DARA: Few-shot Budget Allocation in Online Advertising via In-Context Decision Making with RL-Finetuned LLMs

• URL: http://arxiv.org/abs/2601.14711v1
• Date: Wed, 21 Jan 2026 06:58:44 GMT
• Title: DARA: Few-shot Budget Allocation in Online Advertising via In-Context Decision Making with RL-Finetuned LLMs
• Authors: Mingxuan Song, Yusen Huo, Bohan Zhou, Shenglin Yin, Zhen Xiao, Jieyi Long, Zhilin Zhang, Chuan Yu,
• Abstract summary: Large Language Models offer a promising alternative for AIGB.<n>They lack the numerical precision required for fine-grained optimization.<n>We propose DARA, a novel dual-phase framework that decomposes the decision-making process into two stages.<n>Our approach consistently outperforms existing baselines in terms of cumulative advertiser value under budget constraints.
• Score: 21.30516760599435
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Optimizing the advertiser's cumulative value of winning impressions under budget constraints poses a complex challenge in online advertising, under the paradigm of AI-Generated Bidding (AIGB). Advertisers often have personalized objectives but limited historical interaction data, resulting in few-shot scenarios where traditional reinforcement learning (RL) methods struggle to perform effectively. Large Language Models (LLMs) offer a promising alternative for AIGB by leveraging their in-context learning capabilities to generalize from limited data. However, they lack the numerical precision required for fine-grained optimization. To address this limitation, we introduce GRPO-Adaptive, an efficient LLM post-training strategy that enhances both reasoning and numerical precision by dynamically updating the reference policy during training. Built upon this foundation, we further propose DARA, a novel dual-phase framework that decomposes the decision-making process into two stages: a few-shot reasoner that generates initial plans via in-context prompting, and a fine-grained optimizer that refines these plans using feedback-driven reasoning. This separation allows DARA to combine LLMs' in-context learning strengths with precise adaptability required by AIGB tasks. Extensive experiments on both real-world and synthetic data environments demonstrate that our approach consistently outperforms existing baselines in terms of cumulative advertiser value under budget constraints.

Related papers

• AHBid: An Adaptable Hierarchical Bidding Framework for Cross-Channel Advertising [8.53485049764747]
  AHBid is an Adaptable Hierarchical Bidding framework that integrates generative planning with real-time control.<n>Experiments conducted on large-scale offline datasets and through online A/B tests demonstrate the effectiveness of AHBid.
  arXiv  Detail & Related papers  (2026-02-26T06:07:28Z)
• RELATE: A Reinforcement Learning-Enhanced LLM Framework for Advertising Text Generation [17.34586562700226]
  In online advertising, advertising text plays a critical role in attracting user engagement and driving advertiser value.<n>We propose RELATE, a reinforcement learning-based end-to-end framework that unifies generation and objective alignment within a single model.<n>To better capture ultimate advertiser value beyond click-level signals, We incorporate conversion-oriented metrics into the objective and jointly model them with compliance constraints as multi-dimensional rewards.
  arXiv  Detail & Related papers  (2026-02-12T10:00:55Z)
• MAESTRO: Meta-learning Adaptive Estimation of Scalarization Trade-offs for Reward Optimization [56.074760766965085]
  Group-Relative Policy Optimization has emerged as an efficient paradigm for aligning Large Language Models (LLMs)<n>We propose MAESTRO, which treats reward scalarization as a dynamic latent policy, leveraging the model's terminal hidden states as a semantic bottleneck.<n>We formulate this as a contextual bandit problem within a bi-level optimization framework, where a lightweight Conductor network co-evolves with the policy by utilizing group-relative advantages as a meta-reward signal.
  arXiv  Detail & Related papers  (2026-01-12T05:02:48Z)
• Multi-Objective Reward and Preference Optimization: Theory and Algorithms [3.316593788543852]
  This thesis develops theoretical frameworks and algorithms that advance constrained reinforcement learning (RL) across control, preference learning, and alignment of large language models.<n>ACPO, e-COP, warmPref-PS, PSPL, and MOPO advance RL across average-cost, episodic, and preference-driven paradigms.<n> Collectively, the thesis unifies RL across average-cost, episodic, and preference-driven paradigms, delivering theoretical advances and practical tools for safe and aligned decision-making.
  arXiv  Detail & Related papers  (2025-12-11T12:51:21Z)
• Data Efficient Adaptation in Large Language Models via Continuous Low-Rank Fine-Tuning [34.343514432589586]
  This paper proposes textbf, a novel framework that integrates Low-Rank Adaptation (LoRA) with a continuous fine-tuning strategy.<n> Experiments on 15 diverse datasets show that DEAL consistently outperforms baseline methods.<n>These findings demonstrate the potential of our approach to advance continual adaptation in Large Language Models.
  arXiv  Detail & Related papers  (2025-09-23T12:55:57Z)
• Beyond Naïve Prompting: Strategies for Improved Zero-shot Context-aided Forecasting with LLMs [57.82819770709032]
  Large language models (LLMs) can be effective context-aided forecasters via na"ive direct prompting.<n>ReDP improves interpretability by eliciting explicit reasoning traces, allowing us to assess the model's reasoning over the context.<n>CorDP leverages LLMs solely to refine existing forecasts with context, enhancing their applicability in real-world forecasting pipelines.<n> IC-DP proposes embedding historical examples of context-aided forecasting tasks in the prompt, substantially improving accuracy even for the largest models.
  arXiv  Detail & Related papers  (2025-08-13T16:02:55Z)
• RecLLM-R1: A Two-Stage Training Paradigm with Reinforcement Learning and Chain-of-Thought v1 [20.92548890511589]
  This paper introduces RecLLM-R1, a novel recommendation framework leveraging Large Language Models (LLMs)<n> RecLLM-R1 significantly surpasses existing baseline methods across a spectrum of evaluation metrics, including accuracy, diversity, and novelty.
  arXiv  Detail & Related papers  (2025-06-24T01:39:34Z)
• Enhancing Decision-Making of Large Language Models via Actor-Critic [28.870961806283425]
  Large Language Models (LLMs) have achieved remarkable advancements in natural language processing tasks.<n>Existing methods either rely on short-term auto-regressive action generation or face limitations in accurately simulating rollouts and assessing outcomes.<n>This paper introduces a novel LLM-based Actor-Critic framework, termed LAC, that effectively improves LLM policies with long-term action evaluations.
  arXiv  Detail & Related papers  (2025-06-04T14:58:27Z)
• Adaptive Resource Allocation Optimization Using Large Language Models in Dynamic Wireless Environments [25.866960634041092]
  Current solutions rely on domain-specific architectures or techniques, and a general DL approach for constrained optimization remains undeveloped.<n>We propose a large language model for resource allocation (LLM-RAO) to address the complex resource allocation problem while adhering to constraints.<n>LLM-RAO achieves up to a 40% performance enhancement compared to conventional DL methods and up to an $80$% improvement over analytical approaches.
  arXiv  Detail & Related papers  (2025-02-04T12:56:59Z)
• Large Language Model driven Policy Exploration for Recommender Systems [50.70228564385797]
  offline RL policies trained on static user data are vulnerable to distribution shift when deployed in dynamic online environments.<n>Online RL-based RS also face challenges in production deployment due to the risks of exposing users to untrained or unstable policies.<n>Large Language Models (LLMs) offer a promising solution to mimic user objectives and preferences for pre-training policies offline.<n>We propose an Interaction-Augmented Learned Policy (iALP) that utilizes user preferences distilled from an LLM.
  arXiv  Detail & Related papers  (2025-01-23T16:37:44Z)
• Federated Fine-Tuning of LLMs: Framework Comparison and Research Directions [59.5243730853157]
  Federated learning (FL) provides a privacy-preserving solution for fine-tuning pre-trained large language models (LLMs) using distributed private datasets.<n>This article conducts a comparative analysis of three advanced federated LLM (FedLLM) frameworks that integrate knowledge distillation (KD) and split learning (SL) to mitigate these issues.
  arXiv  Detail & Related papers  (2025-01-08T11:37:06Z)
• Self-Augmented Preference Optimization: Off-Policy Paradigms for Language Model Alignment [104.18002641195442]
  We introduce Self-Augmented Preference Optimization (SAPO), an effective and scalable training paradigm that does not require existing paired data. Building on the self-play concept, which autonomously generates negative responses, we further incorporate an off-policy learning pipeline to enhance data exploration and exploitation.
  arXiv  Detail & Related papers  (2024-05-31T14:21:04Z)
• Unleashing the Power of Pre-trained Language Models for Offline Reinforcement Learning [50.9692060692705]
  This paper introduces $textbfLanguage Models for $textbfMo$tion Control ($textbfLaMo$), a general framework based on Decision Transformers for offline RL.<n>Our framework highlights four crucial components:.<n>Initializing Decision Transformers with sequentially pre-trained LMs, (2) employing the LoRA fine-tuning method,.<n>In particular, our method demonstrates superior performance in scenarios with limited data samples.
  arXiv  Detail & Related papers  (2023-10-31T16:24:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.