arXiv:2606. 12268v1 Announce Type: new Abstract: Advanced AI systems have extensive knowledge of their environments; in fact, their knowledge may (far) exceed that of their developers or users.
arXiv:2606. 18327v1 Announce Type: cross Abstract: Language models (LMs) that faithfully describe their own behavior can more easily be audited, understood, and trusted by users.
arXiv:2606. 29657v1 Announce Type: new Abstract: As AI systems become more capable, training procedures that optimize for downstream outcomes risk introducing implicit agency: goal-directed behavior that designers never specified.
As AI systems become more capable, training procedures that optimize for downstream outcomes risk introducing implicit agency: goal-directed behavior that designers never specified. We present a formal safety argument for the Scientist AI (SAI) Predictor, trained to approximate the Bayesian posterior conditioned on a dataset of "epistemically contextualized" natural-language statements.
The paper investigates how agentic systems decide between acting and abstaining, focusing on the fidelity of their reasoning explanations. Using Qwen3‑8B in a multi‑party conversation setting, the authors compare direct decision policies, reasoning policies, supervised fine‑tuning, and reinforcement learning, finding a trade‑off: strong direct policies yield higher performance but no traceable reasoning, while reasoning policies provide an audit trail at the cost of lower recall. The study also uncovers that exposing reasoning can alter the agent’s policy and that common faithfulness metrics may overstate the alignment between reasoning and decisions.
arXiv:2609.23939v1 Announce Type: new Abstract: Effective communication between users and AI agents is essential for human-AI collaboration. The XY problem is a well-known communication pitfall where...
arXiv:2609.26037v1 Announce Type: new Abstract: Explanations are central to causal reasoning, and cognitive science has long established that the human drive to explain is itself a mechanism for lear...
The paper introduces FAME, a training‑free framework that evaluates false memory in autonomous agents by tracking how their internal beliefs shift under counterfactual scenarios. False memory, defined as biases arising from spurious correlations, environment shifts, or knowledge conflicts, is hard to detect with standard methods. FAME measures concept drift in hidden states, achieving AUROCs between 76.2% and 96.7% and outperforming baselines on benchmarks such as GSM‑Symbolic, GitChameleon, and BigBench‑Hard.
The paper discusses how Large Language Models can produce natural language self‑explanations that appear plausible but may not accurately reflect the model’s reasoning. It critiques current evaluation methods for such explanations and offers practical guidelines to assess their plausibility and faithfulness. Additionally, it argues that evaluation should also consider the actionability of these explanations, showing how they can aid decision‑making for various stakeholders.
arXiv:2607. 21209v1 Announce Type: cross Abstract: In the field of Artificial Intelligence, an agent is a system which is able to autonomously make decisions in order to reach a desired goal.
arXiv:2609.17496v1 Announce Type: new Abstract: LLM assistants are widely used for daily social advice, yet evaluating their social reasoning in such consultation settings remains challenging since (...
Persuasion is a core dynamic of natural language communication, shaping how large language models (LLMs) update beliefs, resolve disagreements, and reach decisions. As LLMs increasingly debate, advise, and think collaboratively with humans and each other, resistance to harmful persuasion becomes a core requirement for reliable behavior.
arXiv:2608. 11624v1 Announce Type: cross Abstract: Persuasion is a core dynamic of natural language communication, shaping how large language models (LLMs) update beliefs, resolve disagreements, and reach decisions.