11 articles tagged with #decision-theory. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.
A research paper identifies fundamental limitations in current AI agent design when handling multiple conflicting objectives simultaneously. The study proposes that optimization-based AI agents cannot properly identify incommensurable choices and lack autonomy to resolve them, creating alignment and reliability problems that standard safeguards like human oversight cannot fully address.
Researchers prove 'selection theorems' showing that AI agents achieving low regret on prediction tasks must develop internal predictive models and belief states. The work demonstrates that structured internal representations are mathematically necessary, not just helpful, for competent decision-making under uncertainty.
Researchers have developed a new decision-theoretic framework to detect steganographic capabilities in large language models, which could help identify when AI systems are hiding information to evade oversight. The method introduces 'generalized V-information' and a 'steganographic gap' measure to quantify hidden communication without requiring reference distributions.
A theoretical paper examines conditions under which optimizing a proxy utility function produces harmful outcomes, raising fundamental questions about the applicability of decision theory to real-world systems. The research challenges assumptions underlying many optimization approaches used in AI and economic modeling.
Researchers present the first implementation of infra-Bayesian reinforcement learning, a decision-theoretic framework that handles model misspecification and adversarial uncertainty better than classical RL. The approach demonstrates lower worst-case regret in environments with Knightian uncertainty and achieves optimal strategies in game-theoretic problems like Newcomb's paradox.
Researchers propose Bayesian Selective Latent Inference (BSLI), a machine learning method that uses wastewater surveillance data to monitor influenza spread in communities before clinical cases are reported. The system intelligently decides whether additional data sources are needed or if abstention is appropriate, improving disease monitoring accuracy while managing data acquisition costs.
Researchers have developed a formal decision-theoretic framework that quantifies the value of perception, prediction, communication, and common sense in autonomous decision-making systems. The work reveals that perception alone can have negative value, while combined perception-prediction and standalone prediction always yield non-negative returns, with applications to autonomous systems design and cognitive science.
Researchers present a framework for aligning AI agent behavior with human moral values by accounting for contextual factors when aggregating diverse moral perspectives. The work reveals that traditional aggregation mechanisms violate the weak Pareto principle due to contextual dependencies, analogous to Simpson's paradox, highlighting fundamental limitations in current moral uncertainty approaches.
Researchers develop a decision-theoretic framework for optimizing LLM cascades, where cheaper models defer to expensive ones on low-confidence queries. Testing across five benchmarks reveals that cascade performance is fundamentally limited by structural costs rather than routing sophistication, with simpler router-based approaches often outperforming optimized cascade policies.
A research position paper argues that agentic AI systems should incorporate Bayesian decision theory at their orchestration layer to improve decision-making under uncertainty. Rather than making LLMs themselves Bayesian, the framework proposes applying Bayesian principles to the control systems that coordinate multiple LLMs and tools, enabling better belief maintenance and resource allocation.
Researchers propose VEROIC, a framework for optimizing inference costs in black-box LLM services by dynamically deciding when to allocate additional computation. The system uses partially observable reliability signals to balance response quality against computational expenses, achieving better cost-efficiency trade-offs than existing approaches.
