Related papers: Omission Constraints Decay While Commission Constr…

Large Language Model (LLM) agents increasingly act through external tools, making their safety contingent on tool-call workflows rather than text generation alone. While recent benchmarks evaluate agents across diverse environments and risk…

Human cognition, driven by complex neurochemical processes, oscillates between imagination and reality and learns to self-correct whenever such subtle drifts lead to hallucinations or unsafe associations. In recent years, LLMs have…

Large language model (LLM) agents on multi-step tasks suffer reasoning degradation, looping, drift, stuck states, at rates up to 30% on hard tasks. Current solutions include hard step limits (abrupt) or LLM-as-judge monitoring (10-15%…

Large Language Models (LLMs) have enabled collaborative Multi-Agent (MA) systems, where interacting agents improve performance through diverse reasoning and iterative refinement. However, these systems remain vulnerable to error…

Multimodal large language models (MLLMs) are increasingly deployed in open-ended, real-world environments where inputs are messy, underspecified, and not always trustworthy. Unlike curated benchmarks, these settings frequently involve…

System Instructions in Large Language Models (LLMs) are commonly used to enforce safety policies, define agent behavior, and protect sensitive operational context in agentic AI applications. These instructions may contain sensitive…

Abstention Ability (AA) is a critical aspect of Large Language Model (LLM) reliability, referring to an LLM's capability to withhold responses when uncertain or lacking a definitive answer, without compromising performance. Although…

Large language models (LLMs) are increasingly used in clinical and care settings. This exploratory study investigates whether LLMs exhibit sycophantic behavior - adapting their responses to social expectation signals rather than maintaining…

Colluding language-model agents can hide coordination in messages that remain policy-compliant at the surface level. We present CLBC, a protocol where generation and admission are separated: a message is admitted to transcript state only if…

Large language models can follow complex instructions in a single turn, yet over long multi-turn interactions they often lose the thread of instructions, persona, and rules. This degradation has been measured behaviorally but not…

Sparsity has long been a central theme in LLM efficiency, but its role in context processing remains unresolved. As LLM workloads shift toward longer contexts and agentic interactions, the compute and memory bottlenecks of attention become…

When researchers iteratively refine ideas with large language models, do the models preserve fidelity to the original objective? We introduce DriftBench, a benchmark for evaluating constraint adherence in multi-turn LLM-assisted scientific…

Large language models (LLMs) achieve impressive performance when a task is fully specified in a single turn, yet the same models lose up to 39% of that performance when the identical task is revealed incrementally across multiple turns, a…

As large language models (LLMs) integrate into collaborative teams, their social conformity -- the tendency to align with majority opinions -- has emerged as a key concern. In humans, conformity arises from informational influence (rational…

Long-horizon LLM agents accumulate growing conversation histories that eventually exceed the model's context window. Context compaction via LLM-based summarization keeps the conversation bounded, but summarization is inherently lossy and…

The deployment of Large Language Models (LLMs) as tool-using agents causes their alignment training to manifest in new ways. Recent work finds that language models can use tools in ways that contradict the interests or explicit instructions…

Self-consistency (SC) improves the performance of large language models (LLMs) across various tasks and domains that involve short content. However, does this support its effectiveness for long-context problems? We challenge the assumption…

Existing benchmarks for Large Language Model (LLM) agents focus on task completion under idealistic settings but overlook reliability in real-world, user-facing applications. In domains, such as in-car voice assistants, users often issue…

Ensuring that large language models (LLMs) remain both helpful and harmless poses a significant challenge: fine-tuning on repetitive safety datasets, where unsafe prompts are paired with standard refusal templates, often leads to false…

Large language models (LLMs) can be influenced by harmful or irrelevant context, which can significantly harm model performance on downstream tasks. This motivates principled designs in which LLM systems include built-in mechanisms to guard…