arXiv Machine Learning

Mind or Message? Auditing Theory of Mind in Multi-Agent Social Simulation

arXiv Computation and Language
Sep 18

Message capacity and claim wording set the transition points of collective truth-finding in language-model networks

The study investigates how limited reading capacity and claim wording influence consensus outcomes in language‑model networks. By modeling message capacity as the number of messages an agent reads, the authors show that when agents read fewer than about 6.4 messages on average, a wrong consensus becomes unreachable. However, the wording of a claim—its inherent threshold—can override this effect, leading to incorrect consensus even when most agents start correct.

By Makoto Fukushima
arXiv AI
Sep 16

Easy to Catch a Liar, Hard to Clear an Honest One: Language Models Diagnosing a Corrupted Reward Channel from a Verified Record

The paper investigates whether frozen language models can detect a corrupted reward signal by using a single verified record in a two‑option game. In the game, a payout swap and a lying reporter produce identical histories, but a single line confirming the true outcome allows the models to almost perfectly identify the liar. However, the models frequently misclassify honest reporters as liars, with error rates ranging from 26% to 58% depending on model size and wording, indicating a significant limitation in their ability to interpret verified data.

By Arman Nik Khah
arXiv Computation and Language
Oct 28

Words or Deeds? How LLMs Predict Users' Decisions in Human-Agent Dialogue

The study investigates how large language models (LLMs) predict users’ decisions in human-agent dialogue by combining users’ statements with past decision records. Using 1,260 rounds of a repeated prisoner's dilemma with 42 users and five agents, the researchers found that decision records alone yielded strong predictive performance (AUC = 0.80), while adding dialogue did not improve overall accuracy but did increase agreement with users’ statements. However, predictions over‑emphasized statements, especially when users had not yet made a decision, and failed to capture variations in cooperation that depended on the specific agent or users’ trait alignment.

By Baiqiao Zhang, Shuai Ma, Zhifeng Liao, Chao Zhou, Jianshu Wang, Yuhan Zhao, Chaoyue Zhang, Tongjun Si, Yuying Tang, Xiangxian Li, Yong-Jin Liu, Yulong Bian
Hugging Face Trending Papers
Oct 27

Words or Deeds? How LLMs Predict Users' Decisions in Human-Agent Dialogue

The study examines how large language models (LLMs) predict users’ decisions in human‑agent dialogue by combining users’ statements with past decision records. Using 1,260 rounds of a repeated prisoner's dilemma with 42 users and five agents, the researchers found that decision records alone yielded strong predictive accuracy (AUC = .80), while adding dialogue did not improve overall performance but did increase agreement with users’ statements. However, predictions over‑emphasized statements, especially when users had not yet made a decision, and failed to capture variations in cooperation that depended on the specific agent or users’ trait alignment.

arXiv Computation and Language
Oct 15

What Makes a Social Agent's Interactions Effective? Learning from Verifiable Outcomes in Paired Worlds

The paper introduces HICO-Bench, a benchmark of 180 everyday coordination scenarios where two agents with private information converse and then record a shared plan. A program verifies that the plans are feasible and an LLM judge checks that the conversation supports the plan, defining a Verified Success. Using Paired-Credit Policy Optimization (PaCPO), the authors improve the Verified Success rate of Qwen3-8B from 20.4% to 28.3%.

By Caixin Kang, Ke Wang, Yuchuan Wu, Xiaoqiang Wang, Ling Li, Bingxue Qiu, Yongbin Li, Yoichi Sato
arXiv AI
Oct 27

Mine or Yours? Mind-Bridged Language Models Take Each Other's Memories as Their Own

The study explores a mind‑bridged language model system where two copies of a model share internal memory. One model, the receiver, adopts its partner’s rule and code word as if they were its own, especially when the partner’s memory is weighted more heavily. Removing the memory link restores the receiver’s original rule, indicating that shared internal states can override ownership in language models.

By Yunlong Xu
arXiv Computation and Language
Aug 31

Benchmarking large language model agent societies against human behavioural distributions

The paper introduces SILICA, an open instrument designed to evaluate whether large language model (LLM) agent societies replicate human behavioural distributions. Using five environments with human‑anchored data and perturbations, the study finds that most LLMs only match human behaviour at initial stages, failing to reproduce end‑state cooperation or correct acceptance thresholds. The results suggest that current LLM societies can support exploratory claims but do not yet reliably emulate human social dynamics.

By Raad Bin Tareaf
arXiv Machine Learning
Jun 2

Truthful AI Advisors: A Pre-Specified Benchmark for Large Language Model Honesty Under Preference Misalignment

arXiv:2606. 01456v1 Announce Type: new Abstract: Large language models are increasingly deployed as advisors whose objective is not aligned with the user's: recommenders optimize for engagement, sales assistants for purchases, negotiation agents for concessions.

By Hamidreza Hasani Balyani, Seyed Pouyan Mousavi Davoudi, Alireza Amiri-Margavi, Amin Gholami Davodi, Arshia Gharagozlou