DRIFT proposes a novel framework that efficiently optimizes LLMs for multi-turn interactions by decoupling rollout from optimization, allowing the use of weighted supervised fine-tuning to match the p…

The paper proposes Guided Denoiser Self-Distillation (GDSD), a novel method that bypasses the use of likelihood surrogates (like ELBO) in RL for diffusion language models, achieving state-of-the-art p…

The paper proposes DNQ, a scalable solver-in-the-loop framework for training agents in multi-turn simultaneous bidding games by leveraging pairwise payoff estimation to approximate complex equilibrium…

The paper introduces Posterior Hybrid Bayesian Belief (PhyB), a novel framework that reformulates policy optimization in Bayesian Offline RL by approximating expectations as a convex combination over…

The paper introduces Drifting Preference Optimization (DrPO), an efficient online method for preference finetuning one-step text-to-image generators that avoids complex gradient calculations and model…

This paper proposes two horizon-control strategies, Progressive OPD (POPD) and Truncated OPD (TOPD), demonstrating that full rollouts are often unnecessary for On-Policy Distillation, leading to signi…

EchoRL proposes a lightweight module to exploit valuable learning signals from advantage-degenerated rollouts in Reinforcement Learning with Verifiable Rewards (RLVR), significantly improving LLM post…

The paper introduces Q-ALIGN DT, a novel framework that improves conditioned sequence models by enforcing alignment between the input return-to-go (RTG) signal and the output policy's expected Q-value…

The paper proposes a novel framework combining behavior-invariant task representation learning and a Transformer-based world model to achieve robust generalization in offline meta-reinforcement learni…

The paper proposes a cost-aware, adaptive maintenance framework using Reinforcement Learning (RL) and self-supervised learning to mitigate performance degradation (concept drift) in Android malware de…

The paper introduces Trust-Region behavior Blending (TRB), a warmup method that improves on-policy distillation by replacing poor early student rollouts with teacher-aligned behavior policies, leading…

ADWIN introduces an adaptive window framework for on-policy distillation (OPD) that efficiently manages the supervision horizon by training on short, teacher-anchored prefixes while using delayed full…

SPAR introduces a novel framework that rectifies action policies by performing local fine-tuning in a residual space anchored to a pure behavior cloning policy, achieving state-of-the-art performance…

The paper introduces OPD+, a corrected on-policy distillation framework that mathematically proves the bias of standard stop-gradient methods and improves the stability and performance of knowledge tr…

The paper introduces the Markov decision contest, a new framework for reinforcement learning using pairwise preferences, and proves that stationary Markov policies are optimal and solvable efficiently…

This paper proposes a new imitation learning algorithm called DistIL that uses distributional feedback to improve policy improvement and regret guarantees.

The paper proposes DIBS, a decoupled behavioral cloning approach that stabilizes inductive generalization in RL by separating task-specific policy learning from the evolution function, leading to impr…

TraceGraph introduces a graph-based framework to map agent decision-making across pooled trajectories, revealing hidden differences in agent behavior and improving performance by targeting known failu…

The OISD framework improves language model reasoning by distilling on-policy predictive signals from the final output layer to intermediate representations, leading to substantial improvements on math…

The paper proposes ProRL, an effective Reinforcement Learning framework that rectifies gradient estimation deficiencies to optimize proactive recommendation paths, significantly outperforming existing…