Policy optimisation, reward modelling and RLHF — how models are trained by feedback rather than by labels.
arXiv:2608. 02034v1 Announce Type: new Abstract: Multi-step returns accelerate reward propagation in off-policy reinforcement learning, but couple the evaluation of each decision to the suboptimal logged actions that follow it, inducing a pessimistic bias that grows with the horizon.
arXiv:2608. 01559v1 Announce Type: cross Abstract: Adversarial self-play is an appealing recipe for legal reasoning: have a student model draft an argument, have an adversary attack it, and reward the student when its argument survives the attack.
arXiv:2608. 02073v1 Announce Type: cross Abstract: We investigate Optimization under Input Uncertainty (OIU), in which the input to the objective function, rather than the objective function itself, is subject to uncertainty.
arXiv:2608. 02509v1 Announce Type: cross Abstract: Sequential decision-making in real-world applications often involves uncertainty about the environment's model.
Reinforcement learning (RL) has emerged as an effective method for enhancing the reasoning capabilities of large language models (LLMs). However, existing methods suffer from insufficient precision in feedback on generated answer trajectories and exhibit the phenomenon of problem difficulty drift.
Large Language Models (LLMs) are integrated into software systems and AI services, making efficient LLM serving a concern for software engineering. Serving LLMs is challenging because inference requires computation, memory, GPU resources, and execution while maintaining latency and throughput.
Large language models (LLMs) are increasingly deployed in complex, compound AI systems where performance hinges on the quality of prompts. Recent state-of-the-art optimizers like GEPA (Genetic-Pareto) have argued that reflective instruction evolution can outperform traditional reinforcement learning and few-shot optimization.
Artificial intelligence (AI) is increasingly central to power and energy systems, supporting modeling, forecasting, optimization, and control. Yet most existing works emphasize specialized applications and offer little reusable material for newcomers or interdisciplinary learners, who increasingly rely on large language models rather than building their own.
Effective model-based reinforcement learning in stochastic environments requires planning that accounts for predictive uncertainty. Propagating full state distributions analytically offers a principled way to do this, but has traditionally required restrictive policy or reward structures to remain tractable.
Sequential decision-making in real-world applications often involves uncertainty about the environment's model. Uncertain Markov decision processes (UMDPs) represent the possible environments as a set of MDPs with shared states and actions but potentially different transition probabilities and rewards.
Recent advances in Reinforcement Learning (RL) have substantially improved the capabilities of autonomous search agents, enabling sophisticated planning, and iterative retrieval over dynamic information sources. However, optimizing language models for specialized search behaviors often incurs an alignment tax, where gains in search performance come at the expense of general-purpose capabilities, limiting their effectiveness as universal assistants.
Post-training Large Language Models (LLMs) with Reinforcement Learning (RL) has become an important tool for improving model capabilities, but the LLM action-space structure introduces challenges distinct from classical RL, with implications for inducing exploration. New methods are required that leverage the broad knowledge and flexibility of pre-trained LLMs to deliberately generate diverse experience at training time.
Discounted exponential utility provides a principled criterion for risk-sensitive sequential decision-making, but its nonlinear structure complicates reinforcement learning. A recent work \citep{thoppe2026reinforcement} addressed this difficulty by introducing a Bellman-compatible surrogate and two model-free fixed-point algorithms for optimizing it over stationary policies.
Part-level 3D generation has recently attracted increasing attention for producing structured and editable 3D assets. However, existing methods typically decompose objects according to functional semantics rather than the editable material boundaries (e.
Verifier-guided reinforcement learning has become a powerful paradigm for improving LLM reasoning. In multi-turn settings, models receive a verifier score after each turn and iteratively refine their outputs.
arXiv:2607. 28862v1 Announce Type: cross Abstract: The rapid development of Large Language Models (LLMs) has led to significant advances across a wide range of language tasks, while simultaneously raising growing concerns about unauthorized data exploitation and privacy leakage.
arXiv:2607. 28647v1 Announce Type: cross Abstract: This paper presents ConnectED, a human-centered AI system that supports the full instructional lifecycle in Vietnamese education by linking curriculum-aligned lesson design, interactive student learning, and feedback-driven refinement.
arXiv:2607. 29468v1 Announce Type: new Abstract: Self-play agents can generate training problems without questions from target benchmarks, but their curricula lack persistent state: failures affect gradients yet do not explicitly shape future practice.
arXiv:2601. 09361v4 Announce Type: replace-cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) is a key paradigm for improving large-scale reasoning models.
arXiv:2605. 00015v2 Announce Type: replace-cross Abstract: Time Series Foundation Models (TSFMs) have demonstrated strong generalization capability and data efficiency in time series forecasting through large-scale pretraining.