arXiv AI
FlexiFlow: Bandit-based Model Switching in ML Workflows
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Oct 12
CB-Orchestrator: Adaptive Workflow Optimization for LLM Agents via Contextual Bandits
CB-Orchestrator is an adaptive framework for optimizing large language model (LLM) agent workflows. It separates workflow generation—via evolutionary search—from workflow selection, which is treated as a contextual bandit problem to enable sample‑efficient learning. The approach reduces training‑phase API token usage by up to 40.55% and overall token overhead by at least 29.73%, while outperforming baselines on five benchmarks, including the MATH dataset.
arXiv AI
Aug 3
RecHarness: A Bandit-Routed Agentic Harness for Self-Evolving Recommender Systems
arXiv:2607. 29241v1 Announce Type: cross Abstract: Optimizing modern recommender models still depends heavily on engineers manually iterating over architectural, objective, and training-strategy changes.
arXiv AI
Oct 12
COBALT: Contextual Bandit Learning with Offline Trajectories for Multi-Turn Code Generation
COBALT is a contextual bandit learning method that reuses offline multi-turn code generation trajectories to train large language models efficiently. It treats multi-turn code generation as a one-step recoverable Markov decision process, collecting partial trajectories from a reference LLM and training the target model to complete each partial trajectory in a single step. Experiments on LiveCodeBench show that COBALT improves Pass@1 scores for R1-Distill 8B and Qwen3 8B by up to 9.0 and 6.2 points, matches the performance of two online RL baselines, and enhances robustness against misleading execution feedback.
arXiv Machine Learning
Oct 15
In-Context Batch Black-box Optimization via Flow Matching
In-Context Batch Black-box Optimization via Flow Matching introduces FMTR, an amortized method that learns a continuous, history-conditioned proposal distribution for variable-size batch sampling in expensive black-box optimization settings. FMTR is trained offline using conditional flow matching on Thompson-sampling argmaxes refined through a horizon-dependent Langevin pushforward map, enabling adaptive exploration-exploitation over the optimization horizon. At test time, FMTR generates batches without task-specific surrogate refitting or numerical acquisition optimization, achieving strong performance on synthetic and real-world benchmarks while significantly reducing batch selection computational cost.
arXiv Machine Learning
Sep 10
Data Efficient Sample Selection for In-Context Learning
arXiv:2609.06670v1 Announce Type: new Abstract: The In-context learning (ICL) paradigm aids large language models (LLMs) to adapt to new tasks without need for fine-tuning. However, selecting an opti...
arXiv AI
Jul 7
DynamixSFT: Dynamic Mixture Optimization of Instruction Tuning Collections
arXiv:2508. 12116v2 Announce Type: replace-cross Abstract: As numerous instruction-tuning datasets continue to emerge, dynamically balancing and optimizing their mixtures has become a critical challenge.