Towards Data Science
1d ago
Ten Is Not a Hundred
The number that fooled every hallucination detector The post Ten Is Not a Hundred appeared first on Towards Data Science .
AI safety and alignment
Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
OpenAI Blog
1d ago
Pacing model development in an era of cyber-critical capabilities
OpenAI is strengthening monitoring, alignment, and security for frontier AI models. See how new safeguards are guiding the pace of model development.
arXiv AI
1d ago
Breaking and Defending LLM-Powered Social Media Bot Detection Systems
arXiv:2608. 15893v1 Announce Type: new Abstract: The rise of social media bots poses a persistent threat, enabling misinformation, opinion manipulation, and the erosion of trust in online platforms.
arXiv AI
1d ago
Frontier AI Forecasting Has a Measurement Problem: An Audit of Progress Evidence
arXiv:2608. 14903v1 Announce Type: new Abstract: Quantitative forecasts of frontier artificial intelligence often connect dated targets to trends in benchmark scores, training compute, release time, or expert belief.
arXiv AI
1d ago
UC-PSRO: Utility-Conditioned Policy-Space Response Oracles with a Communication-Dropout Curriculum for Game-Theoretic Course-of-Action Generation in Adversarial Swarms
arXiv:2608. 15372v1 Announce Type: new Abstract: We study generating game-theoretically optimized Courses of Action (COAs) for a Blue UAS swarm against an adaptive Red adversary in a communication-degraded environment, motivated by (but not derived from) a public U.
arXiv AI
1d ago
TRACE: Trajectory Aware Reasoning for Multi-Turn Adversarial Conversation Evaluation
arXiv:2608. 15594v1 Announce Type: new Abstract: Multi-turn jailbreak attacks have emerged as a critical safety threat to LLMs, as harmful objectives are decomposed across a sequence of apparently benign turns to bypass guardrails.
arXiv AI
1d ago
When Do LLMs Apply the Wrong Law? Diagnosing LLM Failures in Temporal Legal Reasoning
arXiv:2608. 14610v1 Announce Type: new Abstract: Legal reasoning tasks such as legal judgment prediction (LJP) require identifying the temporally correct version of the law governing a case -- a capability we term temporal applicable-law determination.
arXiv AI
1d ago
Position: AI Governance Needs ISO-like Interoperability Protocols, Not Just Laws
arXiv:2608. 14568v1 Announce Type: new Abstract: As Artificial Intelligence (AI) systems become deeply integrated into critical global infrastructure, the urgency for robust governance frameworks has intensified.
arXiv AI
1d ago
Beyond Pass@k: Measuring Reliability and Security of Agentic Code Generation
arXiv:2608. 14711v1 Announce Type: new Abstract: AI coding agent benchmarks rank agents with the Chen et al.
arXiv AI
1d ago
MINT: Min-Selection Preference Distillation for Balanced Multi-Objective Alignment
arXiv:2608. 14828v1 Announce Type: new Abstract: Aligning a language agent to several objectives at once is a persistent failure mode of preference-based training: when objectives are combined additively, optimization collapses onto whichever is cheapest to improve and sacrifices the rest, so a support agent learns to sound warm while giving no real help.
arXiv AI
1d ago
Decentralized Federated Learning for Heterogeneous Multi-Task Semantic Communication
arXiv:2608. 15256v1 Announce Type: new Abstract: Collaborative training in distributed semantic communication (DSC) networks typically relies on decentralized federated learning (DFL).
arXiv AI
1d ago
Physiological World Models for Human State Transitions
arXiv:2608. 15309v1 Announce Type: new Abstract: Continuous multimodal sensing now allows human physiology to be observed throughout daily life rather than only during occasional clinical visits.
arXiv AI
1d ago
TwinGridShield: Consequence-Aware Runtime Authorization for LLM Grid-Agent Actions
arXiv:2608. 15391v1 Announce Type: new Abstract: Large language model (LLM)-assisted energy-management tools can translate natural-language context into structured grid commands, but syntactic validity does not imply physical admissibility.
arXiv AI
1d ago
Agent Gym: A Framework for Continuous Evaluation and Evolution of LLM Agents Through Human-in-the-Loop Feedback
arXiv:2608. 15591v1 Announce Type: new Abstract: Large Language Model (LLM) agents deployed in production environments face a fundamental tension: the agent's behavior is frozen at deployment time, while the business rules and edge cases it must handle continue to evolve.
arXiv AI
1d ago
Cross-Domain Industrial Fault Detection by Causal Mechanism Monitoring
arXiv:2608. 14666v1 Announce Type: new Abstract: Unsupervised fault detection in industrial systems is dominated by reconstruction based methods that monitor individual sensor marginal distributions.
arXiv AI
1d ago
Does a Tool Result Carry More Authority Than Plain Text? Three Prospective Studies of False-Claim Adoption in a Synthetic Assignment Task with Claude Opus 5
arXiv:2608. 14992v1 Announce Type: new Abstract: Language-model systems increasingly read from stores they also write to, so a claim that was merely written earlier can return looking retrieved.
arXiv AI
1d ago
OGX: An Open-Source, Vendor-Neutral Generative AI Application Server
arXiv:2608. 14580v1 Announce Type: new Abstract: OGX (Open GenAI Stack) is an open-source AI application server and Python library that implements the APIs of major frontier labs (OpenAI, Anthropic, Google) with pluggable backend providers.
arXiv AI
1d ago
Toward Safe LLM Agents: A Survey of Specification, Verification, and Enforcement
arXiv:2608. 14590v1 Announce Type: new Abstract: LLM agents increasingly perform irreversible real-world actions, including database updates, API calls, file operations, and autonomous use of tools.
arXiv AI
1d ago
When Agentic Executions Fail: Detecting and Localizing Runtime Faults from Telemetry
arXiv:2608. 14680v1 Announce Type: new Abstract: Reliability in LLM-based agentic systems is a property of the whole execution (its tool calls, model calls, guardrails, and inter-agent messages), not of the final answer alone, yet evaluating only task outcomes reveals little about how or why a run fails.
arXiv AI
1d ago
Eigenanalysis framework for autoregressive neural emulators of multi-scale chaotic dynamics
arXiv:2608. 16084v1 Announce Type: new Abstract: Neural autoregressive models have rapidly emerged as powerful emulators of high-dimensional chaotic systems, yet their long-term instability and error growth remain poorly understood, leading to ad-hoc solutions.