Policy optimisation, reward modelling and RLHF — how models are trained by feedback rather than by labels.
arXiv:2608. 14156v1 Announce Type: new Abstract: The task of constructing vehicles optimal routes for pickup and delivery of goods is one of most promising tasks in the context of global urban population growth.
arXiv:2608. 13698v1 Announce Type: cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR), often optimized with Group Relative Policy Optimization (GRPO), has become a central recipe for improving the reasoning capabilities of pretrained language models but current studies remain heavily English-centric.
arXiv:2506. 01568v4 Announce Type: replace Abstract: Being able to solve a task in diverse ways makes agents more robust to task variations and less prone to local optima.
arXiv:2608. 12764v1 Announce Type: cross Abstract: Deep search agents operate over trajectories spanning dozens of steps, yet standard reinforcement learning provides only a single outcome reward per trajectory, which is far too sparse for effective credit assignment.
arXiv:2608. 12831v1 Announce Type: cross Abstract: Online platforms increasingly compare many adaptive decision policies---ranking systems, recommendation algorithms, pricing rules, and language-model agents---while each reward-bearing interaction can be costly or risky.
arXiv:2605. 08756v2 Announce Type: replace Abstract: Automatic heuristic design (AHD) has emerged as a promising paradigm for solving NP-hard combinatorial optimization problems (COPs).
arXiv:2608. 12917v1 Announce Type: new Abstract: Developing effective robot navigation methods in crowded environments is essential for real-world applications.
arXiv:2608. 13297v1 Announce Type: new Abstract: In evolutionary search, a weak child can be a valuable ancestor that makes high-fitness regions reachable.
arXiv:2608. 12753v1 Announce Type: new Abstract: We study decentralized multi-player reinforcement learning in episodic tabular Markov decision processes (MDPs) under three forms of information asymmetry: (A) unobserved actions with common rewards, (B) observed actions with independent rewards, and (C) unobserved actions with independent rewards.
arXiv:2608. 12743v1 Announce Type: new Abstract: Spatial intelligence is becoming a foundation for embodied agents, robotic planning, and multimodal assistants.
arXiv:2608. 12679v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed in discovery domains such as math and science.
arXiv:2608. 13345v1 Announce Type: new Abstract: Artificial Intelligence (AI) safety systems combine character shaping (e.
arXiv:2603. 01891v2 Announce Type: replace Abstract: Action chunking improves exploration and accelerates value propagation in long-horizon reinforcement learning, but naively applying off-policy methods to the temporally extended action space at reduced decision frequency offsets these gains, leading to poor sample efficiency.
arXiv:2602. 10840v2 Announce Type: replace Abstract: Large language models (LLMs) have been widely studied in areas such as mathematical reasoning, complex coding, and scientific problem solving.
arXiv:2604. 17299v3 Announce Type: replace-cross Abstract: Aligning large language models with human preferences must balance two competing goals: responding helpfully to legitimate requests and reliably refusing harmful ones.
arXiv:2605. 31034v2 Announce Type: replace-cross Abstract: Reinforcement learning with verifiable rewards (RLVR) and group-based policy optimization methods such as GRPO update a stochastic policy by sampling multiple completions per prompt and increasing the policy's probability on those with higher reward, regularized by a KL penalty toward a reference policy.
arXiv:2603. 27803v2 Announce Type: replace Abstract: We provide a distributed online algorithm for multi-agent submodular maximization under communication delays.
arXiv:2502. 17666v5 Announce Type: replace-cross Abstract: Existing offline in-context reinforcement learning (ICRL) methods have predominantly relied on supervised training objectives, which are known to have limitations in offline RL settings.
arXiv:2608. 13505v1 Announce Type: new Abstract: Scientific discovery increasingly requires AI systems that can reason over scientific evidence of heterogeneous modalities, interact with scientific tools and environments, and sustain progress across long task horizons.
arXiv:2608. 12585v1 Announce Type: new Abstract: Improving reasoning LLMs requires the ability to judge the quality of long reasoning traces for effective reasoning data curation, strong training signals during reinforcement learning, and an in-depth understanding of reasoning behaviors during model performance evaluation.