相关论文: Ghost in the Context: Measuring Policy-Carriage Fa…

Large language model (LLM) agents are fundamentally constrained by context length on long-horizon tasks. We introduce Context-Folding, a framework that empowers agents to actively manage their working context. An agent can procedurally…

Safety evaluations of memory-equipped LLM agents typically measure within-task safety: whether an agent completes a single scenario safely, often under adversarial conditions such as prompt injection or memory poisoning. In deployment,…

As large language models (LLMs) are applied across diverse domains, the ability to selectively unlearn specific information is becoming increasingly essential. For instance, LLMs are expected to selectively provide confidential information…

Large Language Models (LLMs) have been shown to organize the representations of input sequences into straighter neural trajectories in their deep layers, which has been hypothesized to facilitate next-token prediction via linear…

Improving Large Language Model (LLM) agents for sequential decision-making tasks typically requires extensive task-specific knowledge engineering--custom prompts, curated examples, and specialized observation/action spaces. We investigate a…

Deploying compound LLM agents in adversarial, partially observable sequential environments requires navigating several design dimensions: (1) what the agent sees, (2) how it reasons, and (3) how tasks are decomposed across components. Yet…

Recent advancements in artificial intelligence have led to the creation of highly capable large language models (LLMs) that can perform tasks in a human-like manner. However, LLMs exhibit only infant-level cognitive abilities in certain…

Large Language Models (LLMs) have become increasingly capable of interacting with external tools, granting access to specialized knowledge beyond their training data - critical in dynamic, knowledge-intensive domains such as Chemistry and…

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…

Extended interaction with large language models (LLMs) has been linked to the reinforcement of delusional beliefs, a phenomenon attracting growing clinical and public concern. Yet most empirical work evaluates model safety in brief…

Large Language Model (LLM) agents are increasingly expected to maintain coherent, long-term personalized memory, yet current benchmarks primarily measure static fact retrieval, overlooking the ability to revise stored beliefs when new…

Recent work reports that Large Reasoning Models (LRMs) undergo a collapse in performance on solving puzzles beyond certain perplexity thresholds. In subsequent discourse, questions have arisen as to whether the nature of the task muddles an…

Progress on training and architecture strategies has enabled LLMs with millions of tokens in context length. However, empirical evidence suggests that such long-context LLMs can consume far more text than they can reliably use. On the other…

Large language models (LLMs) are increasingly deployed in multi-agent systems where agents communicate in natural language to solve tasks jointly. A key capability in such systems is consensus formation, where agents iteratively exchange…

While Large Language Models (LLMs) have shown significant advancements in performance, various jailbreak attacks have posed growing safety and ethical risks. Malicious users often exploit adversarial context to deceive LLMs, prompting them…

LLM-based agents can execute actions that are syntactically valid, user-sanctioned, and semantically appropriate, yet still violate organizational policy because the facts needed for correct policy judgment are hidden at decision time. We…

Long-context LLM agents often struggle with growing token, memory, and latency costs, making efficient context compression essential for practical deployment. Existing LLM-as-a-compressor methods remain noticeably inferior to using the full…

Language model (LM) agents have demonstrated significant potential for automating real-world tasks, yet they pose a diverse array of potential, severe risks in safety-critical scenarios. In this work, we identify a significant gap between…

Many AI alignment discussions of "runaway optimisation" focus on RL agents: unbounded utility maximisers that over-optimise a proxy objective (e.g., "paperclip maximiser", specification gaming) at the expense of everything else. LLM-based…

Current research on large language model (LLM) agents is fragmented: discussions of conceptual frameworks and methodological principles are frequently intertwined with low-level implementation details, causing both readers and authors to…