Related papers: LLM Agents Already Know When to Call Tools -- Even…

Proof engineering is notoriously labor-intensive: proofs that are straightforward on paper often require lengthy scripts in theorem provers. Recent advances in large language models (LLMs) create new opportunities for proof automation:…

Embodied robotic systems increasingly rely on large language model (LLM)-based agents to support high-level reasoning, planning, and decision-making during interactions with the environment. However, invoking LLM reasoning introduces…

This study investigates the reasoning robustness of large language models (LLMs) on mathematical problem-solving tasks under systematically introduced input perturbations. Using the GSM8K dataset as a controlled testbed, we evaluate how…

Fine-tuning LLMs for classification typically maps inputs directly to labels. We ask whether attaching brief explanations to each label during fine-tuning yields better models. We evaluate conversational response quality along three axes:…

A long-lived LLM agent, such as OpenClaw, earns its value by acting on a user's preferences and constraints across sessions, not just the current request. Yet today's agents keep what a user volunteers but rarely ask for what stays…

Existing benchmarks for tool-augmented language models (TaLMs) lack fine-grained control over task difficulty and remain vulnerable to data contamination. We present FuncBenchGen, a unified, contamination-free framework that evaluates TaLMs…

Small language models (SLMs) enable scalable tool-augmented multi-agent systems where multiple SLMs handle subtasks orchestrated by a powerful coordinator. However, they struggle with tool-use tasks, particularly in selecting appropriate…

Temporal Knowledge Graph Question Answering (TKGQA) is challenging because it requires multi-hop reasoning under complex temporal constraints. Recent LLM-based approaches have improved semantic modeling for this task, but many still rely on…

Large language model (LLM) agents rely on external tools to solve complex tasks, but real-world toolsets often contain redundant tools with overlapping names and descriptions, introducing ambiguity and reducing selection accuracy. LLMs also…

As large language models (LLMs) are applied across diverse domains, the ability to selectively unlearn specific information is becoming increasingly essential. For instance, LLMs are expected to selectively provide confidential information…

Reinforcement learning (RL) trained language model agents with tool access are increasingly deployed in coding assistants, research tools, and autonomous systems. We introduce the Reward Hacking Benchmark (RHB), a suite of multi-step tasks…

When deploying LLMs in agentic architectures requiring real-time decisions under temporal constraints, we assume they reliably determine whether action windows remain open or have closed. This assumption is untested. We characterize…

Many state-of-the-art LLMs are trained to think before giving their answer. Reasoning can greatly improve language model capabilities, but it also makes them less interactive: given a new input, a model must stop thinking before it can…

Large language model (LLM) agents are moving beyond prompting alone. ChatGPT marked the rise of general-purpose LLM assistants, DeepSeek showed that on-policy reinforcement learning with verifiable rewards can improve reasoning and tool…

Temporal reasoning is pivotal for Large Language Models (LLMs) to comprehend the real world. However, existing works neglect the real-world challenges for temporal reasoning: (1) intensive temporal information, (2) fast-changing event…

Large language models often default to step-by-step computation even when efficient numerical shortcuts are available. This raises a basic question: do they exhibit number sense in a human-like behavioral sense, i.e., the ability to…

Large Language Models (LLMs) are widely deployed in reasoning, planning, and decision-making tasks, making their trustworthiness critical. A significant and underexplored risk is intentional deception, where an LLM deliberately fabricates…

LLM agents increasingly act by writing code, yet a split persists between the runtime that drives the agent and the code the model writes. The runtime owns the loop, context, and control flow, and the model has little say over any of them.…

Large language models deployed as agents increasingly interact with external systems through tool calls--actions with real-world consequences that text outputs alone do not carry. Safety evaluations, however, overwhelmingly measure…

Agents powered by large language models have shown remarkable abilities in solving complex tasks. However, most agent systems remain reactive, limiting their effectiveness in scenarios requiring foresight and autonomous decision-making. In…