Related papers: State Contamination in Memory-Augmented LLM Agents

Large language models (LLMs) have recently demonstrated impressive capabilities in reasoning tasks. Currently, mainstream LLM reasoning frameworks predominantly focus on scaling up inference-time sampling to enhance performance. In…

We study reinforcement learning (RL) fine-tuning of large language model (LLM) agents for long-horizon multi-turn tool use, where context length quickly becomes a fundamental bottleneck. Existing RL pipelines can suffer from degraded…

Large language model (LLM) agents achieve impressive single-task performance but commonly exhibit repeated failures, inefficient exploration, and limited cross-task adaptability. Existing reflective strategies (e.g., Reflexion, ReAct)…

The widespread adoption of Large Language Models (LLMs) in critical applications has introduced severe reliability and security risks, as LLMs remain vulnerable to notorious threats such as hallucinations, jailbreak attacks, and backdoor…

Modern news is often comprehensive, weaving together information from diverse domains, including technology, finance, and agriculture. This very comprehensiveness creates a challenge for interpretation, as audiences typically possess…

Large Language Models (LLMs) have shown promise as decision-makers in dynamic settings, but their stateless nature necessitates creating a natural language representation of history. We present a unifying framework for systematically…

The open-endedness of large language models (LLMs) combined with their impressive capabilities may lead to new safety issues when being exploited for malicious use. While recent studies primarily focus on probing toxic outputs that can be…

Persistent language-model agents increasingly combine tool use, tiered memory, reflective prompting, and runtime adaptation. In such systems, behavior is shaped not only by current prompts but by mutable internal conditions that influence…

The rapid adoption of Large Language Model (LLM) agents and multi-agent systems enables remarkable capabilities in natural language processing and generation. However, these systems introduce security vulnerabilities that extend beyond…

Large language model (LLM) agents face fundamental limitations in long-horizon reasoning due to finite context windows, making effective memory management critical. Existing methods typically handle long-term memory (LTM) and short-term…

LLM agents increasingly operate in open-ended environments spanning hundreds of sequential episodes, yet they remain largely stateless: each task is solved from scratch without converting past experience into better future behavior. The…

Retrieval-Augmented Generation (RAG) mitigates LLM hallucinations but introduces a critical vulnerability: corpus integrity. We present SilentRetrieval, a two-stage data poisoning attack that hijacks RAG systems through adversarially…

We study behavioral alignment and representation dynamics of large language model (LLM) agents in financial decision environments. Using TradeArena, an auditable trading-agent testbed with risk reports, execution simulation, memory, and…

To tackle long-context reasoning tasks without the quadratic complexity of standard attention mechanisms, approaches based on agent memory have emerged, which typically maintain a dynamically updated memory when linearly processing document…

As large language models (LLMs) are increasingly deployed as autonomous agents, understanding how strategic behavior emerges in multi-agent environments has become an important alignment challenge. We take a neutral empirical stance and…

State space models (SSMs) have emerged as an efficient alternative to Transformer models for language modeling, offering linear computational complexity and constant memory usage as context length increases. However, despite their…

Language models (LMs) rely on their parametric knowledge augmented with relevant contextual knowledge for certain tasks, such as question answering. However, the contextual knowledge can contain private information that may be leaked when…

Modern large language models (LLMs) exhibit critical vulnerabilities to poison pill attacks: localized data poisoning that alters specific factual knowledge while preserving overall model utility. We systematically demonstrate these attacks…

Memory systems often organize user-agent interactions as retrievable external memory and are crucial for long-running agents by overcoming the limited context windows of LLMs. However, existing memory systems invoke LLMs to process every…

Large language models face challenges in long-context question answering, where key evidence of a query may be dispersed across millions of tokens. Existing works equip large language models with a memory buffer that is dynamically updated…