Policy optimisation, reward modelling and RLHF — how models are trained by feedback rather than by labels.
arXiv:2610.14570v1 Announce Type: new Abstract: Large language models (LLMs) support social simulation, but faithfully reproducing real users requires grounding both structured platform decisions and...
arXiv:2610.14883v1 Announce Type: new Abstract: We present MARL-BattleGrounds (MARL-BGs), an easy-to-use JAX-native benchmark for heterogeneous and competitive multi-agent reinforcement learning (MAR...
arXiv:2610.18851v1 Announce Type: new Abstract: Multi-objective molecular optimization is a critical process in drug discovery that aims to modify a given molecule to simultaneously improve multiple...
arXiv:2610.18067v1 Announce Type: new Abstract: Scaling interactive environments is important for training long-horizon agents through reinforcement learning. These environments often require further...
arXiv:2610.16632v1 Announce Type: cross Abstract: Memory-based long-video generation aims to combine user control with long-range visual consistency. We organize this process into three functional co...
arXiv:2610.13996v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards improves mathematical reasoning when a final answer can be checked, but a correct answer does not cert...
arXiv:2610.13998v1 Announce Type: cross Abstract: This paper proposes a hybrid reinforcement learning trading framework integrating intraday market data with transformer-based financial sentiment sig...
arXiv:2610.14000v1 Announce Type: cross Abstract: Group-relative reinforcement learning methods such as GRPO train large language model (LLM) agents by comparing rollouts for the same task. When ever...
arXiv:2610.16172v1 Announce Type: cross Abstract: Recent multimodal large language models (MLLMs) achieve strong results on video question answering, yet often fail to recover the temporal structure...
arXiv:2610.16735v1 Announce Type: cross Abstract: Multimodal reinforcement learning with verifiable rewards commonly assigns one sequence advantage to an entire response. This outcome-level signal di...
Large language models increasingly rely on external memory to answer queries grounded in long-horizon histories such as multi-session dialogues and lengthy documents. However, existing memory methods...
To address sparse terminal rewards in LLM arithmetic reasoning, we propose a Bellman-consistent trajectory RL method. Our framework introduces Trajectory Bellman Residual Minimization (TBRM) to transf...
A ReAct-style agent accumulates observations, intermediate results, and failed attempts in a single context. As this context grows, stale and off-path information consumes its limited capacity and obs...
Counterfactual reasoning (asking what would have happened, had a decision been different) is a powerful tool for identifying causes of failure and explaining the behaviour of AI systems in sequential...
Drifting models have emerged as a highly efficient and stable paradigm for policy design in offline reinforcement learning (RL). However, standard drift policies determine repulsion solely from geomet...
Segment Anything Model 3 (SAM 3) is a foundation model for image and video segmentation that sets the state of the art in visual object tracking. Its tracker, inherited from SAM 2, stores information...
Reasoning over infinitely long documents is becoming a reality with recurrent memory agents. However, increasing context length exacerbates the trade-off between reasoning performance and inference ef...
Molecular design is often formulated as an optimization problem over existing molecular spaces. However, molecular optimization and the discovery of structurally distinct replacement molecules represe...
We study finite stochastic partial monitoring (PM) games with side information, a paradigm of sequential learning with partial feedback. On each round $t \in [T]$, both player and environment observe...
Reinforcement Learning with Verifiable Rewards (RLVR) improves reasoning in language models, but scalar outcomes provide coarse supervision over response trajectories. Self-distillation offers denser...