Policy optimisation, reward modelling and RLHF — how models are trained by feedback rather than by labels.
arXiv:2606. 29820v1 Announce Type: cross Abstract: In complex continuous-control reinforcement learning tasks, multimodal optimal actions often coincide with uncertain, multimodal return distributions, making reliable value estimation and multimodal exploration challenging.
arXiv:2606. 30345v1 Announce Type: cross Abstract: Enabling large language models to achieve stable self-improvement without external expert supervision remains a central challenge in complex reasoning tasks.
arXiv:2606. 29713v1 Announce Type: cross Abstract: Hallucination is the reliability bottleneck for LLM-based agents, and fact attribution verifiers are the last line of defense -- yet today's verifiers emit only opaque binary labels, leaving agents unable to self-correct and operators unable to audit.
arXiv:2606. 28671v1 Announce Type: new Abstract: Stackelberg differential games (SDGs) provide a powerful framework for hierarchical decision-making in stochastic and continuous-time environments, yet their solution remains computationally challenging due to the complexity of traditional dynamic programming and Hamilton-Jacobi-Bellman-Isaacs (HJBI) methods, especially in high-dimensional systems.
arXiv:2508. 09883v2 Announce Type: replace-cross Abstract: Large language models (LLMs) demonstrate remarkable reasoning capabilities in tasks such as algorithmic coding and mathematical problem-solving.
arXiv:2601. 22823v2 Announce Type: replace-cross Abstract: We study offline reinforcement learning of style-conditioned policies using explicit style supervision via subtrajectory labeling functions.
arXiv:2605. 29032v2 Announce Type: replace Abstract: Model-based reinforcement learning (MBRL) agents typically learn world models by minimizing predictive loss.
arXiv:2606. 28339v1 Announce Type: cross Abstract: Industrial 6G networks require ultra-reliable, low-latency, and energy-efficient connectivity in dynamic and blockage-prone environments, where conventional terrestrial deployments often fail to ensure stable coverage.
arXiv:2606. 30627v1 Announce Type: cross Abstract: Conservative offline training is widely advocated as a safe foundation for subsequent online adaptation: if a policy stays close to well-supported behaviour, the argument goes, it is less likely to exploit imperfections in a learned reward model.
arXiv:2601. 01569v4 Announce Type: replace Abstract: LLM-based agents are increasingly capable of complex task execution, yet current agentic systems remain constrained by text-centric paradigms that struggle with long-horizon tasks due to fragile multi-turn dependencies and context drift.
arXiv:2606. 28433v1 Announce Type: new Abstract: One goal in reinforcement learning (RL) research is to understand general-purpose sequential decision-making, using benchmark simulators as a proxy for learning in deployment settings.
arXiv:2512. 07287v3 Announce Type: replace-cross Abstract: As intents unfold and environments change, multi-turn agents face continuously shifting decision contexts.
arXiv:2511. 14900v2 Announce Type: replace-cross Abstract: Vision--language models (VLMs) have recently shown promise for assisting clinical reasoning in dermatological diagnosis.
arXiv:2606. 28403v1 Announce Type: cross Abstract: Vulnerability detection in C/C++ software remains a major security challenge due to code complexity, manual memory management, and the limitations of traditional static analysis.
arXiv:2606. 30185v1 Announce Type: new Abstract: Improving vision-language models (VLMs) on visual reasoning typically requires retraining or hand-designed prompts and tools.
arXiv:2606. 29983v1 Announce Type: cross Abstract: Looped Transformers, which repeatedly apply a shared transformer block, are an architecturally natural fit for variable-length algorithmic tasks.
arXiv:2606. 28436v1 Announce Type: cross Abstract: Program verifiers play a central role in training coding agents, including selecting trajectories for supervised fine-tuning (SFT) and providing rewards for reinforcement learning (RL).
arXiv:2606. 29871v1 Announce Type: new Abstract: We present the AI Training Manager, a bounded LLM-based supervisory controller for adaptive machine learning training.
arXiv:2606. 25178v2 Announce Type: replace Abstract: Reinforcement learning with verifiable rewards (RLVR) has been extended from single-domain training to multi-domain reasoning suites spanning mathematics, programming, and science.
arXiv:2606. 30406v1 Announce Type: cross Abstract: Modern large language models (LLMs) rely on reinforcement learning during post-training to push specific capabilities, yet integrating multiple capabilities into one model remains hard.