Related papers: SEAL: Self-Evolving Agentic Learning for Conversat…

Reinforcement learning (RL) has been pivotal in enhancing the reasoning capabilities of large language models (LLMs), but it often suffers from limited exploration and entropy collapse, where models exploit a narrow set of solutions,…

Reasoning is a fundamental cognitive process underlying inference, problem-solving, and decision-making. While large language models (LLMs) demonstrate strong reasoning capabilities in closed-world settings, they struggle in open-ended and…

Recent advances in large language models (LLMs) have enabled the development of autonomous agents capable of complex reasoning and multi-step problem solving. However, these agents struggle to adapt to specialized environments and do not…

Document Visual Question Answering (VQA) requires models to not only extract accurate textual answers but also precisely localize them within document images, a capability critical for interpretability in high-stakes applications. However,…

Widely used language-model benchmarks are increasingly saturated, with frontier systems often receiving near-tied scores that standard metrics cannot resolve. Rather than constructing harder alternatives, we ask whether existing tasks can…

Answering complex, long-context questions remains a major challenge for large language models (LLMs) as it requires effective question clarifications and context retrieval. We propose Agentic Long-Context Understanding (AgenticLU), a…

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…

Despite the significant improvements achieved by large language models (LLMs) in English reasoning tasks, these models continue to struggle with multilingual reasoning. Recent studies leverage a full-parameter and two-stage training…

While many advanced LLMs are designed to handle long sequence data, we can still observe notable quality degradation even within the sequence limit. In this work, we introduce a novel approach called Scaling to Emphasize Attention for…

Table understanding requires structured, multi-step reasoning. Large Language Models (LLMs) struggle with it due to the structural complexity of tabular data. Recently, multi-agent frameworks for SQL generation have shown promise in…

We introduce SealQA, a new challenge benchmark for evaluating SEarch-Augmented Language models on fact-seeking questions where web search yields conflicting, noisy, or unhelpful results. SealQA comes in three flavors: (1) Seal-0 (main) and…

Large Language Models (LLMs), despite their success in question answering, exhibit limitations in complex multi-hop question answering (MQA) tasks that necessitate non-linear, structured reasoning. This limitation stems from their inability…

Large language models (LLMs) have been widely integrated into information retrieval to advance traditional techniques. However, effectively enabling LLMs to seek accurate knowledge in complex tasks remains a challenge due to the complexity…

Large Language Model (LLM)-based agents exhibit systemic failures in compositional generalization, limiting their robustness in interactive environments. This work introduces AGEL-Comp, a neuro-symbolic AI agent architecture designed to…

The rapid advancement of chat-based language models has led to remarkable progress in complex task-solving. However, their success heavily relies on human input to guide the conversation, which can be challenging and time-consuming. This…

With the recent advancements in reasoning capabilities, tool calling using MCP servers and Audio Language Models (ALMs), development and integration of multi-modal agents (with voice and text support) has come to the industry forefront.…

Large language models have been shown to suffer from reasoning inconsistency issues. That is, they fail more in situations unfamiliar to the training data, even though exact or very similar reasoning paths exist in more common cases that…

The evolution of Large Language Models (LLMs) from passive text generators to autonomous, goal-driven systems represents a fundamental shift in artificial intelligence. This chapter examines the emergence of agentic AI systems that…

Progress in long-context reasoning for large language models (LLMs) has lagged behind other recent advances. This gap arises not only from the intrinsic difficulty of processing long texts, but also from the scarcity of reliable human…

Making the content generated by Large Language Model (LLM), accurate, credible and traceable is crucial, especially in complex knowledge-intensive tasks that require multi-step reasoning and each step needs knowledge to solve.…