arXiv:2605.30434v1 Announce Type: new Abstract: Real-world data analysis is inherently iterative, yet existing benchmarks mostly evaluate isolated or short interactive tasks, leaving agents’ ability to track evolving analytical context over long horizons untested. We introduce LongDS, a benchmark for long-horizon,…
arXiv:2412.18134v4 Announce Type: replace Abstract: Randomized self-reductions (RSRs) express $f(x)$ using $f$ evaluated at random correlated points, enabling self-correcting programs, instance-hiding protocols, and applications in complexity theory and cryptography. Yet discovering RSRs has required manual expert derivation for over 40…
arXiv:2605.30447v1 Announce Type: new Abstract: Calibration, the alignment of predicted probabilities with true outcome frequencies, is essential for reliable decision-making. While extensively studied for classification and regression, calibration has not been formally addressed for probabilistic label ranking, where the goal…
arXiv:2511.03100v2 Announce Type: replace Abstract: The agent-environment co-design paradigm jointly optimises agent policies and environment configurations in search of improved system performance. With application domains ranging from warehouse logistics to windfarm management, co-design promises to fundamentally change how we deploy…
arXiv:2605.30448v1 Announce Type: new Abstract: Black-box LLM distillation is usually evaluated as an output-matching problem: a student is considered successful when its responses are semantically similar to, or task-consistent with, those of a teacher. However, output similarity does not imply…
arXiv:2602.01553v2 Announce Type: replace Abstract: Link prediction is a core challenge in graph machine learning, demanding models that capture rich and complex topological dependencies. While Graph Neural Networks (GNNs) are the standard solution, state-of-the-art pipelines often rely on explicit structural…
arXiv:2605.30451v1 Announce Type: new Abstract: Group Relative Policy Optimization (GRPO) is an effective recipe for training reasoning models with verifier-based outcome rewards, but its supervision is sparse: when all sampled trajectories for a prompt receive the same verifier reward, the…
arXiv:2602.23280v2 Announce Type: replace Abstract: Offline goal-conditioned reinforcement learning (GCRL) learns goal-reaching behaviors from static datasets, but accurate value estimation remains challenging under limited state-action coverage. Existing physics-informed approaches address this by imposing pointwise distance-like geometric constraints derived from Hamilton–Jacobi–Bellman…
arXiv:2605.30452v1 Announce Type: new Abstract: Many machine learning problems involve multiple inherent trade-offs that are best addressed by gradient-based multi-objective optimization (MOO) algorithms. Existing methods are often proposed with various motivations, analyzed case by case, and differ algorithmically in how…
arXiv:2605.17373v2 Announce Type: replace Abstract: AI research agents accelerate ML research by automating hypothesis generation, experimentation, and empirical refinement. Existing agent strategies range from greedy hill-climbing to tree search and evolutionary optimization, yet which strategy choices drive performance remains unclear.…
