AI/ML arXiv cs.AI

Don't Mix Rewards, Mix Policies: Policy Decomposition and Optimization for Multi-Reward RL

Proposes PRISM, a multi-reward RL framework that optimizes standalone positive and negative policies to reduce conflict and alignment tax in LLM post-training.

AI/ML arXiv cs.AI

Tool Specifications Matter: Uncovering and Mitigating Safety Risks in AI Agents

Identifies safety risks in AI agent tool specifications and introduces SafeKeep, an inference-time safeguard that decouples safety judgment from tool execution.

AI/ML arXiv cs.AI

MAGA: Multi-Platform Self-Fusion of GUI Agents via Structured Action Distillation

Introduces MAGA, a method for multi-platform self-fusion of GUI agents via structured action distillation to create a single cross-environment policy.

AI/ML arXiv cs.AI

Beyond Component Testing: Validating Agentic AI Systems

A survey of 257 papers on validating agentic AI systems, emphasizing the need to validate trajectories in context rather than isolated components.

AI/ML arXiv cs.AI

ModelEquivBench: Certifying Multi-Relational Evaluation of LLM-Generated Optimization Models

Presents ModelEquivBench, a multi-relational evaluation system for certifying the equivalence of LLM-generated optimization models.

AI/ML arXiv cs.AI

Beyond Retrieval: Analytic Memory for Multimodal Agents

Introduces AdaMM, a framework that combines retrieval memory with analytic memory for multimodal agents to support complex queries over observations.

AI/ML arXiv cs.AI

Self-Play Meets Skill Evolution: Self-Evolving Search Agents that Pose, Solve, and Remember

Presents SESA, a self-evolving search agent that co-evolves task generation and procedural skill memory through a self-play loop.

AI/ML arXiv cs.AI

Fragility of Value under Imperfect Alignment

This paper examines the risk of AI systems optimizing for imperfect proxies of human values, potentially leading to catastrophic outcomes if optimization pressure is too high.

AI/ML arXiv cs.AI

Identifying Informative Environments for Cognition Parameter Inference via Bayesian Experimental Design

The authors propose a Bayesian Experimental Design (BED) framework to identify the most informative environments for inferring cognitive parameters in computational modeling.

AI/ML arXiv cs.AI

NeSyFS: A Neuro-symbolic Fast-Slow Thinking Framework for LLM Agent under Partial Observability

NeSyFS is a neuro-symbolic framework that uses knowledge graphs and a twisted sequential Monte Carlo algorithm to help LLM agents handle partial observability.

AI/ML arXiv cs.AI

MerchantBench: Benchmarking LLM Agents for Long-Term Coherence in E-Commerce Operations

MerchantBench is a new 365-day simulation benchmark for testing the long-term coherence of LLM agents in complex e-commerce operations.

AI/ML arXiv cs.AI

Scaling Scientific Discovery Environments for Turn-Level Agentic RL

SciDisco is a scalable framework for training scientific discovery agents using process-verifiable environments and turn-level credit assignment.

AI/ML arXiv cs.AI

MMShopBench: A Real-Log Benchmark for Multimodal, Multi-Turn Shopping Agents

MMShopBench introduces a real-log benchmark and an offline shopping sandbox for evaluating multimodal, multi-turn shopping agents.

AI/ML arXiv cs.AI

Evidence-Grounded Constraint Checking in Construction Documents

This research investigates the trade-offs between resolution and breadth when using RAG-based pipelines for evidence-grounded constraint checking in construction documents.

AI/ML arXiv cs.AI

On the Generalization of Steering Vectors for Chain-of-Thought Faithfulness

The study explores how activation steering vectors can improve the faithfulness of Chain-of-Thought reasoning across different LLMs.

AI/ML arXiv cs.AI

A Generalized-Bayes Perspective on Counterfactual Explanations: Posterior-Based Decision-Making and Evaluation

The authors present a Generalized-Bayes perspective on counterfactual explanations, introducing new decision rules for more interpretable ML model outputs.

AI/ML arXiv cs.AI

Harnessing the Wisdom of LLM Crowds through Complementarity-Driven Iterative Collaboration

WILC is a framework for coordinating multiple LLMs through iterative collaboration and complementarity-driven model selection to achieve higher collective intelligence.

Tech Business/VC Hacker News

OpenAI's super PAC is funding AI-generated news site attacking industry critics

OpenAI's super PAC is allegedly funding an AI-generated news site used to attack critics of the AI industry.

Software Engineering Hacker News

Cro – elegant reactive services in Raku

Introduction to Cro, a framework for building elegant reactive services using the Raku programming language.

Software Engineering Hacker News

AI migrated legacy COBOL programs to Java, bugs included

A report on the failure of AI to migrate legacy COBOL programs to Java without introducing bugs.