Researchers propose a theoretical framework to address performance saturation in closed-loop AI systems by identifying how external information can overcome internal feedback limitations.
Researchers have developed an adaptive layer-freezing technique for federated learning to reduce the computational burden of training models in resource-constrained healthcare environments.
A new contrastive framework called SARA aims to improve the robustness of preference-based reinforcement learning against noisy or inaccurate human labeling.
Researchers have developed SOReL, a Bayesian model-based reinforcement learning method that enables hyperparameter selection without requiring online environment interactions.
This paper presents a mathematical framework for reinforcement learning in environments where the underlying dynamics switch between different states.
The SAGA agent framework is proposed to improve long-horizon strategic planning in complex games by better managing relational structures and evolving goals.
This research proposes a framework to transition LLM-based agents from stateless interactions to situated models capable of maintaining temporal continuity for psychological support.
A new study evaluates the effectiveness of belief-based memory architectures in LLM agents using Bayesian inference to manage long-term information.
Researchers have developed a framework called HG-RAG that improves retrieval-augmented generation by utilizing hierarchical graph traversal for more effective knowledge retrieval.
A multi-country study identifies the primary global factors influencing public acceptance of Level 3 autonomous vehicles.
ToolAnchor is a proposed method to help AI agents overcome behavioral inertia and more effectively integrate new tools into their workflows.
The study demonstrates that high transition accuracy in LLM-synthesized world models does not necessarily correlate with effective planning performance.
This paper argues for the application of sociotechnical systems analysis to better understand and mitigate risks in automated decision-making technologies.
A study evaluated the performance of OpenAI's o4-mini model on undergraduate physics problems to assess the reasoning capabilities of current inference-scaling LLMs.
ViPSAM is a new visual prompting framework designed to improve medical image segmentation in non-contrast CT scans by leveraging contrast-enhanced MRI data.
Researchers investigate the efficacy of specialized agentic systems compared to general-purpose LLMs for automating business process workflows.
This research introduces a step-level preference learning method to better align the intermediate decision-making processes of generative agents with human preferences.
Researchers introduced a schema-aware grounding method to improve the accuracy of agentic text-to-SPARQL query generation for knowledge base question answering.
RetroAgent utilizes large language models to navigate structured memory for more effective multi-step retrosynthesis planning in chemical research.
The authors introduce a rollout-based training method to improve the performance of constrained diffusion models in satisfying complex feasibility requirements.
The proposed MAPS framework enables multi-agent dialogue systems to model distinct subjective perspectives and cognitive styles during interaction.
Researchers introduced a benchmark designed to evaluate the accuracy and traceability of LLM agents performing complex structural engineering workflows.
This study investigates common assumptions regarding prompting techniques and dataset usage in the evaluation of large language models for multiple-choice tasks.
The CoreForge project demonstrates an iterative workflow where large language models are used to construct a MaxSAT solver directly from academic literature rather than existing codebases.