When Free Executors Cost More: The Free-Executor Paradox in Iterative LLM Code-Repair Loops (paper + reproducibility kit)

Comparative study of transformer and non-transformer encoder architectures for dense retrieval — mapping the latency × accuracy Pareto frontier on BEIR. Solo research, PES University CSE 2026.

Multi-objective RL for reservoir control: PPO agents trace a flood/supply/ecology Pareto frontier in a custom Gymnasium environment, compared against a rule-based operating policy.

Objective Optimization Prediction Web Service Based On Machine Learning

Generate Pareto frontier graphs for Turing Complete levels

Inference cost/quality tradeoff auditor for AI systems. Finds the Pareto frontier, flags dominated routing decisions, and outputs IF/THEN rules with PASS/WARN/FAIL verdicts.

Does making the model faster make it less safe? Safety degradation benchmarking under inference optimization.

Rubric-driven LLM evaluation: multi-provider, judge panels, cost-aware Pareto reports for production model selection

Connect 4 strength-per-byte arena — play 20 agents, exact-solver analysis, and a strength-vs-cost Pareto leaderboard where a 0-byte search agent is champion. FastAPI + React.

Cost-quality routing for LLM APIs with reproducible Pareto frontiers per task class.

Python implementations of Pareto-optimal algorithms for the multi-objective 0-1 knapsack problem, with runtime analysis and benchmarking.