Recurrence for Train-Short, Test-Long Generalization
arXiv:2604. 01577v3 Announce Type: replace-cross Abstract: We study out of distribution generalization in streaming tasks where models are trained on short sequences but must operate over much longer, unknown horizons under bounded memory.
arXiv Machine Learning
Jul 9
Efficient Long-Horizon Learning for Learned Optimization
arXiv:2607. 06772v1 Announce Type: new Abstract: Learned optimization aims to improve upon hand-designed optimizers (e.
arXiv AI
Jul 9
Healthier LLMs: Retrieval-Augmented Generation for Public Health Question Answering
arXiv:2607. 06641v1 Announce Type: cross Abstract: Large language models (LLMs) achieve promising results on medical question answering benchmarks, yet their use in public health is constrained by hallucinations and the rapid evolution of official guidance.
arXiv AI
Jul 9
Entropy Pacing Policy Optimization for Multi-Task Agentic Reinforcement Learning
arXiv:2607. 07178v1 Announce Type: cross Abstract: Recent breakthroughs of Reinforcement Learning (RL) have highlighted its potential for complex agentic Large Language Model (LLM) tasks.
arXiv AI
Jul 9
Riemannian Geometry for Pre-trained Language Model Embeddings
arXiv:2607. 07047v1 Announce Type: cross Abstract: Understanding the geometric structure of pre-trained language model embeddings matters for interpretability and safety.
arXiv AI
Jul 9
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems
arXiv:2607. 06807v1 Announce Type: cross Abstract: While enabling effective collaboration on complex tasks, LLM-based Multi-Agent Systems (MAS) face critical security challenges due to vulnerabilities at the agent and interaction levels.
arXiv AI
Jul 9
Comprehensive Evaluation of Large Language Model Responses: A Multi-Factor Scoring System
arXiv:2607. 06940v1 Announce Type: cross Abstract: The remarkable performance of large language models (LLMs) in linguistic tasks underscores an urgent need for comprehensive evaluation of their response quality.
arXiv AI
Jul 9
Health System Scale Semantic Search Across Unstructured Clinical Notes
arXiv:2604. 25605v2 Announce Type: replace-cross Abstract: Introduction: Semantic search, which retrieves documents based on conceptual similarity rather than keywords, offers advantages for retrieval of clinical information.
arXiv AI
Jul 9
Reason Less, Verify More: Deterministic Gates Recover a Silent Policy-Violation Failure Mode in Tool-Using LLM Agents
arXiv:2607. 07405v1 Announce Type: new Abstract: Tool-using LLM agents can violate the very policies they are deployed to enforce while appearing to complete the task successfully.
arXiv AI
Jul 9
HIVE: Understanding Post-Hallucination Reasoning in Vision Language Models
arXiv:2607. 07507v1 Announce Type: cross Abstract: Hallucinations in vision language models (VLMs) are commonly treated as semantic errors, yet they often arise from partial or ambiguous visual evidence.
arXiv Machine Learning
Jul 9
PALS: Percentile-Aware Layerwise Sparsity for LLM Pruning
arXiv:2607. 07557v1 Announce Type: cross Abstract: One-shot pruning methods like Wanda and SparseGPT apply the same sparsity ratio to every layer of a transformer, ignoring known variation in layer importance.