cs.AI · 2026-06-18 · No. 27
Artificial Intelligence, 2026-06-18.
24 new papers in cs.AI. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
24 entries-
01
Rethinking Reward Supervision: Rubric-Conditioned Self-Distillation
Siyi Gu, Jialin Chen, Sophia Zhou, Arman Cohan, Rex Ying
cs.AI · cs.CL
Post-training of reasoning language models is commonly driven by supervised distillation and reinforcement learning with verifiable rewards. Distillation often relies on chain-of-thought annotations that are expensive to obtain and may themselves be noisy, incomplete, or partially incorrect; even when the final solution is correct, an imperfect rationale can interfere with learning. Reinforcement learning with verified rewards, on the other...
-
02
NeSyCat Torch: A Differentiable Tensor Implementation of Categorical Semantics for Neurosymbolic Learning
Daniel Romero Schellhorn, Till Mossakowski, Björn Gehrke
cs.AI · cs.LG · cs.LO · math.CT · math.LO · math.PR
Neurosymbolic semantics is fragmented: classical, fuzzy, probabilistic and neural systems each define truth by their own inductive rules. NeSyCat, extending ULLER, subsumes them under a single inductive definition of truth, parametric in a strong monad and an aggregation structure on truth-values. NeSyCat has so far lacked an account of predicates and functions learned by neural networks. We provide NeSyCat Torch as the missing link and...
-
03
X+Slides: Benchmarking Audience-Conditioned Slide Generation
Haodong Chen, Xuanhe Zhou, Wei Zhou, Xinyue Shao, Yanbing Zhu, Bo Wang, Jiawei Hong, Anya Jia, Fan Wu
cs.AI
Automatically generating slide decks from source documents is an important application of large language models (LLMs). Existing benchmarks primarily assess slide completeness and technical depth, while overlooking the target audience as a critical real-world factor. For instance, specialists demand rigorous proofs, whereas decision-makers prioritize actionable conclusions. To bridge this gap, we introduce X+Slides, a benchmark specifically...
-
04
TxBench-PP: Analyzing AI Agent Performance on Small-Molecule Preclinical Pharmacology
Hannah Le, Ramesh Ramasamy, Alex Urrutia, Mahsa Yazdani, Tim Proctor, Kenny Workman
cs.AI · cs.LG
Artificial intelligence (AI) agents promise to accelerate drug discovery by compressing interpretation and decision-making loops, but practical deployment requires trusted evaluation on realistic program decisions. We introduce TherapeuticsBench Preclinical Pharmacology (TxBench-PP), a verifiable benchmark for small-molecule preclinical pharmacology and the first focused slice of a broader TherapeuticsBench effort across drug-discovery stages...
-
05
User as Engram: Internalizing Per-User Memory as Local Parametric Edits
Bojie Li
cs.AI
Personal memory in a language model is two problems: content and reasoning skill. The brain keeps the two apart (a sparse, local engram in the hippocampus for each episode, a slow neocortex for the shared skills that interpret it), so a new fact need not overwrite everything else. Most personalization today keeps a user's facts outside the weights, in a natural-language memory file or a retrieval index. When facts are written into the model...
-
06
Beyond Safe Data: Pretraining-Stage Alignment with Regular Safety Reflection
Jinhan Li, Kexian Tang, Yihan Xu, Zhuorui Ye, Kaifeng Lyu
cs.AI · cs.LG
To achieve deeper safety alignment for large language models (LLMs), recent efforts have studied how to push safety interventions earlier into the pretraining stage, primarily by filtering unsafe data or rewriting it into safer forms. We argue that pretraining-stage alignment should go beyond making the data safe: LLMs may compose seemingly benign knowledge and capabilities into unsafe behaviors. To this end, we propose Safety Reflection...
-
07
Human-AI Coevolution Dynamics: A Formal Theory of Social Intelligence Emergence Through Long-Term Interaction
Jingyi Zhou, Senlin Luo, Haofan Chen
cs.AI · cs.CL
Current conversational AI systems have made significant progress in language generation, personalization, and long-context interaction. However, most existing methods model social behavior through isolated components such as emotion modeling, memory retrieval, or persona conditioning, lacking a unified framework to explain the emergence of stable social relationships and social intelligence in long-term human-AI interaction.To address this,...
-
08
Analysing drivers and interdependencies in European electricity markets using XAI
Antoine Pesenti, Aidan O'Sullivan
cs.AI · cs.LG · econ.GN
Electricity markets are inherently complex systems characterised by strong nonlinearities, high-dimensional interactions, and increasing interdependence across regions. While deep neural networks (DNNs) have demonstrated strong predictive capabilities for electricity prices, their lack of interpretability limits their usefulness for understanding the underlying drivers of price formation. This paper addresses this gap by combining DNN models...
-
09
Towards an Agent-First Web: Redesigning the Web for AI Agents
Eranga Bandara, Ross Gore, Ravi Mukkamala, Asanga Gunaratna, Safdar H. Bouk, Xueping Liang, Peter Foytik, Abdul...
cs.AI · cs.CY
The World Wide Web was built on an assumption held for three decades: the primary consumer of web content is a human being. This permeates every layer; its access model presumes human visitors, its economics rest on human attention, and its content targets human perception. The rapid emergence of AI agents as intermediaries between humans and web content invalidates this assumption. Yet the web resists agents through blanket blocking,...
-
10
ARIADNE: Agnostic Routing for Inference-time Adapter DyNamic sElection
Enrico Cassano, Michał Brzozowski, Zuzanna Dubanowska, Paolo Mandica, Neo Christopher Chung
cs.AI
The increasing deployment of parameter-efficient fine-tuning (PEFT) has led to model ecosystems in which a single backbone is paired with many task-specialized adapters. In this setting, inference-time queries often arrive without task labels, requiring the system to automatically select the most appropriate adapter from a growing and heterogeneous adapter pool. Existing routing methods either depend on access to adapter internals, such as...
-
11
RODS: Reward-Driven Online Data Synthesis for Multi-Turn Tool-Use Agents
Ruishan Fang, Siyuan Lu, Chenyi Zhuang, Tao Lin
cs.AI
Multi-turn tool-use RL is bottlenecked by the rapid depletion of informative samples in static datasets. We observe that the gradient signal in GRPO concentrates on tasks with the highest rollout reward variance, a consequence of the Popoviciu upper bound. Consequently, samples near the agent's capability boundary -- where successes and failures are roughly balanced -- contribute disproportionately large policy gradients. As training...
-
12
ThinkDeception: A Progressive Reinforcement Learning Framework for Interpretable Multimodal Deception Detection
Jinhao Song, Shan Liang, Yiqun Yue, Zhuhuayang Zhang, Tianqi Gao
cs.AI
Multimodal deception detection is critical for identifying fraudulent intentions, yet existing approaches predominantly rely on end to end black--box paradigms. These methods suffer from a severe lack of interpretability failing to provide transparent reasoning trajectories and struggling to explicitly capture the subtle, cross modal inconsistencies inherent in deceptive behaviors. To transcend these limitations, we propose ThinkDeception, a...
-
13
RTSGameBench: An RTS Benchmark for Strategic Reasoning by Vision-Language Models
San Kim, Daechul Ahn, Reokyoung Kim, Hyeonbeom Choi, Seungyeon Jwa, Jonghyun Choi
cs.AI
Modern Vision-Language Models (VLMs) often struggle with strategic reasoning, i.e., anticipating and influencing other agents' actions, under uncertainty in competitive and cooperative settings. Real-time strategy (RTS) games can be a natural testbed for diagnosing this limitation, as they demand coordination with allies, adaptation to opponents' strategy, and long-horizon planning under partial observability. However, existing RTS benchmarks...
-
14
Decoupling Search from Reasoning: A Vendor-Agnostic Grounding Architecture for LLM Agents
Emmanuel Aboah Boateng, Kyle MacDonald, Amardeep Kumar, Siddharth Kodwani, Sudeep Das
cs.AI · cs.CL · cs.IR · cs.MA
Production LLM agents increasingly depend on real-time search, yet native search grounding bundles retrieval policy, provider choice, evidence injection, cost, latency, and generation behavior behind a single model-provider boundary. This coupling makes grounding hard to inspect, tune, reuse, or port, and can trigger Search-Induced Verbosity that breaks strict output contracts. We present Decoupled Search Grounding (DSG), a vendor-agnostic...
-
15
SciRisk-Bench: A Risk-Dimension-Aware Benchmark for AI4Science Safety
Linghao Feng, Yinqian Sun, Dongqi Liang, Sicheng Shen, Chenfei Yan, Yuxuan Peng, Yilin Zhao, Haibo Tong, Kai Li,...
cs.AI · cs.CY
Large language models (LLMs) are increasingly embedded in AI for Science (AI4Science) workflows, from scientific question answering and literature analysis to laboratory planning and autonomous discovery. This progress creates an urgent need for safety benchmarks that evaluate not only scientific competence, but also whether models recognize and avoid risks in high-stakes scientific contexts. Existing AI4Science safety datasets cover several...
-
16
Skill-Guided Continuation Distillation for GUI Agents
Zhimin Fan, Hongwei Yu, Yeqing Shen, Haolong Yan, Guozhen Peng, Tianhao Peng, Yudong Zhang, Xiaowen Zhang, Kaijun...
cs.AI
Improving GUI agents typically relies on behavior cloning on expert trajectories. However, as the current policy deviates from the expert policy, it inevitably encounters policy-induced off-trajectory states during closed-loop execution, i.e., states that fall outside the expert trajectories. Since expert trajectories provide no demonstrations for these unseen states, such states receive no effective supervision, leaving the policy unable to...
-
17
Generative-Model Predictive Planning for Navigation in Partially Observable Environments
Thomas Quilter, Yifan Zhu, Guorui Quan, Mingfei Sun, Samuel Kaski
cs.AI
Navigation in partially observable environments presents a significant challenge for autonomous agents, requiring effective decision-making with limited sensory information in unknown environments. Belief-based methods, particularly those using neural networks to approximate the belief space, often fail to capture the inherent multimodality of belief spaces, especially in high-dimensional cases with perceptual aliasing. While generative...
-
18
Externalizing Research Synthesis and Validation in AI Scientists through a Research Harness
Zijian Wang, Hanqi Li, Ziyue Yang, Zijian Hu, Shenghan Zuo, Yunzhe Zhang, Da Ma, Danyu Luo, Chenrun Wang, Jing Peng,...
cs.AI
AI systems can increasingly automate scientific workflows, but the reasoning that links prior evidence, generated ideas, experiments and final claims often remains implicit inside model inference. Here we introduce Xcientist, a research harness that externalizes research synthesis and experimental validation into inspectable, contract-governed processes. Xcientist organizes literature evidence, idea states, implementation plans, ablation...
-
19
WorldLines: Benchmarking and Modeling Long-Horizon Stateful Embodied Agents
Yehang Zhang, Jianchong Su, Haojian Huang, Yifan Chang, Tianhao Zhou, Xinli Xu, Yingjie Xu, Yinchuan Li, Zexi Li,...
cs.AI
To assist humans over extended periods in real homes, embodied agents must remember user routines, world states, and past interactions. Existing long-term memory benchmarks mainly evaluate language-centric retrieval and question answering, while embodied benchmarks often focus on short-horizon task execution without testing long-term memory use in dynamic environments. We introduce WorldLines, a project-driven benchmark for long-horizon...
-
20
ProfiLLM: Utility-Aligned Agentic User Profiling for Industrial Ride-Hailing Dispatch
Tengfei Lyu, Zirui Yuan, Xu Liu, Kai Wan, Zihao Lu, Li Ma, Hao Liu
cs.AI · cs.CY
Bringing Large Language Models (LLMs) into industrial ride-hailing dispatch as semantic feature extractors over platform-scale behavioral logs is a compelling but under-explored data systems problem. Production matching pipelines remain dominated by structured numerical features, yet decisive behavioral signals (e.g., a driver's habitual aversion to certain regions) are inherently contextual and naturally expressible as LLM-generated user...
-
21
R2D-RL: A RoboCup 2D Soccer Environment for Multi-Agent Reinforcement Learning
Haobin Qin, Baofeng Zhang, Hidehisa Akiyama, Keisuke Fujii
cs.AI
Robot soccer is a challenging testbed for multi-agent reinforcement learning because it combines partial observability, cooperative and adversarial interaction, sparse rewards, and long-horizon tactical behavior. RoboCup 2D Soccer Simulation (RCSS2D) provides a mature robot-soccer platform, but its competition-oriented server-client architecture is difficult to use directly with modern Python-based MARL workflows. We introduce R2D-RL, a...
-
22
What Must Generalist Agents Remember?
Khurram Yamin, Namrata Deka, Maitreyi Swaroop, Albert Ting, Jeff Schneider, Bryan Wilder
cs.AI
This paper develops a formal account of what generalist agents must store in memory in order to act near-optimally across multiple environments and goals. It shows that when two domains share an observational bottleneck but require incompatible optimal actions, any uniformly near-optimal policy must induce distinct memory distributions at that bottleneck. The result yields a separation theorem: sufficiently successful agents cannot rely only...
-
23
ForecastBench-Sim: A Simulated-World Forecasting Benchmark
Jaeho Lee, Nick Merrill, Ezra Karger
cs.AI · cs.CL · cs.LG
Forecasting benchmarks for general-purpose AI systems usually inherit the constraints of the real world: outcomes resolve slowly, tail events are rare, and counterfactual questions are difficult to score. We introduce ForecastBench-Sim, a simulated-world forecasting benchmark built on game rollouts from Freeciv, a turn-based strategy game modelled on the Civilization series. Forecasters receive a fixed world report (a structured snapshot of...
-
24
Optimizing Lithium Production Decisions under Geological, Demand, and Pricing Uncertainties: A POMDP Framework for Multi-Objective Decision Making
Anna C. Edmonds, Mansur M. Arief, Robert J. Moss, Mykel J. Kochenderfer, Jef Caers
cs.AI · cs.LG
Decision making in lithium production is challenging, whether from an investor's perspective or a strategic production standpoint. Determining which mines to open and when to open them involves not only geological and price uncertainties, but also complexities around the choice of extraction method, from direct lithium extraction to hard rock mining. Prior work explored models of this problem and different methods to optimize mining...
This edition is part of The Daily Abstract — cs.AI archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.
#D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.