B. Low

MMT: Achieving Exact Federated Unlearning with Improved Post-unlearning Performance

MESH-Harness: Self-Improving Agent Harnesses via Bandit-Guided Compositional Evolution

An agent harness is the code that organizes context, maintains state, and coordinates tool calls for a language model. We study how to improve the harness under a limited evaluation budget while keeping model weights fixed. Our method, MESH-Harness, organizes each harness into functional modules with explicit role-spec...

COBRA-Skills: Contextual Bandit-Guided Evolution for Agent Skill Optimization

COBRA-Skills is introduced, an efficient framework that formulates skill optimization as budgeted sequential optimization over a dynamically evolving candidate space and remains robust to changes in the agent harness and performs effectively when the target model itself is used for skill generation and refinement.

Diffusion-Inspired Reconfiguration of Transformers for Uncertainty Calibration

A diffusion-inspired reconfiguration of transformers in which each feature transformation block is modeled as a probabilistic mapping that mimics the structure of a diffusion process, transporting data mass from the input distribution to the pre-trained feature distribution.

Keep Everyone Happy: Online Fair Division of Numerous Items with Few Copies

This paper proposes algorithms that model online fair division as a contextual bandit problem and achieve provable sublinear regret and proposes algorithms that model utility is an unknown function of item-agent features.

Scaling Near-Optimal SFT-RL Annotation Budget Allocation from Small to Large LLMs

This work describes the near-optimal region, the set of allocations within a specified tolerance of peak performance, which is wide even for small tolerances, widens with model scale, and transfers reliably from small proxy models to large target models.

Efficiently Estimating Optimal Hyperparameter Scaling Laws through Power-Law Entropy Search

This work introduces Power-Law Entropy Search (PLES), a computational cost-aware acquisition function built on multi-fidelity Bayesian optimization that efficiently estimates optimal hyperparameter scaling laws through adaptive experimentation using less than one-tenth of the computational budget required by convention...