Related papers: Demand-Driven Context: A Methodology for Building …
Multi-agent systems represent a significant advancement in artificial intelligence, enabling complex problem-solving through coordinated specialized agents. However, these systems face fundamental challenges in context management,…
The performance of Large Language Models (LLMs) is fundamentally determined by the contextual information provided during inference. This survey introduces Context Engineering, a formal discipline that transcends simple prompt design to…
We tackle the task of question generation over knowledge bases. Conventional methods for this task neglect two crucial research issues: 1) the given predicate needs to be expressed; 2) the answer to the generated question needs to be…
Large language model agents increasingly operate through environment-facing scaffolds that expose files, web pages, APIs, and logs. These observations influence tool use, state tracking, and action sequencing, yet their reliability and…
Language environments such as web browsers, code terminals, and interactive simulations emit raw text rather than states, and provide none of the runtime structure that MDP analysis requires. No explicit state space, no observation-to-state…
Documenting tacit knowledge in organizations can be a challenging task due to incomplete initial information, difficulty in identifying knowledgeable individuals, the interplay of formal hierarchies and informal networks, and the need to…
Retrieving real-time information is a fundamental capability for search-integrated agents in real-world applications. However, existing benchmarks are predominantly static and therefore fail to capture the temporal dynamics of information…
Current state-of-the-art large language models are effective in generating high-quality text and encapsulating a broad spectrum of world knowledge. These models, however, often hallucinate and lack locally relevant factual data.…
Spec-driven development (SDD) with AI coding agents provides a structured workflow, but agents often remain "context blind" in large, evolving repositories, leading to hallucinated APIs and architectural violations. We present Spec Kit…
To promote engineering self-aware and self-adaptive software systems in a reusable manner, architectural patterns and the related methodology provide an unified solution to handle the recurring problems in the engineering process. However,…
Large Language Models (LLMs) have shown remarkable prowess in text generation, yet producing long-form, factual documents grounded in extensive external knowledge bases remains a significant challenge. Existing "top-down" methods, which…
The rapid advancement of large language models has fundamentally shifted the bottleneck in AI development from computational power to data availability-with countless valuable datasets remaining hidden across specialized repositories,…
Across millennia, complex societies have faced the same coordination problem of how to organize collective action among cognitively bounded and informationally incomplete individuals. Different civilizations developed different political…
Domain adaptation is a sub-field of machine learning that involves transferring knowledge from a source domain to perform the same task in the target domain. It is a typical challenge in machine learning that arises, e.g., when data is…
Code intelligence is an emerging domain in software engineering, aiming to improve the effectiveness and efficiency of various code-related tasks. Recent research suggests that incorporating contextual information beyond the basic original…
Achieving satisfying performance in machine translation on domains for which there is no training data is challenging. Traditional supervised domain adaptation is not suitable for addressing such zero-resource domains because it relies on…
Communication and interaction among agents have been the subject of extensive investigation since many years. Commitment-based communication, where communicating agents are seen as a debtor agent who is committed to a creditor agent to…
One of the key challenges for multi-agent learning is scalability. In this paper, we introduce a technique for speeding up multi-agent learning by exploiting concurrent and incremental experience sharing. This solution adaptively identifies…
Modern vehicles generate thousands of different discrete events known as Diagnostic Trouble Codes (DTCs). Automotive manufacturers use Boolean combinations of these codes, called error patterns (EPs), to characterize system faults and…
A long-term goal of language agents is to learn and improve through their own experience, ultimately outperforming humans in complex, real-world tasks. However, training agents from experience data with reinforcement learning remains…