#multi-objective-learning News & Analysis

5 articles tagged with #multi-objective-learning. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

5 articles

AINeutralarXiv – CS AI · Jun 56/10

🧠

When Gradients Collide: Failure Modes of Multi-Objective Prompt Optimization for LLM Judges

Researchers identify critical failure modes in multi-objective prompt optimization for LLM judges, finding that jointly optimizing across multiple evaluation criteria reduces gradient task-focus by 59% and combining single-objective prompts degrades performance by 27%. The study reveals fundamental limitations in extending textual gradient methods to multi-criteria scenarios, constraining practical applications of automated LLM judge customization.

AINeutralarXiv – CS AI · Jun 26/10

🧠

Learning to Construct Practical Agentic Systems

Researchers propose a practical framework for building LLM-based agentic systems that prioritizes simplicity, cost predictability, and controllability over maximum optimization. The framework uses modular "pseudo-tools" and fixed workflows, demonstrating that hand-engineered agents often outperform dynamically-planned systems in production environments.

AINeutralarXiv – CS AI · Jun 26/10

🧠

Simultaneous Multi-objective Alignment Across Verifiable and Non-verifiable Rewards

Researchers propose MAHALO, a framework for training large language models across multiple competing objectives simultaneously, including verifiable tasks like math reasoning and non-verifiable subjective preferences like human values alignment. The approach uses PRM-guided decoding and Multi-Action-Head DPO to balance conflicting goals while maintaining user control during inference.

AIBullisharXiv – CS AI · May 286/10

🧠

Extrapolative Weight Averaging Reveals Correctness-Efficiency Frontiers in Code RL

Researchers demonstrate that extrapolative weight averaging—extending beyond trained model checkpoints—can navigate and extend correctness-efficiency frontiers in code reinforcement learning without additional training. Testing on competitive programming tasks reveals that ensembles using this technique improve performance by 3.3% on hard problems, suggesting a scalable method for optimizing AI systems across competing objectives.

AINeutralarXiv – CS AI · May 116/10

🧠

Multi-Objective Constraint Inference using Inverse reinforcement learning

Researchers introduce MOCI (Multi-Objective Constraint Inference), a novel framework that uses inverse reinforcement learning to extract safety constraints and individual preferences from diverse expert demonstrations where multiple experts have different objectives. The approach addresses limitations in existing methods that assume homogeneous expert behavior and offers improved computational efficiency.