Related papers: The Conversations Beneath the Code: Triadic Data f…

Post-training data plays a pivotal role in shaping the capabilities of Large Language Models (LLMs), yet datasets are often treated as isolated artifacts, overlooking the systemic connections that underlie their evolution. To disentangle…

Open-domain dialogue systems have seen remarkable advancements with the development of large language models (LLMs). Nonetheless, most existing dialogue systems predominantly focus on brief single-session interactions, neglecting the…

As a research-product hybrid group in AI for Software Engineering (AI4SE), we present four key takeaways from our experience developing in-IDE AI coding assistants. AI coding assistants should set clear expectations for usage, integrate…

Agentic AI systems, specifically LLM-driven agents that plan, invoke tools, maintain persistent memory, and delegate tasks to peer agents via protocols such as MCP and A2A, introduce a threat surface that differs materially from standalone…

Software development is a cognitively intensive process requiring multitasking, adherence to evolving workflows, and continuous learning. With the rise of large language model (LLM)-based tools, such as conversational agents (CAs), there is…

Current generative AI systems are increasingly effective at processing explicit knowledge, including retrieving information, summarising documents, generating explanations, and supporting codified workflows. However, high-level expertise…

Long-horizon interactive agents often accumulate large trajectory histories yet still fail to answer questions about earlier events reliably. We argue that the main bottleneck is not context length alone, but the trajectory-to-answer…

Auto-regressive LLM-based software engineering (SWE) agents, henceforth SWE agents, have made tremendous progress (>60% on SWE-Bench Verified) on real-world coding challenges including GitHub issue resolution. SWE agents use a combination…

The integration of Artificial Intelligence (AI) into Integrated Development Environments (IDEs) is reshaping software development, fundamentally altering how developers interact with their tools. This shift marks the emergence of Human-AI…

Static "human data" faces inherent limitations: it is expensive to scale and bounded by the knowledge of its creators. Continuous learning from "experience data" - interactions between agents and their environments - promises to transcend…

Behavioral analysis of tutoring dialogues is essential for understanding student learning, yet manual coding remains a bottleneck. We present a methodology where LLM coding agents autonomously improve the prompts used by LLM classifiers to…

Foundation models have shown impressive adaptation and scalability in supervised and self-supervised learning problems, but so far these successes have not fully translated to reinforcement learning (RL). In this work, we demonstrate that…

Long-horizon tasks that require sustained reasoning and multiple tool interactions remain challenging for LLM agents: small errors compound across steps, and even state-of-the-art models often hallucinate or lose coherence. We identify…

Contemporary multi-agent systems encounter persistent challenges in cross-platform interoperability, dynamic task scheduling, and efficient resource sharing. Agents with heterogeneous implementations often lack standardized interfaces;…

While Large Language Models (LLMs) excel at short-term tasks, scaling them to long-horizon agentic workflows remains challenging. The core bottleneck lies in the scarcity of training data that captures authentic long-dependency structures…

Communication stands as a potent mechanism to harmonize the behaviors of multiple agents. However, existing works primarily concentrate on broadcast communication, which not only lacks practicality, but also leads to information redundancy.…

This paper envisions a transformative paradigm in software engineering, where Artificial Intelligence, embodied in fully autonomous agents, becomes the primary driver of the core software development activities. We introduce a new class of…

Agent communication protocols are becoming critical infrastructure for large language model (LLM) systems that must use tools, coordinate with other agents, and operate across heterogeneous environments. This work presents a human-inspired…

People navigate complex environments using cues, heuristics, and other strategies, which are often adaptive in stable settings. However, as AI increasingly permeates society's information environments, those become more adaptive and…

As large models evolve from conversational assistants into autonomous agents, challenges increasingly arise from long-horizon decision making, tool use, and real environment interaction. Existing agenticinfrastructure remain fragmented…