Related papers: Why Agent Caching Fails and How to Fix It: Structu…
Modern Large Language Model (LLM) agents promise end to end assistance with real-world software tasks, yet existing benchmarks evaluate LLM agents almost exclusively in pre-baked environments where every dependency is pre-installed. To fill…
Software development is iterative, yet agentic coding benchmarks hide design issues through their single-shot setup. Recent iterative benchmarks attempt to remedy this but heavily constrain an agent's design decision space, making it…
Coding agents are increasingly deployed to autonomously maintain software, including to resolve user-reported issues: a bug report comes in and the agent creates a patch to address it. However, in any real-world deployment, they will…
Agentic artificial intelligence (AI) is a natural fit for Internet of Things (IoT) and edge systems, but edge deployments are often constrained to models around 8 billion parameters or smaller. An important question is: How much…
Prompt injection remains a central obstacle to the safe deployment of large language models, particularly in multi-agent settings where intermediate outputs can propagate or amplify malicious instructions. Building on earlier work that…
Slot-filling and intent detection are well-established tasks in Conversational AI. However, current large-scale benchmarks for these tasks often exclude evaluations of low-resource languages and rely on translations from English benchmarks,…
Large language models (LLMs) are increasingly deployed as autonomous agents in offensive cybersecurity. In this paper, we reveal an interesting phenomenon: different agents exhibit distinct attack patterns. Specifically, each agent exhibits…
Multi-agent systems (MAS) built on large language models promise improved problem-solving through collaboration, yet they often fail to consistently outperform strong single-agent baselines due to error propagation at inter-agent message…
Many real-world tasks involve a mixed-initiative setup, wherein humans and AI systems collaboratively perform a task. While significant work has been conducted towards enabling humans to specify, through language, exactly how an agent…
Long-running autonomous AI agents suffer from a well-documented memory coherence problem: tool-execution success rates degrade 14 percentage points over 72-hour operation windows due to four compounding failure modes in existing flat-file…
The increasing complexity of AI tasks has shifted the paradigm from monolithic models toward multi-agent large language model (LLM) systems. However, these collaborative architectures introduce a critical bottleneck: redundant prefill…
Large language models (LLMs) have shown promise for automated patching, but their effectiveness depends strongly on how they are integrated into patching systems. While prior work explores prompting strategies and individual agent designs,…
From professional research to everyday planning, many tasks are bottlenecked by wide-scale information seeking, which is more repetitive than cognitively complex. With the rapid development of Large Language Models (LLMs), automated search…
Getting a real cybersecurity risk assessment for a small organization is expensive -- a NIST CSF-aligned engagement runs $15,000 on the low end, takes weeks, and depends on practitioners who are genuinely scarce. Most small companies skip…
Large Language Model (LLM)-based coding agents show promise in automating software development tasks, yet they frequently fail in ways that are difficult for developers to understand and debug. While general-purpose LLMs like GPT can…
Large Language Models demonstrate remarkable capabilities yet remain fundamentally probabilistic, presenting critical reliability challenges for enterprise deployment. We introduce the Six Sigma Agent, a novel architecture that achieves…
The revolutionary capabilities of Large Language Models (LLMs) are attracting rapidly growing popularity and leading to soaring user requests to inference serving systems. Caching techniques, which leverage data reuse to reduce computation,…
AI agents are changing the requirements for document parsing. What matters is semantic correctness: parsed output must preserve the structure and meaning needed for autonomous decisions, including correct table structure, precise chart…
Coding agents represent a new paradigm in automated software engineering, combining the reasoning capabilities of Large Language Models (LLMs) with tool-augmented interaction loops. However, coding agents still have severe limitations.…
Does structured intent representation generalize across languages and models? We study PPS (Prompt Protocol Specification), a 5W3H-based framework for structured intent representation in human-AI interaction, and extend prior Chinese-only…