The paper proposes a coherent inverse reinforcement learning (IRL) method to improve large behavior models for robotic control, achieving superior sample efficiency and performance on complex sparse m…

The paper introduces a logic-driven framework using a neural certificate function to rigorously evaluate and benchmark the generalization capabilities of reinforcement learning algorithms on unseen ta…

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 Parameterized Diffusion Policy (PDP) framework transforms diffusion models from general stochastic generators into precise, steerable tools for learning and adapting complex robotic behaviors by e…

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 VERA, a decoupled policy that uses an action-free video world model combined with an embodiment-specific Inverse Dynamics Model (IDM) to achieve generalizable, zero-shot robot contr…

ReSkill is an RL-in-the-loop framework that reconciles skill creation and policy optimization by automatically creating, testing, and refining modular skills alongside the agent's policy learning, lea…

This paper studies how to scale robust robot policies by expanding physical domains in a recoverable way.

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 Banyan, a new continual reinforcement learning benchmark, demonstrating that while task diversity enables local transfer across distribution shifts, it does not guarantee sustaine…

SCOPE introduces a data-free self-play framework that co-evolves a task-generating Challenger and a document-answering Solver, significantly improving open-ended performance on language models without…

SkillC introduces a Contrastive Skill Credit Assignment (CSCA) framework to enable LLM agents to autonomously internalize skills during training, significantly outperforming existing methods without r…

The paper investigates the limits of self-evolution in LLM reasoning under closed-loop settings, finding that while self-improvement is significant, it consistently falls short of perfect oracle super…

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

The paper proposes S2L-PO, a framework that uses smaller, naturally diverse models as structured explorers to enhance the policy-level diversity and performance of larger language models during traini…

The Implicit Drifting Policy (IDP) is a novel one-step action generation framework that implicitly enforces trajectory correction constraints by analyzing local expert action geometry, overcoming the…

The paper proposes a feasible-reward-set framework to perform Inverse Reinforcement Learning (IRL) when data comes from multiple imperfect demonstrators, providing theoretical guarantees and practical…

The paper proposes Deep Research as Rubric (DR-rubric), a novel evidence-driven framework that treats rubric construction itself as a research problem to generate fine-grained, scalable reward signals…