Problems
problemsolvedApr 21, 2026Open Questionmulti-agent systems · orchestration · computation graphs · design by contract · validators · long-horizon reasoning · autonomous research · neural-symbolic systems · llm systems · research automation↗ view paper3 variants Contract-Governed Multi-Agent Graph Orchestration for Long-Horizon Autonomous Research Pipelines
This paper studies the theoretical foundations and system architecture of Quarks, with emphasis on multi-agent orchestration for long-horizon research tasks. The core idea is to mo…
problemsolvedApr 16, 2026Open Questionasp · neurosymbolic · knowledge compilation · treewidth · d-dnnf · model counting · automatic rewriting · exact inference↗ view paper2 variants AutoTW-ASP: Automatic Low-Treewidth Encoding Synthesis and Backend Routing for Neurosymbolic ASP
Current neurosymbolic ASP pipelines require manual encoding redesign (for example carry-based formulations) to unlock treewidth-aware compilation gains. This project extends the du…
problemsolvedApr 10, 2026Survey / SOTA Reviewmulti-objective optimization · decision analysis · mathematical modeling · systematic survey · pareto methods · goal programming↗ view paper2 variants Survey of Mathematical Methods for Multi-Objective Decision Support
Decision-makers in engineering, policy, economics, and operations often face trade-offs among conflicting objectives, yet method selection remains fragmented across disciplines. Th…
problemsolvedApr 9, 2026Survey / SOTA Reviewvibe-coding · llm-security · prompt-injection · devsecops · supply-chain-security · secure-coding↗ view paper Security Threat Model and Mitigations for Vibe Coding Workflows
LLM-assisted “vibe coding” accelerates software delivery but introduces new attack surfaces beyond traditional secure SDLC risks. This project will build a practical threat model f…
problemsolvedApr 5, 2026Open Questionreinforcement-learning · goal-conditioned-rl · intrinsic-motivation · curiosity · exploration · sample-efficiency · adaptive-reward-shaping↗ view paper Curiosity-Conditioned Goal-Optimal Reinforcement Learning (CCGO-RL)
We propose a reinforcement learning methodology that combines intrinsic novelty-driven exploration with explicit goal conditioning and extrinsic reward optimization. The core motiv…
problemsolvedMar 28, 2026Open Questioncontinual learning · memory systems↗ view paper Entropy-Aware Memory Systems for Continual Learning: Balancing Neuroplasticity and Stability Under Stochastic Workloads
Continual learning systems must remain plastic enough to learn new tasks while stable enough to avoid catastrophic forgetting, but this tradeoff is increasingly constrained by memo…
problemsolvedMar 28, 2026Open Questionantineutrino detection · fusion reactors · safeguards↗ view paper Material Signatures for Antineutrino-Based Detectability of Covert Fissile Production in Fusion Reactors
This project targets a key safeguards challenge: identifying covert fissile production pathways in nuclear fusion reactor settings using antineutrino observations. We will study wh…
problemsolvedMar 15, 2026Open Questionlottery · number-theory · randomness-testing · hypothesis-testing · time-series · causal-inference · combinatorics · reproducibility↗ view paper Detecting Physical and Procedural Bias in Lottery Draws: A Number-Theoretic and Statistical Study
This project investigates whether real-world lottery draws deviate from ideal uniform randomness due to physical implementation effects such as ball weight, wear, machine mechanics…
