Related papers: Beyond the Final Answer: Evaluating the Reasoning …

Large Language Models (LLMs) often do not perform well on queries that require the aggregation of information across texts. To better evaluate this setting and facilitate modeling efforts, we introduce TACT - Text And Calculations through…

Inference-time compute scaling has emerged as a powerful technique for improving the reliability of large language model (LLM) agents, but existing methods apply compute uniformly: every decision step receives the same budget regardless of…

The inherent capabilities of a language model (LM) and the reasoning strategies it employs jointly determine its performance in reasoning tasks. While test-time scaling is regarded as an effective approach to tackling complex reasoning…

Graphical User Interface (GUI) agents can automate complex tasks across digital environments, but their development is hindered by the scarcity of high-quality trajectory data for training. Existing approaches rely on expensive human…

Despite the utility of Large Language Models (LLMs) across a wide range of tasks and scenarios, developing a method for reliably evaluating LLMs across varied contexts continues to be challenging. Modern evaluation approaches often use LLMs…

Reinforcement learning (RL) has become the dominant paradigm for improving the performance of language models on complex reasoning tasks. Despite the substantial empirical gains demonstrated by RL-based training methods like GRPO, a…

We introduce PATHWAYS, a benchmark of 250 multi-step decision tasks that test whether web-based agents can discover and correctly use hidden contextual information. Across both closed and open models, agents typically navigate to relevant…

Tool-augmented large language models (LLMs) are usually trained with supervised imitation or coarse-grained reinforcement learning that optimizes single tool calls. Current self-reflection practices rely on heuristic prompts or one-way…

A critical bottleneck in automating AI research is the execution of complex machine learning engineering (MLE) tasks. MLE differs from general software engineering due to computationally expensive evaluation (e.g., model training) and…

This survey explores the development of meta-thinking capabilities in Large Language Models (LLMs) from a Multi-Agent Reinforcement Learning (MARL) perspective. Meta-thinking self-reflection, assessment, and control of thinking processes is…

Looped Language Models (LoopLMs) perform multi-step latent reasoning prior to token generation and outperform conventional LLMs on reasoning benchmarks at smaller parameter budgets. However, attempts to further improve LoopLM reasoning with…

Recent advances in Large Language Models have led to Large Reasoning Models, which produce step-by-step reasoning traces. These traces offer insight into how models think and their goals, improving explainability and helping users follow…

While Large Language Models (LLMs) have shown remarkable advancements in reasoning and tool use, they often fail to generate optimal, grounded solutions under complex constraints. Real-world travel planning exemplifies these challenges,…

Large Language Models (LLMs) have shown impressive capabilities in multi-step reasoning and problem-solving.Recent works introduce multi-agent reflection frameworks where multiple LLM agents critique and refine each other's outputs using…

The combination of LLM agents with external tools enables models to solve complex tasks beyond their knowledge base. Human-designed tools are inflexible and restricted to solutions within the scope of pre-existing tools created by experts.…

Identifying the strategic uses of reformulation in discourse remains a key challenge for computational argumentation. While LLMs can detect surface-level similarity, they often fail to capture the pragmatic functions of rephrasing, such as…

Large Language Model (LLM) agents have demonstrated remarkable generalization capabilities across multi-domain tasks. Existing agent tuning approaches typically employ supervised finetuning on entire expert trajectories. However,…

Despite rapid development, large language models (LLMs) still encounter challenges in multi-turn decision-making tasks (i.e., agent tasks) like web shopping and browser navigation, which require making a sequence of intelligent decisions…

The standard feedback model of reinforcement learning requires revealing the reward of every visited state-action pair. However, in practice, it is often the case that such frequent feedback is not available. In this work, we take a first…

TRUST Agents is a collaborative multi-agent framework for explainable fact verification and fake news detection. Rather than treating verification as a simple true-or-false classification task, the system identifies verifiable claims,…