AI/ML arXiv cs.AI

Your Agent Has a Genome: Sequence-Level Behavioral Analysis and Runtime Governance of LLM-Powered Autonomous Agents

Introduces Base Sequence Analysis for LLM agent behavior and Governor, a runtime intervention system that increases success rates and reduces token costs.

AI/ML arXiv cs.AI

Agentic Retrieval and Reinforcement Learned Equation Chains: A Controlled Generation Framework for Complex and Novel Physics Word Problems

Introduces ARVRE, a framework using reinforcement learning and agentic RAG to generate mathematically valid and complex physics word problems.

AI/ML arXiv cs.AI

Integrating Reasoning and Generalization in Text-to-SQL via Self-Enhanced Fine-Tuning

Presents CoTE-SQL, a method for enhancing Text-to-SQL generation using self-enhanced reasoning traces and error-aware revision.

AI/ML arXiv cs.AI

NeuroSymbolic AI for Legal AI-TRISM: Trustworthy, Reliable, Interpretable, Safe Models

Proposed TRISM framework combining NeuroSymbolic AI with LLMs to improve trust, reliability, and interpretability in legal AI applications.

AI/ML arXiv cs.AI

Towards Next-Generation Healthcare: A Survey of Medical Embodied AI for Perception, Decision-Making, and Action

A comprehensive survey on Medical Embodied AI, focusing on the integration of perception, decision-making, and action in clinical environments.

Cybersecurity Hacker News

I Could've Rickrolled the FIFA World Cup. All I Needed Was My ID

A first-person account of a potential security vulnerability at the FIFA World Cup involving ID badge access.

AI/ML arXiv cs.AI

Reward Hacking in Language Model Agents: Revisiting AI Safety Gridworlds

Research on reward hacking in LLM agents using a text-based evaluation suite to show that proxy-reward failures resist standard mitigations.

AI/ML arXiv cs.AI

Hierarchical Modeling of ICD Codes in EHR Foundation Models

A study on improving EHR foundation models by explicitly incorporating the hierarchical structure of ICD-10-CM diagnosis codes.

AI/ML arXiv cs.AI

Who Drifted: the System or the Judge? Anytime-Valid Attribution in LLM Evaluation Pipelines

Proposed method for anytime-valid attribution in LLM evaluation pipelines to distinguish between product drift and judge model drift.

AI/ML arXiv cs.AI

Towards End-to-End Automation of AI Research

Introduction of 'The AI Scientist', an end-to-end automated system that can generate research ideas, execute experiments, and write scientific manuscripts.

AI/ML arXiv cs.AI

Synthetic Counteradaptation: A Principle of Human-AI Co-evolution

Introduction of the 'synthetic counteradaptation' principle to describe the recursive co-evolution of strategies between humans and AI.

AI/ML arXiv cs.AI

Toward Vibe Medicine: A Self-Evolving Multi-Agent Framework for Clinical Decision Support

VIBEMed is presented as a self-evolving multi-agent framework for clinical decision support that learns from patient outcomes and past failures.

AI/ML arXiv cs.AI

Frame-Conditioned Moral Computation in LLaMA 3.1-8B-Instruct: A Mechanistic Interpretability Audit of Ethical Reasoning

A mechanistic interpretability audit of LLaMA 3.1-8B-Instruct's ethical reasoning, revealing that surface-level prompts often dominate the internal computation.

AI/ML arXiv cs.AI

ToolMenuBench: Benchmarking Tool-Menu Filtering Strategies for Reliable and Efficient LLM Agents

ToolMenuBench is a new benchmark for evaluating how the selection and filtering of tools provided to LLM agents affects reliability and efficiency.

AI/ML arXiv cs.AI

Minimal Oversight: Uncertainty-Aware Governance for Delegated AI Systems

A framework for uncertainty-aware governance in delegated AI systems using the Minimum Sufficient Oversight Principle (MSO).

Other Hacker News

Show HN: Garden of Flowers – an archive of pictorial typography before ASCII art

A showcase of a digital archive featuring pictorial typography from the era before ASCII art.

Cybersecurity Hacker News

Honeypot Design

A discussion on the design and implementation of honeypots for security research and threat detection.

AI/ML arXiv cs.AI

Mask-Proof: An LLM-based Automated Data Curation Pipeline on Mathematical Proofs

Mask-Proof is an LLM-based pipeline for automatically curating and evaluating step-level mathematical reasoning in long proofs.

AI/ML arXiv cs.AI

Feature Attribution in Directed Acyclic Graphs Using Edge Intervention

DAG-SHAP is a new feature attribution method using edge intervention to better capture causal relationships in Directed Acyclic Graphs.

AI/ML arXiv cs.AI

A Formal Framework for Declarative Agentic AI in Business Process Analysis

A formal framework called AGO for declarative Agentic AI used in Business Process Analysis, grounded in set theory and logic.