Policy optimisation, reward modelling and RLHF — how models are trained by feedback rather than by labels.
arXiv:2606. 26936v1 Announce Type: cross Abstract: With a profusion of jailbreaks for LLMs now widely known, a growing concern is that non-expert malicious actors ("the average Jane") could elicit actionable responses to malicious requests.
arXiv:2602. 07533v2 Announce Type: replace Abstract: Reward models are critical for reinforcement learning from human feedback, as they determine the alignment quality and reliability of generative models.
arXiv:2606. 23603v2 Announce Type: replace Abstract: Unhealthy dietary behavior continues to be a persistent public health issue in the United States, exacerbated by recommendation systems that prioritize user preference without considering nutritional health.
arXiv:2606. 26498v1 Announce Type: cross Abstract: This paper addresses model-free continuous-time mean-field control in a setting where the population dynamics evolve continuously according to an unknown McKean-Vlasov stochastic differential equation, while only discrete-time transition data are available.
arXiv:2606. 26350v1 Announce Type: new Abstract: Although large language model agents are increasingly applied to quantitative-finance workflows, their evaluation remains fragmented across isolated tasks, while the financial relevance of benchmark tasks is often overlooked.
arXiv:2606. 26399v1 Announce Type: new Abstract: We study certain extremal problems in combinatorial geometry that ask about configurations of points in an $n \times n$ grid that satisfy strict, global geometric constraints.
arXiv:2604. 04535v2 Announce Type: replace Abstract: Modern machine learning systems, such as generative models and recommendation systems, often evolve through a cycle of deployment, user interaction, and periodic model updates.
arXiv:2606. 26123v1 Announce Type: cross Abstract: Ultra-low latency and high throughput are required for Virtual Reality (VR) services in 6G networks, which presents critical challenges for Software-Defined Radio Access Networks (SD-RANs) dynamic resource management.
arXiv:2606. 26102v1 Announce Type: cross Abstract: Standard post-training pipelines apply supervised fine-tuning (SFT) and reinforcement learning (RL) to make language models helpful, but these processes may inadvertently degrade values instilled during pre-training.
arXiv:2606. 26333v1 Announce Type: new Abstract: Reinforcement learning in large or sparse-reward environments suffers from slow temporal-difference reward propagation, as value information spreads only locally across the state space.
arXiv:2606. 25524v2 Announce Type: replace Abstract: Large language models (LLMs) reach high accuracy in mathematical reasoning, but individual traces on the same problem diverge; some arrive at the correct answer while others fail.
arXiv:2606. 27180v1 Announce Type: cross Abstract: Sparse rewards are inherently challenging for reinforcement learning agents as they lack intermediate feedback to guide exploration and to correctly attribute the sparse success rewards to relevant parts of the trajectory.
arXiv:2606. 26442v1 Announce Type: cross Abstract: We present AXLE (Axiom Lean Engine), a cloud service for Lean 4 proof manipulation, extraction, and verification.
arXiv:2605. 02405v2 Announce Type: replace Abstract: Closed-loop management of geological CO2 storage requires control policies that adapt to uncertain reservoir behavior while relying on observations that are realistically available during operation.
arXiv:2510. 09976v2 Announce Type: replace Abstract: Vision-Language-Action (VLA) models such as OpenVLA, Octo, and $\pi_0$ have shown strong generalization by leveraging large-scale demonstrations, yet their performance is still fundamentally constrained by the quality and coverage of supervised data.
arXiv:2606. 27369v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) for training LLMs typically rely on ground-truth answers to assign rewards, limiting their applicability to tasks where the ground-truth solution is unknown.
arXiv:2509. 20008v2 Announce Type: replace Abstract: Penetration testing, the simulation of cyberattacks to identify security vulnerabilities, presents a sequential decision-making problem well-suited for reinforcement learning (RL) automation.
arXiv:2606. 26534v1 Announce Type: cross Abstract: Recently, zero-shot text-to-speech (TTS) has enabled high-fidelity and expressive speech synthesis, but it often fails to imitate unseen speaking styles from uncommon scenarios (e.
arXiv:2505. 23527v4 Announce Type: replace Abstract: Modern reinforcement learning (RL) algorithms have found success by using powerful probabilistic models, such as transformers, energy-based models, and diffusion/flow-based models.
arXiv:2603. 19864v2 Announce Type: replace Abstract: Penetration testing, the practice of simulating cyberattacks to identify vulnerabilities, is a complex sequential decision-making task that is inherently partially observable and features large action spaces.