Related papers: The Memory Curse: How Expanded Recall Erodes Coope…

Enhancing the reasoning capabilities of Large Language Models (LLMs) is a key strategy for building Agents that "think then act." However, recent observations, like OpenAI's o3, suggest a paradox: stronger reasoning often coincides with…

Large language models (LLMs) have shown great potential in decision-making due to the vast amount of knowledge stored within the models. However, these pre-trained models are prone to lack reasoning abilities and are difficult to adapt to…

Long-context LLMs can infer objectives that are not stated explicitly. This capability is useful for reasoning over documents, code, retrieved evidence, and tool traces, but it also creates a safety risk: harmful intent can be distributed…

Large Language Models (LLMs) are often evaluated against ideals of perfect Bayesian inference, yet growing evidence suggests that their in-context reasoning exhibits systematic forgetting of past information. Rather than viewing this…

LLM-based agents have been extensively applied across various domains, where memory stands out as one of their most essential capabilities. Previous memory mechanisms of LLM-based agents are manually predefined by human experts, leading to…

An ideal embodied agent should possess lifelong learning capabilities to handle long-horizon and complex tasks, enabling continuous operation in general environments. This not only requires the agent to accurately accomplish given tasks but…

Effectively processing long contexts remains a fundamental yet unsolved challenge for large language models (LLMs). Existing single-LLM-based methods primarily reduce the context window or optimize the attention mechanism, but they often…

A core challenge for faithful LLM role-playing is sustaining consistent characterization throughout long, open-ended dialogues, as models frequently fail to recall and accurately apply their designated persona knowledge without explicit…

With the widespread use of large language models (LLMs), understanding their potential failure modes during user interactions is essential. In practice, users often pose multiple questions in a single conversation with LLMs. Therefore, in…

The use of large language models either as decision support systems, or in agentic workflows, is rapidly transforming the digital ecosystem. However, the understanding of LLM decision-making under uncertainty remains limited. We study LLM…

Achieving effective test-time scaling requires models to engage in In-Context Exploration -- the intrinsic ability to generate, verify, and refine multiple reasoning hypotheses within a single continuous context. Grounded in State Coverage…

Modern language agents must operate over long-horizon, multi-turn histories, yet deploying such agents with Small Language Models (SLMs) remains fundamentally difficult. Full-context prompting causes context overflow, flat retrieval exposes…

The recent work by Shojaee et al. (2025), titled The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity, presents a compelling empirical finding, a reasoning cliff, where…

Large Language Models (LLMs) have made significant progress in open-ended dialogue, yet their inability to retain and retrieve relevant information from long-term interactions limits their effectiveness in applications requiring sustained…

The rise of Large Reasoning Models (LRMs) signifies a paradigm shift toward advanced computational reasoning. Yet, this progress disrupts traditional agent frameworks, traditionally anchored by execution-oriented Large Language Models…

Despite their impressive capabilities, LLMs exhibit a basic generalization failure known as the Reversal Curse, where they struggle to learn reversible factual associations. Understanding why this occurs could help identify weaknesses in…

Large language models (LMs) have been shown to memorize parts of their training data, and when prompted appropriately, they will emit the memorized training data verbatim. This is undesirable because memorization violates privacy (exposing…

Memory is critical for enabling large language model (LLM) based agents to maintain coherent behavior over long-horizon interactions. However, existing agent memory systems suffer from two key gaps: they rely on a one-size-fits-all memory…

Previous studies suggest that punishment is a useful way to promote cooperation in the well-mixed public goods game, whereas it still lacks specific evidence that punishment maintains cooperation in spatial prisoner's dilemma game as well.…

Large language models (LLMs) are increasingly deployed as intelligent agents that reason, plan, and interact with their environments. To effectively scale to long-horizon scenarios, a key capability for such agents is a memory mechanism…