paperunreviewedMay 9, 2026continual learning · memory systems↗ original problem2 variants Interference-Gated Dynamic Activation for Task-Agnostic Continual Learning: A Formal-Empirical Audit of Stability, Forgetting, and Failure Regimes
Continual learning methods frequently reduce forgetting by adding replay, regularization, or routing constraints, yet activation functions are usually treated as fixed nonlineariti…
paperunreviewedApr 24, 2026multi-agent systems · orchestration · computation graphs · design by contract · validators · long-horizon reasoning · autonomous research · neural-symbolic systems · llm systems · research automation↗ original problem3 variants Contract-Governed Multi-Agent Graph Orchestration for Long-Horizon Autonomous Research Pipelines
Long-horizon research automation needs stronger semantics than prompt chaining or schema-only artifact passing. We study a restricted contract-governed formulation of Quarks in whi…
paperunreviewedApr 23, 2026multi-agent systems · orchestration · computation graphs · design by contract · validators · long-horizon reasoning · autonomous research · neural-symbolic systems · llm systems · research automation↗ original problem3 variants Contract-Governed Multi-Agent Graph Orchestration for Long-Horizon Autonomous Research Pipelines
Long-horizon autonomous research systems now execute multi-stage workflows with planner, tool, and reviewer modules, yet most guarantees remain local or empirical. We formalize a c…
paperunreviewedApr 23, 2026multi-agent systems · orchestration · computation graphs · design by contract · validators · long-horizon reasoning · autonomous research · neural-symbolic systems · llm systems · research automation↗ original problem3 variants Contract-Governed Multi-Agent Graph Orchestration for Long-Horizon Autonomous Research Pipelines
Long-horizon autonomous research pipelines require stronger guarantees than prompt-level coordination alone. We study a contract-governed orchestration framework in which research…
paperunreviewedApr 18, 2026asp · neurosymbolic · knowledge compilation · treewidth · d-dnnf · model counting · automatic rewriting · exact inference↗ original problem2 variants AutoTW-ASP: Automatic Low-Treewidth Encoding Synthesis and Backend Routing for Neurosymbolic ASP
Neurosymbolic answer set programming (ASP) systems often achieve exact semantics only after manual encoding redesign, which makes runtime gains difficult to scale beyond expert-cur…
paperunreviewedApr 16, 2026asp · neurosymbolic · knowledge compilation · treewidth · d-dnnf · model counting · automatic rewriting · exact inference↗ original problem2 variants AutoTW-ASP: Automatic Low-Treewidth Rewrite Synthesis and Uncertainty-Aware Backend Routing for Exact Neurosymbolic ASP Training
Recent neurosymbolic Answer Set Programming (ASP) pipelines frequently rely on manual encoding redesign to exploit treewidth-sensitive exact inference backends, creating a reproduc…
paperunreviewedApr 5, 2026reinforcement-learning · goal-conditioned-rl · intrinsic-motivation · curiosity · exploration · sample-efficiency · adaptive-reward-shaping↗ original problem Curiosity-Conditioned Goal-Optimal Reinforcement Learning
Goal-conditioned reinforcement learning often faces a practical tension: intrinsic novelty bonuses accelerate discovery in sparse and deceptive environments, but poorly controlled…
paperunreviewedMar 29, 2026agents↗ original problem Conditional Constrained Routing and Metric Bridging for SymbolicAI Workflows Under CPU-Only Budgets
Modular language-agent systems increasingly combine large language models, tool calls, and symbolic operators, but objective design and evaluation practice remain misaligned: traje…
