Self-Play Enhancement via Advantage-Weighted Refinement in Online Federated LLM Fine-Tuning with Real-Time Feedback

• URL: http://arxiv.org/abs/2605.07977v1
• Date: Fri, 08 May 2026 16:35:42 GMT
• Title: Self-Play Enhancement via Advantage-Weighted Refinement in Online Federated LLM Fine-Tuning with Real-Time Feedback
• Abstract summary: We introduce SPEAR, an efficient online learning algorithm for federated feedback fine-tuning.<n>We validate SPEAR across various benchmark datasets, demonstrating its superior performance in comparison to state-of-the-art baselines.
• Score: 37.79391516435725
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent works have advanced feedback-based learning systems, whereby a foundation model is able to intake incoming feedback (e.g., a user) to self-improve, creating a self-loop system of training. However, existing works are limited in needing to consider an offline setup to allow for such feedback-based methods, and are further limited in the need of requiring privileged ground-truth contexts for training. Moreover, there is limited consideration of federated learning (FL), which is particularly well-suited for incorporating external feedback across large networks of end users, for example, but requires methods to be efficient for training on resource-constrained edge devices. Therefore, we introduce SPEAR (Self-Play Enhancement via Advantage-Weighted Refinement), an efficient online learning algorithm for federated LLM fine-tuning. SPEAR utilizes a feedback-guided self-play loop to construct naturally contrastive pairs per prompt which are utilized to be trained on (i) standard maximum likelihood on correct completions and (ii) confidence-weighted unlikelihood on tail tokens of incorrect completions. Without the need of expensive group generations and ground-truth contexts for training (i.e., only partial, non-answer feedback), in contrast with existing works, SPEAR can be trained both online and in a resource-efficient manner. We validate SPEAR across various benchmark datasets, demonstrating its superior performance in comparison to state-of-the-art baselines. The implementation code is publicly available at https://github.com/lee3296/SPEAR.

Related papers

• Harnessing LLM Agents with Skill Programs [58.356514745548026]
  We introduce HASP, a new framework that upgrades skills into executable Program Functions (PFs)<n>PFs act as executable guardrails that activate on failure-prone states and modify the next action or inject corrective context.<n> HASP drives substantial gains compared to both training-free and training-based methods on web-search, math reasoning, and coding tasks.
  arXiv  Detail & Related papers  (2026-05-18T01:35:11Z)
• When Learning Hurts: Fixed-Pole RNN for Real-Time Online Training [58.25341036646294]
  We analytically examine why learning recurrent poles does not provide tangible benefits in data and empirically offer real-time learning scenarios.<n>We show that fixed-pole networks achieve superior performance with lower training complexity, making them more suitable for online real-time tasks.
  arXiv  Detail & Related papers  (2026-02-25T00:15:13Z)
• Learning in Context, Guided by Choice: A Reward-Free Paradigm for Reinforcement Learning with Transformers [55.33468902405567]
  We propose a new learning paradigm, In-Context Preference-based Reinforcement Learning (ICPRL), in which both pretraining and deployment rely solely on preference feedback.<n>ICPRL enables strong in-context generalization to unseen tasks, achieving performance comparable to ICRL methods trained with full reward supervision.
  arXiv  Detail & Related papers  (2026-02-09T03:42:16Z)
• SeRL: Self-Play Reinforcement Learning for Large Language Models with Limited Data [65.56911325914582]
  We propose Self-play Reinforcement Learning (SeRL) to bootstrap Large Language Models (LLMs) training with limited initial data.<n>The proposed SeRL yields results superior to its counterparts and achieves performance on par with those obtained by high-quality data with verifiable rewards.
  arXiv  Detail & Related papers  (2025-05-25T13:28:04Z)
• Trajectory Balance with Asynchrony: Decoupling Exploration and Learning for Fast, Scalable LLM Post-Training [71.16258800411696]
  Reinforcement learning (RL) is a critical component of large language model (LLM) post-training.<n>Existing on-policy algorithms used for post-training are inherently incompatible with the use of experience replay buffers.<n>We propose efficiently obtaining this benefit of replay buffers via Trajectory Balance with Asynchrony (TBA)
  arXiv  Detail & Related papers  (2025-03-24T17:51:39Z)
• Self-Contrastive Forward-Forward Algorithm [3.1361717406527667]
  Forward-Forward (FF) algorithm relies on feedforward operations to optimize layer-wise objectives.<n>FF has failed to reach state-of-the-art performance on most standard benchmark tasks.<n>We propose Self-Contrastive Forward-Forward (SCFF) algorithm, a competitive training method aimed at closing this performance gap.
  arXiv  Detail & Related papers  (2024-09-17T22:58:20Z)
• Online Bandit Learning with Offline Preference Data for Improved RLHF [15.799929216215672]
  We propose a posterior sampling algorithm for online learning that can be warm-started with an offline dataset with noisy preference feedback.<n>We show that by modeling the 'competence' of the expert that generated it, we are able to use such a dataset most effectively.
  arXiv  Detail & Related papers  (2024-06-13T20:25:52Z)
• Efficient Preference-based Reinforcement Learning via Aligned Experience Estimation [37.36913210031282]
  Preference-based reinforcement learning (PbRL) has shown impressive capabilities in training agents without reward engineering. We propose SEER, an efficient PbRL method that integrates label smoothing and policy regularization techniques.
  arXiv  Detail & Related papers  (2024-05-29T01:49:20Z)
• Benchmarks and Algorithms for Offline Preference-Based Reward Learning [41.676208473752425]
  We propose an approach that uses an offline dataset to craft preference queries via pool-based active learning. Our proposed approach does not require actual physical rollouts or an accurate simulator for either the reward learning or policy optimization steps.
  arXiv  Detail & Related papers  (2023-01-03T23:52:16Z)
• OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learning [107.6943868812716]
  In many practical applications, the situation is reversed: an agent may have access to large amounts of undirected offline experience data, while access to the online environment is severely limited. Our main insight is that, when presented with offline data composed of a variety of behaviors, an effective way to leverage this data is to extract a continuous space of recurring and temporally extended primitive behaviors. In addition to benefiting offline policy optimization, we show that performing offline primitive learning in this way can also be leveraged for improving few-shot imitation learning.
  arXiv  Detail & Related papers  (2020-10-26T14:31:08Z)

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.