The paper proposes PaW, a co-training framework that uses standard RL rollouts to provide auxiliary world model supervision directly during policy training, significantly improving language agent perf…

This paper investigates the robustness of world models in vision-based quadrotor navigation and identifies factors governing their quality.

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 proposes In-Context Reward Adaptation, a transformer-based framework that uses in-context learning and auxiliary signals (like human response time) to robustly model diverse and unseen human…

The paper introduces the Terminal Representation (TR), a novel, lower-dimensional, and structurally distinct formulation for encoding reward-weighted trajectories in RL that bypasses the need for eige…

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…

The paper introduces Metacognitive Memory Policy Optimization (MMPO), a novel memory training approach that optimizes LLM memory not based on final task success, but on minimizing epistemic uncertaint…

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 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…

The paper proposes a comprehensive framework for LLM-based agent unlearning, enabling agents to selectively forget specific knowledge (states, trajectories, or environments) while maintaining performa…

The paper formally addresses the challenging question of cross-domain transferability of latent predictive models by proposing a structured framework that quantifies the relationship between source an…

This paper demonstrates that transformer-based policies can provably learn complex tree search mechanisms, such as depth-first search, purely through reinforcement learning in a stochastic environment…

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 extending world models for multi-agent reinforcement learning by factorizing the latent state to explicitly model and predict the unobservable intentions and behaviors of teammates.

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…

The paper proposes a scalable, distributed approach for constrained Multi-Agent Reinforcement Learning by using local consensus over dual variables to ensure global constraint satisfaction without cen…

The paper introduces 'layered mutability,' a framework for analyzing how persistent self-modifying AI agents drift away from intended behavior due to the accumulation of locally reasonable, uncoordina…

COMAP introduces a novel co-evolutionary framework that simultaneously updates textual world models and agent policies through closed-loop interaction, significantly improving long-horizon decision-ma…