Related papers: More Is Not Always Better: Cross-Component Interfe…
We present a domain-grounded framework and benchmark for tool-aware plan generation in contact centers, where answering a query for business insights, our target use case, requires decomposing it into executable steps over structured tools…
Multi-agent LLM frameworks are widely used to accelerate the development of agent systems powered by large language models (LLMs). These frameworks impose distinct architectural structures that govern how agents interact, store information,…
When an LLM-based embodied agent fails at a household task, the culprit could be misidentified objects, forgotten sub-goals, or poor action sequencing -- yet existing benchmarks report only a single success rate, making it impossible to…
Large Language Models (LLMs), such as OpenAI-o1 and DeepSeek-R1, have demonstrated strong reasoning capabilities. To further enhance LLM capabilities, recent agentic systems, such as Deep Research, incorporate web interactions into LLM…
Large Language Models (LLMs) are increasingly utilized in multi-agent systems (MAS) to enhance collaborative problem-solving and interactive reasoning. Recent advancements have enabled LLMs to function as autonomous agents capable of…
Structured LLM routing is often treated as a prompt-engineering problem. We argue that it is, more fundamentally, a systems-level burden-allocation problem. As large language models (LLMs) become core control components in agentic AI…
The reasoning capabilities of LLM (Large Language Model) are widely acknowledged in recent research, inspiring studies on tool learning and autonomous agents. LLM serves as the "brain" of the agent, orchestrating multiple tools for…
Multi-agent LLM systems have demonstrated impressive capabilities in complex collaborative tasks, yet most frameworks treat communication as instantaneous and free, overlooking a fundamental constraint in real world teamwork, collaboration…
As network deployments become denser, interference arises as a dominant performance degradation factor. To confront with this trend, Long Term Evolution (LTE) incorporated features aiming at enabling cooperation among different base…
Recent studies show that LLMs possess different skills and specialize in different tasks. In fact, we observe that their varied performance occur in several levels of granularity. For example, in the code optimization task, code LLMs excel…
Automated evidence-based misinformation detection systems, which evaluate the veracity of short claims against evidence, lack comprehensive analysis of their adversarial vulnerabilities. Existing black-box text-based adversarial attacks are…
While integrating tools like Code Interpreter and Search has significantly enhanced Large Language Model (LLM) reasoning in models like ChatGPT Agent and Gemini-Pro, practical guidance on optimal tool use is lacking. The core challenge is…
LLM-based coding agents can localize bugs, generate patches, and run tests with diminishing human oversight, yet the scaffolding code that surrounds the language model (the control loop, tool definitions, state management, and context…
The prevailing assumption in agent orchestration is that more context is better. We test this on multi-agent software design across 10 tasks, 7 context-injection conditions, and over 2,700 runs, and find a crossover effect: the same…
Recent advances in language model (LM) agents have demonstrated significant potential for automating complex real-world tasks. To make progress on these difficult tasks, LM agent architectures have become increasingly complex, often…
Large Language Models (LLMs) are widely used by students, yet their tendency to provide fast and complete answers may discourage reflection and foster overconfidence. We examined how alternative LLM interaction designs support deeper…
Credible safety plans for advanced AI development require methods to verify agent behavior and detect potential control deficiencies early. A fundamental aspect is ensuring agents adhere to safety-critical principles, especially when these…
Large language models still struggle with contest-level programming, while many agentic remedies rely on massive inference-time sampling or expensive multi-stage post-training. We study when execution feedback reliably helps an LLM CP…
Ranking LLMs via pairwise human feedback underpins current leaderboards for open-ended tasks, such as creative writing and problem-solving. We analyze ~89K comparisons in 116 languages from 52 LLMs from Arena, and show that the best-fit…
Multi-agent LLM systems decompose workflows across agents, tools, shared context, memory, and decision gates. This modularity improves interpretability, but creates a propagation risk: a bounded perturbation to one component can be reused…