· ai
[Paper] How Far Are We from Genuinely Useful Deep Research Agents?
Deep Research Agents (DRAs) aim to automatically produce analyst-level reports through iterative information retrieval and synthesis. However, most existing DRA...
-
- · ai
[Paper] Agentic Policy Optimization via Instruction-Policy Co-Evolution
Reinforcement Learning with Verifiable Rewards (RLVR) has advanced the reasoning capability of large language models (LLMs), enabling autonomous agents that can...
- · ai
[Paper] An Empirical Study of Agent Developer Practices in AI Agent Frameworks
The rise of large language models (LLMs) has sparked a surge of interest in agents, leading to the rapid growth of agent frameworks. Agent frameworks are softwa...
- · ai
[Paper] Rectifying LLM Thought from Lens of Optimization
Recent advancements in large language models (LLMs) have been driven by their emergent reasoning capabilities, particularly through long chain-of-thought (CoT) ...
- · ai
[Paper] Latent Debate: A Surrogate Framework for Interpreting LLM Thinking
Understanding the internal thinking process of Large Language Models (LLMs) and the cause of hallucinations remains a key challenge. To this end, we introduce l...
- · ai
[Paper] HERMES: Heterogeneous Application-Enabled Routing Middleware for Edge-IoT Systems
The growth of the Internet of Things has enabled a new generation of applications, pushing computation and intelligence toward the network edge. This trend, how...
- · devops
[Paper] Trace-based, time-resolved analysis of MPI application performance using standard metrics
Detailed trace analysis of MPI applications is essential for performance engineering, but growing trace sizes and complex communication behaviour often render c...
- · ai
[Paper] Integrating Artificial Intelligence and Mixed Integer Linear Programming: Explainable Graph-Based Instance Space Analysis in Air Transportation
This paper analyzes the integration of artificial intelligence (AI) with mixed integer linear programming (MILP) to address complex optimization challenges in a...
- · software
[Paper] Generating REST API Tests With Descriptive Names
Automated test generation has become a key technique for ensuring software quality, particularly in modern API-based architectures. However, automatically gener...
- · ai
[Paper] Revisiting Direct Encoding: Learnable Temporal Dynamics for Static Image Spiking Neural Networks
Handling static images that lack inherent temporal dynamics remains a fundamental challenge for spiking neural networks (SNNs). In directly trained SNNs, static...
- · ai
[Paper] Current Challenges of Symbolic Regression: Optimization, Selection, Model Simplification, and Benchmarking
Symbolic Regression (SR) is a regression method that aims to discover mathematical expressions that describe the relationship between variables, and it is often...
- · ai
[Paper] Morphling: Fast, Fused, and Flexible GNN Training at Scale
Graph Neural Networks (GNNs) present a fundamental hardware challenge by fusing irregular, memory-bound graph traversals with regular, compute-intensive dense m...