Related papers: Why Retrying Fails: Context Contamination in LLM A…

Long-horizon tasks that require sustained reasoning and multiple tool interactions remain challenging for LLM agents: small errors compound across steps, and even state-of-the-art models often hallucinate or lose coherence. We identify…

Large Language Model (LLM) agents trained with reinforcement learning (RL) show great promise for solving complex, multi-step tasks. However, their performance is often crippled by "Context Explosion", where the accumulation of long text…

Automating penetration testing is crucial for enhancing cybersecurity, yet current Large Language Models (LLMs) face significant limitations in this domain, including poor error handling, inefficient reasoning, and an inability to perform…

With the rise of Large Language Models (LLMs) in recent years, abundant new opportunities are emerging, but also new challenges, among which contamination is quickly becoming critical. Business applications and fundraising in Artificial…

Large Language Models (LLMs) have demonstrated remarkable capabilities in comprehending and analyzing lengthy sequential inputs, owing to their extensive context windows that allow processing millions of tokens in a single forward pass.…

Agents powered by Large Language Models (LLMs) have recently demonstrated impressive capabilities in various tasks. Still, they face limitations in tasks requiring specific, structured knowledge, flexibility, or accountable decision-making.…

Early-stage startup investment is a high-risk endeavor characterized by scarce data and uncertain outcomes. Traditional machine learning approaches often require large, labeled datasets and extensive fine-tuning, yet remain opaque and…

Although existing model editing methods perform well in recalling exact edit facts, they often struggle in complex scenarios that require deeper semantic understanding rather than mere knowledge regurgitation. Leveraging the strong…

The rapid advancement of large language models (LLMs) has heightened concerns about benchmark data contamination (BDC), where models inadvertently memorize evaluation data during the training process, inflating performance metrics, and…

The quality of AI-generated output is often attributed to prompting technique, but extensive empirical observation suggests that context completeness may be more strongly associated with output quality. This paper introduces Context…

Multi-agent systems can improve reliability, yet under a fixed inference budget they often help, saturate, or even collapse. We develop a minimal and calibratable theory that predicts these regimes from three binding constraints of modern…

Large language models show promise as autonomous decision-making agents, yet their deployment in high-stakes domains remains fraught with risk. Without architectural safeguards, LLM agents exhibit catastrophic brittleness: identical…

LLM-based coding agents have shown strong performance on automated issue resolution benchmarks, yet existing evaluations largely focus on final task success, providing limited insight into how agents retrieve and use code context during…

Recent generations of language models have introduced Large Reasoning Models (LRMs) that generate detailed thinking processes before providing answers. While these models demonstrate improved performance on reasoning benchmarks, their…

Large language models (LLMs) increasingly rely on long-context processing, but expanding context windows introduces substantial computational and financial costs. Existing context reduction approaches, including retrieval and memory…

Context window expansion is often treated as a straightforward capability upgrade for LLMs, but we find it systematically fails in multi-agent social dilemmas. Across 7 LLMs and 4 games over 500 rounds, expanding accessible history degrades…

Current LLM agents are proficient at calling isolated APIs but struggle with the "last mile" of commercial software automation. In real-world scenarios, tools are not independent; they are atomic, interdependent, and prone to environmental…

Large language model (LLM) self-correction -- the ability to detect and fix errors in generated outputs -- remains largely ad hoc, relying on generic prompts such as "please reconsider your answer" without systematic error analysis or…

Large language model (LLM) agents are fundamentally bottlenecked by finite context windows on long-horizon tasks. As trajectories grow, retaining tool outputs and intermediate reasoning in-context quickly becomes infeasible: the working…

Large Language Models (LLMs) have demonstrated impressive capabilities in code completion tasks, where they assist developers by predicting and generating new code in real-time. However, existing LLM-based code completion systems primarily…