Related papers: Omission Constraints Decay While Commission Constr…

Modern LLM based agents are no longer passive text generators. They read repositories, call tools, browse the web, execute code, maintain memory, communicate with other agents, and act through long horizon workflows. This shift moves the…

LLM agents do not act on raw interaction history; they act on a bounded decision state assembled by truncation, summarization, reordering, and rewriting. If directive-bearing state is dropped, weakened, or rebound during that step, an agent…

Solving complex or long-horizon problems often requires large language models (LLMs) to use external tools and operate over a significantly longer context window. New LLMs enable longer context windows and support tool calling capabilities.…

Large Language Model (LLM) agents demonstrate strong performance in autonomous code generation under loose specifications. However, production-grade software requires strict adherence to structural constraints, such as architectural…

Large language models (LLMs) in research and development toolchains produce output that triggers attribution of agency and understanding -- a cognitive illusion that degrades verification behavior and trust calibration. No existing…

When an LLM agent fails a multi-step tool-augmented task and retries, the failed attempt typically remains in its context window -- contaminating the next attempt and elevating the per-step error rate beyond the base level. This…

Large language models (LLMs) are increasingly deployed as autonomous agents that make sequences of decisions over extended interactions in high-stakes domains. However, the behavior of LLMs under sustained authority pressure is still an…

Large Language Models (LLMs) are increasingly used as core dependencies in software systems. However, the hosted LLM services evolve continuously through provider-side updates without explicit version changes. These silent updates can…

Managing agent context (e.g., thought and observation) during multi-turn agent-environment interactions is an emerging strategy to improve agent efficiency. However, existing studies treat the entire interaction trajectories equally,…

Large Language Models (LLMs) frequently prioritize conflicting in-context information over pre-existing parametric memory, a phenomenon often termed sycophancy or compliance. However, the mechanistic realization of this behavior remains…

Large Language Model (LLM)-based agents are increasingly used as autonomous subordinates that carry out tasks for users. This raises the question of whether they may also engage in deception, similar to how individuals in human…

Large language models (LLMs) exhibiting test-time scaling behavior, such as extended reasoning traces and self-verification, have demonstrated remarkable performance on complex, long-term reasoning tasks. However, the robustness of these…

LLM agents increasingly rely on persistent state, including transcripts, summaries, retrieved context, and memory buffers, to support long-horizon interaction. This makes safety depend not only on individual model outputs, but also on what…

Large Language Models (LLMs) demonstrate exceptional performance across diverse tasks by leveraging pre-trained (i.e., parametric) and external (i.e., contextual) knowledge. While substantial efforts have been made to enhance the…

Large language models have demonstrated impressive retrieval-augmented capabilities. However, a crucial area remains underexplored: their ability to appropriately adapt responses to the certainty of the retrieved information. It is a…

Large language models (LLMs) exhibit degraded performance under prompt compression, but the mechanisms remain poorly understood. We introduce the Compression-Decay Comprehension Test (CDCT), a benchmark that independently measures…

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…

Large Language Models (LLMs) often exhibit behavioral artifacts such as laziness (premature truncation of responses or partial compliance with multi-part requests), decoding suboptimality (failure to select higher-quality sequences due to…

LLMs reliably correct false claims when presented in isolation, yet when the same claims are embedded in task-oriented requests, they often comply rather than correct. We term this failure mode \emph{correction suppression} and construct a…

Operating LLMs as coordinated multi-agent research systems over multi-hour runs surfaces failure modes that single-shot evaluation cannot: upstream providers throttle without warning, sub-agents drift the task to fit accessible tools,…