multi-objective-optimization

QDEvo integrates Quality-Diversity optimization with LLM-driven heuristic search to overcome mode collapse in automated heuristic design, outperforming state-of-the-art methods on benchmarks and real-world applications.

The paper extends the LLaMEA framework to automatically design multi-objective Bayesian optimization algorithms using large language models as mutation and crossover operators within evolutionary strategies, achieving state-of-the-art accuracy with significantly lower computational cost on synthetic and real-world problems.

This paper proposes a deep reinforcement learning framework (MORP-DRL) for multi-objective reliability-based portfolio optimization, jointly optimizing expected return and downside risk using CVaR and EVaR under practical constraints, and demonstrates performance on global equity indices across different market regimes.

This paper presents a multi-objective Bayesian optimization approach to automate weight selection in reinforcement learning for energy-aware control, demonstrating superior sample efficiency over grid search on a physical Quanser Aero 2 testbed.

This paper proposes a multi-objective optimization framework for routing in LLM serving, employing online linear programming with bid-price control to balance latency, throughput, and tail performance, and demonstrates improvements over heuristics using the Vidur simulator.

This paper presents an integrated framework for personalizing free-value thresholds in a two-sided job marketplace, addressing competing objectives and constrained experiments. The deployed system shows significant lift in target metrics while respecting engagement guardrails.

Introduces A3M, a framework combining adaptive deep reinforcement learning, adversarial reasoning, and multi-objective reward design for strategic bidding in repeated auctions, achieving 30-40% regret reduction.

Pepti-Agent is a closed-loop AI framework for therapeutic peptide design that uses MCP tools and an LLM controller to iteratively refine sequences based on multi-property profiles, addressing constraints like solubility, hemolysis, and non-fouling.

This paper proposes DOMOO, a diversity-driven offline multi-objective optimization method that uses accumulative risk control and nested Pareto set learning to address out-of-distribution issues, achieving superior convergence and diversity on benchmarks.

This paper presents a decision support framework for optimizing validator selection in proof-of-stake blockchains, balancing portfolio quality and diversification through multi-objective optimization and interactive preference learning.

R-APS (Reflective Adversarial Pareto Search) is a novel method for constrained design tasks that addresses three structural failures in LLM-based agentic systems—error propagation, robustness evaluation, and knowledge invalidation—through reasoning-mode decomposition across three timescales, requiring no fine-tuning. Evaluated on planar mechanism synthesis, it achieves 3.5x tighter robustness certificates, 46% faster iterations-to-first-admission, and 2.1x Chamfer-distance reduction over baselines.

ATOM is a multi-agent framework that formulates molecular optimization as a tree-structured search with specialized agents along paths, enabling exploration of alternative molecular trajectories and improving Pareto coverage in multi-objective benchmarks.

This paper proposes principled approaches for designing and optimizing practical agentic LLM systems, introducing a framework with pseudo-tools and fixed workflows to improve modularity, cost-efficiency, and accuracy across diverse tasks.

This paper presents a unified theoretical framework for gradient aggregation in multi-objective optimization, establishing convergence rates to Pareto stationarity. The authors introduce a sufficient alignment condition and demonstrate its application to existing and new algorithms, such as capped MGDA.

This paper introduces a parallelization strategy and adaptive steering mechanism for the Baymex algorithm to efficiently learn discretized Bayesian network classifiers for clinical data, achieving speedups over 54x on a 16-core CPU and comparable or better predictive performance than traditional models while maintaining explainability.

This paper introduces COAST, a causal-intelligence framework for designing constraint-aware interventions that drive complex systems between states, integrating causal discovery, modeling, and multi-objective optimization to identify minimal effective interventions with mechanistic rationales.

This paper identifies two failure modes in multi-objective prompt optimization for LLM judges using textual gradients: gradient dilution during optimization and instruction interference during inference, showing that joint gradient processing loses criterion-specific information.

MOCHA introduces a multi-objective optimization method for LLM agent skills, using Chebyshev scalarization and exponential annealing to handle hard platform constraints and discover Pareto-optimal variants, achieving significant improvements over existing optimizers.

This paper proposes GESD, a procedural-oriented fairness metric that measures disparities in explanation stability across subgroups, and integrates it into a multi-objective optimization framework for jointly optimizing utility, outcome fairness, and explanation fairness.

Lean Refactor presents a retrieval-augmented agentic framework for multi-objective, controllable, and version-robust refactoring of Lean proofs, achieving significant compression and compilation-time reduction.