The paper introduces ProSE, a framework for AI assistants that generate proposals while considering users’ bounded rationality and evaluability constraints. It proposes a KL‑regularised bounded‑rational binary response model and a depth‑2 Bayes‑adaptive planner, “ProSE‑Plan,” which scores proposals by expected responses and resulting belief updates. Experiments on graph simulations show that “ProSE‑Plan” outperforms evaluability‑unaware and myopic baselines, especially when evaluation cost is high, and that informative probes are crucial for effective assistance.
arXiv:2607.28077v2 Announce Type: replace Abstract: Reinforcement learning with verifiable rewards (RLVR) improves the reasoning capabilities of large language models, but prompt groups with identica...
Reinforcement learning with verifiable rewards (RLVR) improves the reasoning capabilities of large language models, but prompt groups with identical rollout rewards consume generation budget without effective learning signals. Pre-rollout prompt selection can reduce this waste by screening prompts before rollout generation.
arXiv:2609.39927v1 Announce Type: new Abstract: Prompt optimization improves the performance of language-model systems on downstream tasks by refining their prompts. Classical methods evaluate prompt...
CAST is a critique‑aware training framework that transforms sparse task outcomes into action‑level supervision for both critique learning and policy optimization. By analyzing agent trajectories, CAST synthesizes structured rationales that explain action validity under partial observability, enabling the creation of richer training data. Fine‑tuned Qwen3‑family models trained with CAST show significant reliability gains, outperforming GPT‑OSS‑120B by over 10% on Retail tasks and improving Telehealth performance by 9% in an out‑of‑domain setting.
arXiv:2607. 17973v1 Announce Type: new Abstract: Latent world models have emerged as a powerful planning paradigm by learning action-conditioned predictive dynamics and using them as internal simulators to imagine and evaluate candidate action sequences.
arXiv:2606. 11119v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) is a promising approach for enhancing reasoning and agentic behavior in large language models.
arXiv:2607. 17281v1 Announce Type: cross Abstract: Auto-bidding plays an essential role in online advertising, automatically adjusting bids for advertisers to optimize their commercial goals.
arXiv:2607. 20083v1 Announce Type: cross Abstract: Post-training with evaluator feedback on policy-induced samples serves as a major mechanism for improving large language models.
arXiv:2607. 05046v1 Announce Type: new Abstract: Evaluating generative AI models is a routine, but resource-intensive, process that is conducted over and over again during the course of model development.
arXiv:2512.13095v3 Announce Type: replace Abstract: To address the limited capability expansion and low sample efficiency of Reinforcement Learning (RL), recent methods have integrated ''hints'' into...
The paper introduces Boundary‑Calibrated Intervention Transfer (BCIT), a method for conditional experience transfer in autonomous large language model (LLM) post‑training. BCIT links each past update to its specific parent model, data, and training stage, checks whether those conditions still hold, vetoes updates with hard conflicts, and, when necessary, runs a bounded training trial to confirm applicability before adopting the update. Experiments on a 4B model across finance reasoning, text‑to‑SQL, and function calling show that BCIT reduces harmful updates and achieves higher final‑model quality under equal computational budgets compared to other approaches.
arXiv:2606. 04261v1 Announce Type: new Abstract: Curating training data is among the most consequential yet labor-intensive parts of modern AI development: practitioners iteratively propose, implement, evaluate, and revise data policies against noisy benchmark feedback.