Policy optimisation, reward modelling and RLHF — how models are trained by feedback rather than by labels.
arXiv:2609.24480v1 Announce Type: cross Abstract: Deploying Large Language Models (LLMs) in healthcare requires robust performance across two complementary dimensions - diagnostic reasoning: the conv...
The paper investigates how to balance supervised fine‑tuning (SFT) and reinforcement learning (RL) for long‑horizon advertising agents that must retrieve, reason, and execute code on distributed business data. By classifying training trajectories into Imitation, Lift, and Discovery regimes, the authors develop a diagnostic that predicts which training path to follow, and then apply a targeted SFT‑then‑RL strategy. Across 18 feature‑specific experiments on GPT‑OSS 120B, this approach yields positive gains on most advertiser skills, reduces leakage, and achieves higher mean improvements with 43% less RL compute.
The paper introduces the Universal Observatory Graph (UOG), an AI‑driven framework that models autonomous observatories at L2 Lagrange points as nodes in a weighted graph, with edges defined by interplanetary distance, latency, transmission power, and reliability. Using a six‑observatory Solar System configuration (Earth, Mars, Jupiter, Saturn, Uranus, Neptune), the authors evaluate instantaneous sky coverage with three methods, all showing complete network union coverage and modest overlap. They formulate communication routing as a finite‑horizon Markov decision process solved via tabular Q‑learning, identifying the Earth‑Saturn‑Uranus‑Neptune path as the highest‑return route among 41 feasible simple paths under a four‑hop constraint.
arXiv:2609.22256v1 Announce Type: new Abstract: Effective workplace negotiation requires balancing multiple objectives, including achieving task goals, preserving professional relationships, and reso...
arXiv:2609.22327v1 Announce Type: cross Abstract: Visual graph reasoning requires answering graph-theoretic questions directly from graph images, where graph topology and state are conveyed visually...
The paper investigates whether contrastive activation directions in large language models truly capture a functional valence axis or merely reflect correlated features of the contrast used to extract them. By conducting controlled interventions in a maze task across multiple LLM checkpoints, the authors show that directions fitted on one explicit outcome encoding transfer well to another, suggesting the readout is not tied to surface form. However, when the same outcome is achieved through announced versus unannounced histories, transfer degrades, indicating the direction remains strongly conditioned on prior announcements and does not represent a history‑invariant scalar valence state.
arXiv:2609.23590v1 Announce Type: new Abstract: Battery energy storage system (BESS) dispatch must preserve operational feasibility while declining price spreads reduce the margin available to pay fo...
FLARE introduces a dense supervision paradigm for long‑horizon coding agents, leveraging a Generative Reward Model (GRM) trained via the RADAR diagnostic framework. The GRM provides real‑time, step‑level risk feedback, enabling FLARE to act as an active scaffold that intercepts high‑risk steps during inference and supplies structured signals for post‑training fine‑tuning and reinforcement learning. Experiments show FLARE outperforms existing methods, achieving a 5× reduction in token consumption and significant performance gains in both supervised fine‑tuning and RL settings.
arXiv:2609.23875v1 Announce Type: new Abstract: The rapid growth of resident space objects is increasing the complexity of space situational awareness sensor tasking, challenging classical optimizati...
arXiv:2609.24103v1 Announce Type: new Abstract: In many real-world planning tasks, agents must tackle uncertainty about the environment's state and variability in the outcomes of any chosen policy. W...
arXiv:2609.24259v1 Announce Type: new Abstract: The effectiveness of agent memory ultimately depends on whether the underlying LLM gives each memory in context an appropriate degree of influence over...
arXiv:2609.24380v1 Announce Type: new Abstract: RLVR has substantially improved the reasoning capabilities of LLMs. However, existing methods typically parameterize temporal progression in the Markov...
arXiv:2410.23912v3 Announce Type: replace-cross Abstract: The reasoning abilities of large language models (LLMs) have improved with chain-of-thought (CoT) prompting, allowing models to solve complex...
arXiv:2406.03678v2 Announce Type: replace Abstract: On-policy reinforcement learning methods, like Trust Region Policy Optimization (TRPO) and Proximal Policy Optimization (PPO), often demand extensi...
arXiv:2410.14606v3 Announce Type: replace Abstract: Learning from a stream of experience as it arrives, also known as streaming learning, is a core part of natural learning. However, reliable streami...
Lingshu is a medical‑specialized multimodal large language model that addresses key limitations of existing medical MLLMs, such as narrow knowledge coverage, hallucinations, and weak reasoning. The authors curate a comprehensive dataset combining medical imaging, texts, and general‑domain data, then train Lingshu in multiple stages to embed medical expertise and improve task performance. They also introduce MedEvalKit, a unified evaluation framework, and demonstrate that Lingshu outperforms current open‑source multimodal models on multimodal QA, text‑based QA, and medical report generation.
arXiv:2604.24952v2 Announce Type: replace Abstract: Human visual preferences are inherently multi-dimensional, encompassing aesthetics, detail fidelity, and semantic alignment. However, existing data...
arXiv:2605.11217v2 Announce Type: replace Abstract: The model context protocol (MCP) has been widely adopted as an open standard enabling the seamless integration of generative AI agents. However, wh...
arXiv:2609.23184v1 Announce Type: new Abstract: Embodied world models learn to predict future physical dynamics from visual observations and control signals, where physical knowledge is implicitly en...
arXiv:2406.03894v2 Announce Type: replace Abstract: Proximal Policy Optimization (PPO) is a popular model-free reinforcement learning algorithm, esteemed for its simplicity and efficacy. However, due...