The paper investigates whether large language models (LLMs) follow Occam's Razor when performing inductive and abductive reasoning. It introduces a synthetic framework for generating questions that require both types of reasoning and a new automated metric to evaluate the simplicity and correctness of generated hypotheses. Experiments show that while LLMs can handle simple scenarios, they struggle with complex world models and producing high‑quality, simplest hypotheses, even when using advanced reasoning techniques.
By Yunxin Sun, Abulhair Saparov
The paper evaluates a manager‑worker scaffold that uses a shared filesystem workspace to orchestrate multi‑agent large language model (LLM) coding tasks without training or tuning. Across nine models—including five open‑weight and four closed‑weight systems—the scaffold yields statistically significant accuracy gains for some models (e.g., Qwen3.8‑27B, GPT‑5.6‑Luna, GPT‑5.6‑Terra, Kimi‑K3, Minimax‑M3) while producing null or negative effects for others (e.g., Qwen3.6‑35B). The study shows that the manager can triple token usage but still achieves higher accuracy at a fraction of the cost compared to larger single‑pass models, with key mechanisms identified as context management and problem decomposition.
By Victor Gao (Sang Won), Vida Khosrowshahi (Sang Won), Ali Khosrowshahi (Sang Won), Xihao Sun (Sang Won), Juhyun Lee (Sang Won), Simon (Sang Won), Lee
BekchiAI introduces a benchmark and platform for evaluating large language model agents. The benchmark comprises 13 tool‑using ReAct agents across seven task categories, totaling 2,057 deterministic test tasks with verifier‑checkable gold answers. The platform offers web‑based observability, token and latency telemetry, and remote run termination for live agents.
By Mesut Toruk
The paper introduces Disjoint Parameter Training (DPT), a framework that addresses Skill Conflict—where shared encoder parameters hinder separate tasks of motion prediction and safety planning—by training tasks on distinct parameter subsets before merging. DPT employs sparse merging to integrate only the most influential parameters, reducing interference and enhancing representational capacity. Experiments on JRDB and JTA benchmarks show that DPT outperforms existing unified models, demonstrating its effectiveness for safe, resource‑efficient robot navigation.
By Taewon Seo, Seonae Jeon, Giwon Lee, Kuk-Jin Yoon, Daehee Park
LiveSim is an LLM-based framework designed to simulate users in multi‑agent live‑stream ecosystems. It treats users as editable behavioral hypotheses and refines them through trajectory‑grounded interactions, using discrepancies between simulated and observed trajectories to uncover missing environmental shaping effects. The framework extracts transferable environment‑behavior patterns, stores them in a collective behavioral memory, and demonstrates improved user‑level fidelity and ecosystem‑level analysis on real‑world live‑stream risk‑control data.
By Jiaqi Xu, Yiran Qiao, Jing Chen, Qiwei Zhong, Xiang Ao, Xueqi Cheng
The paper introduces ASIL, an Agent‑Software Interaction Layer that replaces traditional screenshot‑and‑click interfaces with structured JSON observations and code‑executable semantic actions. ASIL is implemented across 15 applications and evaluated on 300 single‑application and 80 multi‑application tasks, achieving over 80% success with fewer than five actions per task. The structured interface also improves training efficiency, boosting performance of Qwen models from 58–66% to 72–80% with small‑scale supervised fine‑tuning and further gains with on‑policy reinforcement learning.
By Rui Xie, Lu Chen
TransMeme introduces a multi‑agent framework for cross‑cultural meme transcreation, addressing the unique challenges of preserving intent, adapting cultural meaning, and maintaining multimodal consistency. The system coordinates specialized agents for cultural adaptation, text rewriting, revision, and visual adjustment, and is evaluated on Chinese‑English meme pairs. Human and LLM‑based evaluations show that TransMeme outperforms baselines, achieving a 33.1% average improvement in human scores and a 60% Top‑1 ranking rate in LLM judgments.
By Jingyi Zheng, Yule Liu, Zifan Peng, Tianyi Hu, Yuemeng Zhao, Xinhu Zheng, Xinlei He
The study compared human and large language model (LLM) workflows for title‑and‑abstract screening in a complex scoping review. Human reviewers and two GPT‑5.4 file‑batch runs retained 42.2‑45.0% of records with 82.3‑82.9% recall, while Gemini 3.1 achieved the highest recall (83.9%) but retained 56.7% of records. Identical GPT‑5.4 runs showed 91.7% agreement yet differed on 94 records, including 29 verified eligible ones.
By Nikol Figalov\'a, Lynn Huestegge, Anne B\"ockler-Raettig
The paper introduces a novel LLM‑driven multi‑agent pipeline that converts relational databases into graph databases by standardizing table and column names and iteratively refining the graph schema through ETL, Analyzer, and Graph agents. The resulting graph database meets accuracy, groundedness, and faithfulness criteria and shows significant performance gains, achieving 85.6% Q&A accuracy—12.12% higher than an SQL agent on PostgreSQL—and reducing latency by roughly threefold on a BFSI dataset. This demonstrates an efficient, automated method for transforming tabular data into a more intuitive and faster‑executing graph format.
By Dinh-Khanh Pham, Quy-Anh Dang, Lam Mai Thanh, Khanh Bui, Truong-Son Hy
The paper introduces Knowledge Cards, a new structured artefact designed to capture validated knowledge about specific concepts that AI systems use to make decisions. Unlike existing model, data, and system cards, Knowledge Cards focus on the layer between inputs and outputs, documenting entities, relationships, reasoning patterns, conditions for validity, and provenance, all grounded in a formal domain ontology and signed off by a domain expert. Prototype cards have been created in the energy and pharmaceutical domains, and the schema is released as a public draft for community engagement.
By Liliana Ferreira
The paper proposes a scalable, automated method for auditing candidate‑job matching systems for demographic bias. It employs large‑language‑model agents to generate neutral resumes, injects controlled demographic variations, ranks candidates with a fine‑tuned embedding model, and evaluates nine fairness metrics across counterfactual, group‑fairness, and merit‑aware families, producing a composite risk report. Experiments on a small corpus show that single‑score audits miss nuanced issues, underscoring the need for multi‑metric evaluation and LLM‑generated audits as a low‑cost complement to human reviews.
By Sai Yashwant, Shruti Bansal, Anurag Dubey, Samaroha Chatterjee, Satyam Kumar, Shreyash Gupta, Gantala Thulsiram
The paper introduces PRISM, a new framework for evaluating how well large language models (LLMs) maintain persona fidelity in dynamic dialogue. PRISM reframes the task as a structured inverse inference problem grounded in Systemic Functional Linguistics, breaking persona fidelity into Task Framing, Interpersonal Stance, and Linguistic Style dimensions. Experiments demonstrate that PRISM produces more accurate and stable judgments than existing holistic or static psychometric methods, offering a more reliable and auditable evaluation process.
By Mengfan Li, Zesheng Wei, Xuanhua Shi, Yang Deng
GraphMemix introduces a combinatorial‑optimization graph memory framework that constructs query‑aware evidence forests for long‑term multimodal agent memory. It expands seed memories via schema and semantic relations, decouples memory support from relation verification to reduce redundancy, and optimizes a forest‑format context within a maximum evidence budget. Experiments on four benchmarks show significant accuracy gains and a new Pareto frontier between accuracy and lifecycle cost.
By Geng Li, Yuhao Wang, Dong Li, Jianye Hao, Yuxin Peng
SWE-Prime introduces a two-stage supervised fine-tuning data selection process for large language models tackling software issues. The first stage filters entire trajectories by quality and representativeness, while the second stage selects meaningful semantic segments based on contribution, learnability, and risk. Experiments on SWE-Bench Pro and Verified demonstrate that training on just 10% of trajectories chosen by SWE-Prime surpasses full-dataset training, achieving up to 12.2% and 24.2% performance gains.
By Dewu Zheng, Ruizhe Ye, Yanlin Wang, Yang Ye, Hongyu Zhang, Ensheng Shi, Xilin Liu, Yuchi Ma, Jianxing Yu, Zibin Zheng
The paper introduces DSA, an evidence‑aware orchestration framework that uses large language model agents to conduct multi‑market stock research. DSA structures the workflow into stages of evidence acquisition, context construction, model‑routed analysis, optional role and Strategy Skill reasoning, and report generation, offering both a default and an agentic profile with distinct output validation and risk safeguards. The reference implementation supports six regional markets, fifteen Strategy Skills, and multiple execution surfaces, and has passed 1,457 portable offline backend contract tests, confirming implementation conformance.
By Linsen Zhu, Yi Shi
The paper investigates whether agents can autonomously set the relative priorities of competing lower-level objectives using emotional preferences generated by higher-level goals, rather than relying on externally defined priorities. It introduces a framework with an inner multi-objective reinforcement learning controller and an outer preference generator that learns state-dependent preference mappings. Experiments in custom multi-objective environments demonstrate that the learned preference function can switch priorities contextually, balance trade-offs, and persist over time, outperforming fixed and handcrafted preference strategies.
By Shiqi Liu, Yihua Tan, Hu Fu, Guanyu Qi
Daydreaming is an execution‑only attack that steals multi‑file agent skills by interacting with a black‑box task service. By adaptively crafting tasks and analyzing the returned results, the attacker reconstructs the hidden skill without ever requesting or revealing it. In experiments on seven skills and four victim models, Daydreaming recovers 86.8% of the original capability using only 32 victim calls on average, outperforming prior methods and demonstrating that hiding skill files and filtering direct disclosure are insufficient defenses.
By Yu-Lin Tsai, Yu-An Lu, Ci-Yang Tsai, Muxi Lyu, Raluca Ada Popa, Chia-Mu Yu
The paper introduces MentorQA, a multilingual dataset and evaluation framework for mentorship-oriented question answering derived from long‑form videos. It contains nearly 9,000 QA pairs across four languages and defines evaluation dimensions such as clarity, alignment, and learning value that extend beyond factual accuracy. Experiments show that Multi‑Agent QA pipelines outperform other architectures, especially on complex topics and low‑resource languages, while automated LLM‑based evaluation shows variable alignment with human judgments.
By Parth Bhalerao, Diola Dsouza, Ruiwen Guan, Oana Ignat
The paper introduces a Latent World Model (LWM) for robot navigation that predicts action‑conditioned latent feature compatibility instead of reconstructing future observations. By exploiting the correlation between spatial proximity and latent feature similarity, the model evaluates action consequences directly in latent space and supports counterfactual training using sampled action sequences. The learned world model can supervise policy learning from unlabeled video and further improve policies via reinforcement learning entirely within the model, eliminating the need for action annotations and additional environment interaction.
By Zengmao Wang, Wei Gao, Shuhan Shen
Nomad is an autonomous system designed to explore and discover insights within large data corpora. It builds an explicit Exploration Map to systematically traverse a domain, generating and testing hypotheses with an explorer agent that leverages document, web, and database searches. After verification, it produces cited reports and meta-reports, and its evaluation framework assesses trustworthiness, quality, and diversity, showing superior performance over baselines on UN, WHO, and arXiv datasets.
By Bokang Jia, Samta Kamboj, Satheesh Katipomu, Seung Hun Han, Neha Sengupta, Andrew Jackson