Policy optimisation, reward modelling and RLHF — how models are trained by feedback rather than by labels.
arXiv:2606. 00257v1 Announce Type: cross Abstract: Token-level credit assignment for language-model reinforcement learning is usually formulated as if the policy were fully trainable, while practical LLM-RL pipelines often rely on parameter-efficient fine-tuning, especially LoRA.
arXiv:2606. 00183v1 Announce Type: cross Abstract: Tree search is a central abstraction behind many language-agent reasoning and decision-making tasks: agents must explore actions, remember failures, and backtrack toward promising alternatives.
arXiv:2606. 02132v1 Announce Type: new Abstract: Agentic reinforcement learning can induce tool abuse, where models overuse external tools even for queries solvable by internal reasoning.
arXiv:2606. 01868v1 Announce Type: new Abstract: Reinforcement Learning (RL) has long served as a model for goal-directed animal behavior in neuroscience.
arXiv:2312. 03644v3 Announce Type: replace Abstract: Offline Multi-agent Reinforcement Learning (MARL) is valuable in scenarios where online interaction is impractical or risky.
arXiv:2606. 00392v1 Announce Type: cross Abstract: AI-text detectors are vulnerable to paraphrasing and detector-guided paraphrasing attacks, but existing detector-evasion methods often lack precise control over semantic preservation.
arXiv:2606. 00350v1 Announce Type: cross Abstract: Offline reinforcement learning requires improving a policy from fixed data while avoiding out-of-distribution actions with unreliable value estimates.
arXiv:2605. 18077v2 Announce Type: replace Abstract: Communication is a key component in multi-agent reinforcement learning (MARL) for mitigating partial observability, yet prior approaches often rely on inefficient information exchange or fail to transmit sufficient state information.
arXiv:2510. 05342v2 Announce Type: replace-cross Abstract: Direct Preference Optimization (DPO) has emerged as a simple and effective method for aligning large language models.
arXiv:2512. 13356v2 Announce Type: replace-cross Abstract: This paper proposes a reinforcement learning (RL) framework for controlling and stabilizing the Twin Rotor Aerodynamic System (TRAS) at specific pitch and azimuth angles and tracking a given trajectory.
arXiv:2606. 01755v1 Announce Type: new Abstract: Personalized large language models adapt responses to users' preferences and social attributes, but can introduce substantial universal truth inconsistencies across social groups, where some groups systematically receive less accurate responses on objective tasks.
arXiv:2606. 00869v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has become central to LLM reasoning, but its outcome-level rewards can make models more willing to give confident answers when evidence or reasoning is unreliable.
arXiv:2606. 00269v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models can be steered at test time by intervening on semantically meaningful internal directions, but existing methods use a fixed steering coefficient, effectively operating in open loop.
arXiv:2605. 27000v2 Announce Type: replace-cross Abstract: Repeated sampling with a verifier is the standard way to allocate test-time compute for code generation, with pass@$K$ as the canonical metric.
arXiv:2606. 02465v1 Announce Type: cross Abstract: Reasoning language models (RLMs) achieve strong performance on complex reasoning tasks, but still exhibit substantial multilingual reasoning gaps, largely due to language-understanding failures in non-English inputs.
arXiv:2602. 02250v2 Announce Type: replace-cross Abstract: Kullback-Leibler (KL) divergence regularization is widely used in reinforcement learning, but it becomes infinite under support mismatch and can degenerate in low-noise regimes.
arXiv:2602. 16953v3 Announce Type: replace Abstract: Execution-aware LLM agents offer a promising paradigm for learning from tool feedback, but such feedback can be expensive and slow to obtain, making online reinforcement learning (RL) less practical in certain scenarios.
arXiv:2604. 20861v3 Announce Type: replace-cross Abstract: Semantic IDs (SIDs) provide the discrete item vocabulary used by generative recommendation, but their quality depends on what item evidence is preserved before quantization.
arXiv:2602. 09474v2 Announce Type: replace Abstract: We study reinforcement learning in MDPs whose transition function is stochastic at most steps but may behave adversarially at a fixed subset of $\Lambda$ steps per episode.
arXiv:2606. 00862v1 Announce Type: cross Abstract: Surrogate-assisted evolutionary algorithms (SAEAs) have been widely used for expensive black-box optimization problems.