cs.AI · 2026-08-10 · No. 80
Artificial Intelligence, 2026-08-10.
61 new papers in cs.AI. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
61 entries-
01
Interaction Creates Dynamical AI Behavior Absent in Isolation
Bella Xinrui Li, Frank Yingjie Huo, Neil F Johnson
cs.AI · cond-mat.dis-nn · cond-mat.stat-mech · physics.soc-ph
What will happen when AI agents interact in daily life, e.g. when one AI starts bossing another around? We find a counterintuitive answer that opens new avenues for out-of-equilibrium Physics. When a boss AI directs a stream of messages at the subordinate AI while ignoring its replies, it drives the subordinate into an alien behavioral state that it would never have exhibited alone. Although the two AIs share the same well-defined (decoding)...
-
02
SkillProx: Self-Evolving Agent Skills via Proximal Textual Gradient Descent
Mingxuan Zheng, Yujin Zhou, Chuxue Cao, Boqin Yin, Yuyao Zhang, Jiapeng Sun, Shuaishuai Gong, Sirui Han, Yike Guo
cs.AI · cs.CL
LLM agents increasingly adapt to recurring tasks by accumulating procedural knowledge in skills. These skills are lightweight, reusable textual artifacts that are loaded into the agent's context without weight updates. Recent methods refine skills through iterative task execution, failure diagnosis, and trajectory-guided text-space updates. However, existing frameworks lack explicit diagnosis--outcome feedback and treat deletion as a generic...
-
03
Blast Radius
MY Pitsane, Hope Mogale
cs.AI
Agentic coding faces growing problems of affordability and wasted tokens. We introduce Blast Radius, a predictive memory management layer that estimates an incoming prompt's reach through coupled context and code channels. NECROPHORESIS enables reversible eviction by archiving dead context verbatim, while Recurring Dead Matter (RDM) identifies and buries repeatedly occurring transcripts. We formulate reversible context eviction over a Polish...
-
04
PsychoAgent: An Affect-Sensitive Cognitive Architecture for Conflict-Aware Memory in LLM Agents
Mohammad Amanlou, Parham Abed Azad, Farbod Davoodi, Mostafa Masumi, Behnam Bahrak, Abdol-Hossein Vahabie
cs.AI · cs.CL · cs.HC
Human-like cognition does not select past experience by topical similarity alone: affective significance and unresolved conflict also shape what becomes accessible. We present PsychoAgent, a cognitive architecture for LLM agents that separates factual and affective memory and integrates both through a conflict-aware executive controller. Affective memories are first filtered by semantic relevance and then re-ranked by salience, preserving...
-
05
Fisher-R1: Training LLM Agents for Reliable Hypothesis Testing
Jiacheng Miao, Jin Mu, Guanhua Chen, James Zou
cs.AI
Reliable hypothesis testing is the foundation of many empirical scientific claims. Large language model (LLM) agents are increasingly used to automate this process, as they can inspect datasets, generate code, and produce analyses end-to-end. However, we show that they frequently make subtle inferential errors that lead to incorrect conclusions despite correctly executed analyses. Existing benchmarks fail to capture this failure mode, as they...
-
06
Post-Grokking Collapse at the Representation-Readout Interface in Muon-Trained Transformers
Ali Janati, Kaoutar El Maghraoui, Andrei Kanavalau, Anass Belfatmi
cs.AI · cs.LG
Under the standard split, Muon gets hidden matrices and AdamW embeddings/output head. Muon groks modular addition faster, but its solutions do not hold. All nine configurations on $(a+b) \bmod 113$ grok and later lose generalization. Across five seeds the selected AdamW reference falls below threshold on four, reaching 27.59%. Instability persists across two moduli, two widths, two training fractions, subtraction, and depth. The failure...
-
07
TEPA: Revoking Stale Memories for Conflict-Robust Language Agents
Yan Zhou, Yue Ouyang, Kaiyang Zheng, Suncheng Xiang
cs.AI
Long-term memory enables language agents to reuse past facts, preferences, and task experience. Persistence also creates a central falsifiability problem: when the world changes, stale memories can remain retrievable and pollute the prompt. We characterize this failure mode as memory pollution: degradation caused by active memories that newer conflicting evidence has superseded. We introduce TEPA, a revocable evidence-memory mechanism that...
-
08
A Picture is Worth a Thousand Tokens: How Vision Language Models Cut AI Energy Costs While Improving Accuracy
Bhavika Jalli, Nikhil Korati Prasanna, Jayanta Choudhury
cs.AI · cs.PF
LLM inference accounts for over 90% of AI operational energy, scaling directly with input token count---a critical inefficiency for telecom network analytics and numerical time-series data analysis (NTSDA), where raw multivariate KPI windows from 4G/5G cell sites expand into thousands of floating-point tokens. Vision-Language Models (VLMs) eliminate this mismatch by encoding time-series as 2D plots, achieving 3.6-10.4x input token reduction...
-
09
CoBa: Cost-Effective Test-Time Scaling via Compute-Balanced Routing
Yan Zhou, Yue Ouyang, Kaiyang Zheng, Suncheng Xiang
cs.AI
Test-time scaling is often implemented by spending more compute along one axis: sampling more solutions, extending a chain of thought, or applying a stronger evaluator. Under a fixed inference budget, these choices compete. This paper formulates test-time reasoning as a compute-allocation problem in which a system must decide whether the next unit of compute should be spent on generation, verification, or stopping. We introduce CoBa, a...
-
10
ResidencyRL: Reinforcement Learning in Simulated Clinical Environments
Valentin Liévin, Samuel Schmidgall, Tim Strother, Alex Bijamov, Akshay Goel, Anil Palepu, Chunjong Park, Vahid...
cs.AI · cs.CL
In medical education, physicians convert academic knowledge into clinical expertise through residency: years of training across thousands of encounters, with diverse sources of feedback and progressively greater autonomy. Much of clinical reasoning relies on the patient encounter, a dialogue in which a clinician elicits history, refines diagnostic hypotheses, and decides management under uncertainty. While large language models (LLMs) excel...
-
11
GeoBenchLLM: A Comprehensive Benchmark for Evaluating LLMs on Geo-Related Tasks
Rodrigo Ferreira Rodrigues, Karim Radouane, Jose G Moreno, Lynda Tamine
cs.AI · cs.CL · cs.IR · cs.LG
In the context of geodata, existing Large Language Models have often been studied in a homogeneous setting, which has considerably limited insights into their generalization capabilities. In this paper, we present \benchName, a comprehensive benchmark for probing LLMs on geo-related tasks. We leverage a careful selection of twelve publicly available datasets from diverse geo-related tasks and domains, and evaluate a set of LLMs on geo-spatial...
-
12
FinRank: An Evidence-Grounded Benchmark for Financial Question Answering and Retrieval over SEC Filings
Sasan Mansouri, Daniel Saad, Mark Wahrenburg, Manu Weissel, Fabian Woebbeking
cs.AI · cs.DB · econ.GN · q-fin.GN
Financial question answering is typically evaluated by answer correctness, yet in SEC filings a plausible and even numerically correct answer can be grounded in the wrong evidence. Similar facts and disclosures recur across sections of a filing, across reporting periods of the same firm, and across comparable firms. FinRank targets this provenance-sensitive retrieval problem by requiring systems to identify evidence for the intended entity,...
-
13
People Are Not Just Their Countries. Disentangling Social Determinants of LLM Value Alignment Across Europe
Maria-Louisa Wightman, Guillaume Bied, Tijl De Bie
cs.AI
As Large Language Models (LLMs) are increasingly used as a primary source of information and advice, understanding their alignment to humans in terms of values becomes a pressing concern. A growing literature has leveraged large scale surveys to investigate to what extent LLMs' and humans' stated values and opinions align. With limited exceptions, studied populations have been defined country borders or cultural bounds. Yet, this focus...
-
14
Curriculum as Code: An AI-Assisted Architecture for Instructional Design in STEM Education
Henrique Mohallem Paiva
cs.AI · cs.CY
Contribution: This paper presents a six-phase AI-assisted instructional design architecture based on the Curriculum as Code paradigm, integrating Generative AI with LaTeX and Python to automate the creation of reproducible, visually consistent, and technically precise materials for STEM education. Background: Creating customized instructional materials for active learning imposes a heavy workload on faculty. Standard presentation tools lack...
-
15
QFCQT: A Chaotically Gated Quantformer Framework for Volatile Time-Series Forecasting
Junkai Lin, Siqi Hou, Raymond Lee
cs.AI
Forecasting non-stationary time series remains difficult due to long-range dependencies, local volatility bursts, structural shifts, and nonlinear oscillatory behaviors. Although Transformer-based forecasters are effective for modeling long-term temporal dependencies, their feed-forward blocks typically rely on smooth static activations that are insufficiently sensitive to abrupt regime changes. Motivated by quantitative Transformer designs...
-
16
An End-to-End Agent Auditing Engine
Haoning Wang, Mingxun Zhang, Chenyue Yu, Yingjun Shang, Xia Hu, Guanchu Wang, Na Zou
cs.AI
With the rapid advancement of large language models (LLMs), harnesses have become essential infrastructure for deploying agents across a wide range of domains. The fast-evolving harness ecosystem has also made rigorous capability evaluation increasingly important. However, efficiently building an end-to-end, systematic, and comprehensive evaluation pipeline remains a significant challenge. To address this challenge, we introduce $A^2E$ (Agent...
-
17
Winning by Peeking: Unenforced Budgets and Test-Set Selection Inflate Short-Budget AutoML Comparisons
Guilin Zhang, Kai Zhao
cs.AI · cs.LG · math.ST
Comparisons between AutoML systems at short time budgets -- tens of seconds rather than hours -- are common in tool READMEs and workshop papers, and they are easy to get wrong. We report a case study in which a simple AutoML engine, Orcetra, appeared to beat FLAML and AutoGluon on 513 OpenML datasets, winning 57.1% of them at a nominal 60-second budget and 78.4% of datasets against FLAML alone at 30 seconds. Both margins came from protocol...
-
18
WNM-3D: A World Navigation Model with 3D Scene Conditioning for Closed-Loop VLN
Yuehao Huang, Yunzi Wu, Xiaotao Zhang, Xinhai Li, Jiankun Dong, Jiajun Lv, Chi Zhang, Chenjia Bai, Yong Liu, Xuelong Li
cs.AI · cs.CV · cs.RO
Recent vision-language navigation (VLN) systems increasingly adapt pretrained vision-language models (VLMs) into vision-language-action (VLA) policies that map egocentric observations and language instructions directly to navigation actions. Although semantically capable, such action-centric training does not explicitly model how the agent's visual observations should evolve under its predicted motion. Generative world-action models (WAMs)...
-
19
Recipes for Creativity: Iterative Generation and Evaluation in Large Language Models
Rens Anderson, Tessa Verhoef, Amirhossein Zohrehvand
cs.AI · cs.CL · cs.NE
Generative models are often evaluated through singular artifacts, whereas human creativity typically emerges through iterative generation, appraisal, and refinement. This pilot study examines whether iterative search improves LLM creativity by adapting FunSearch to recipe generation for the 2024 Pillsbury Bake-Off and evaluating outputs against human benchmarks using TTCT-based LLM evaluation. Across two experiments, we test iteration count,...
-
20
From probability to causality in probabilistic logic programming
Zora Wurm, Kilian Rückschloß, Felix Weitkämper
cs.AI
Probabilistic logic programming is a formalism of statistical relational artificial intelligence that supports causal queries, including interventions from outside the system. When the structure of a probabilistic logic program is learned from data, however, only probabilistic information is used, and a single probability distribution may be compatible with several causal orders. This leads to ambiguity in interventional reasoning, raising...
-
21
Beyond the Black Box: Interpretable Models of Human Randomisation Failures
Ngoc Linh Dao
cs.AI
Mixed strategy equilibrium predicts i.i.d play: past actions should not help predict future decisions. Human players, however, systematically depart from this benchmark, and in O'Neill's zero sum card game, these departures can be predicted by black box sequence models such as LSTMs. This paper asks whether that predictive power can be achieved by transparent alternatives that also reveal the behavioural structure behind it. Using 84,060...
-
22
Authoring and Management of Transparent Research Integrity Assessments of Randomised Clinical Trial Publications Using LLM-assisted Tools and Provenance Knowledge Graphs
Milan Markovic, Goutham Indukuri, Somayajulu Sripada, Colby J. Vorland, Jack Wilkinson, Clare Robertson, Mark...
cs.AI
Systematic reviews of Randomised Controlled Trials (RCTs) are routinely used as evidence for clinical care guidelines. Such evidence has to meet high research integrity standards to prevent low quality or false research outputs influencing the clinical care. However, assessing research integrity of published RCTs is a complex process requiring manual effort, and potentially resulting in diverse opinions of the human assessors. This paper...
-
23
EMAS: Stabilizing Multi-Agent System Evolution through Evidence-Guided Revision
Chao Fei, Qingyi Si, Kaihua Liang, Yanghua Xiao, Panos Kalnis, Hongcheng Guo
cs.AI
Many methods for automated multi-agent system design optimize prompts and topologies during an initial design stage and then deploy the resulting system unchanged on subsequent samples. Experience from these samples is rarely consolidated into reusable system updates, while accuracy-oriented designs may incur high token costs. We introduce EMAS (Evolving Multi-Agent System), which uses this experience to revise MAS topology and prompts...
-
24
SetEasy: A Multi-Modal Classroom Engagement Assessment and Seating Optimization Framework
Zhihao Xie, Hongye Yang, Shien Liu
cs.AI
SetEasy optimizes classroom engagement in fixed seating grids. It fuses multimodal sensing (wristband physiology, 4K video, environmental data) and trains a v-Gage model grounded in a revised ISEQ. Each week, two-week engagement forecasts are mapped to a student-seat utility matrix, and CP-SAT generates seating plans under visual-access and social-dynamics constraints. In a four-week deployment (23 students, 331 classes), v-Gage converged...
-
25
Agent Memory Distillation: Empowering Small LLM Agents with Hierarchical Teacher Memory
Taeil Kim, Kangsan Kim, Sung Ju Hwang
cs.AI · cs.LG
Memory systems have shown promise for improving agent performance, but their potential remains largely unexplored for small language models, which struggle to generate sufficient successful trajectories on their own. We propose Agent Memory Distillation (AMD), a training-free framework that transfers structured knowledge from a large teacher agent to a small student agent through hierarchical memory. AMD constructs three complementary memory...
-
26
NiyamAI - An Intent-Bound AI Agent with Cryptographically Verifiable Guardrails using Zero-Knowledge Proofs
Aditya Katkar, Om Karkele, Kartik Mandhane, Manisha More, Yash Kashid
cs.AI
Giving an AI agent the ability to send emails, query databases, or execute commands is useful--until the agent is tricked into doing something it shouldn't. Prompt injection, hallucinated reasoning, and unsafe tool calls form the primary attack surface for autonomous LLM agents. Existing defenses rely on software checks like system prompts or policy filters running on the same machine the attacker targets, offering no verifiable proof of...
-
27
A MARL Centered Reference Architecture for Large Language Model Augmentation in Smart Manufacturing
Fouad Bahrpeyma, Dirk Reichelt
cs.AI
Modern manufacturing imposes six coupled demands on adaptive control: local decisions with global consequences, partial observability, nonstationarity, reflex speed response with long horizon effects, delayed and diffuse outcomes, and dynamics that resist explicit modeling. Cooperative multiagent reinforcement learning (MARL), posed as a Dec-POMDP under centralized training with decentralized execution, is a particularly natural formalism for...
-
28
DiDPO: Diff-in-Diff Policy Optimization for Coding Agent Training
Xucong Wang, Zhe Zhao, Liheng Yu, Di Wu, Xiaofeng Cao, Pengkun Wang
cs.AI
Reinforcement learning with Verifiable Reward (RLVR) has emerged as a powerful paradigm for training coding agents, where the execution feedback from compilation and tests provides objective verification. However, unlike agent tasks, coding agents face a unique and finer-grained credit assignment challenge: at each step, coding actions simultaneously pack varying changes into different regions of a code version, which makes the contribution...
-
29
How Much, Then Where: Credit-Conserving Action-to-Token Allocation for Multi-Turn Agent Reinforcement Learning
Lichao Ma, Yang Sun, Shuaitao Zhao, Yangyi Fang, Cong Qin, Xiaoliang Fu, Yuhang Tian, Yuchen Wei, Junbo Zhu, Yang...
cs.AI
Credit assignment in multi-turn agent reinforcement learning operates at two levels: assigning trajectory-level credit to actions and distributing each action's credit across its tokens. In this paper, we introduce FACTOR, which separates these decisions. FACTOR uses checkpoint-calibrated TD residuals to assign per-action credits that telescope to the trajectory advantage, and feedback-conditioned teacher-student likelihood gaps to allocate...
-
30
MemWM: Memory-Augmented Text-Based World Model
Yujun Wang, Tao Zhang, Jinhe Bi, Aniri, Wenxuan Ye, Boliang Liu, Sikuan Yan, Shuning Wang, Xuebing Zhou, Sören Pirk,...
cs.AI
World models are increasingly used to support planning in agents by predicting how environment states evolve in response to agent actions. Yet fluent next-state predictions can still omit task-critical facts, corrupt product attributes, or apply incorrect transition rules. To address such systematic prediction errors, we introduce MemWM, a memory-augmented text-based world model. MemWM uses world memory, a curated memory bank of transition...
-
31
Transformers Struggle to Use Their Emergent World Models: Revisiting the Tower of Hanoi, and the Illusion of Thinking
Devin Pereira, Willem Zuidema
cs.AI · cs.LG
The Tower of Hanoi is a simple planning puzzle that in prior work has proven challenging for large reasoning models (LRMs). Current models solve the standard formulation of the puzzle, but still struggle with the flat-to-flat variant (where initial and goal states are not restricted to have all rings on a single peg). This paper presents an in-depth study of how both small, in-house Transformers and large, third-party LRMs solve this task. To...
-
32
MemOPD: On-Policy Distillation through Memory State Alignment for Long-Horizon Agents
Zhiyuan Liu, Tinghong Ye, Chenghao Liu, Yizhuo Li, Songfang Huang
cs.AI
Long-horizon agents accumulate growing contexts during interaction, impairing performance and stability. Compact memory mitigates this problem by compressing and rewriting the history retained between model invocations. Learning what to retain typically relies on proximal policy optimization (PPO) with final task rewards, but sparse rewards provide little guidance for individual memory updates. This limitation motivates on-policy distillation...
-
33
DocMemo: Dynamic Evidence Discovery via Probabilistic Memory-Guided Retrieval for Multi-Modal Document Understanding
Hanshu Yao, Janfeng Zhong, Niu Lian, Jinpeng Wang
cs.AI · cs.CL · cs.IR · cs.MM
Long-document understanding requires locating sparse and heterogeneous evidence across hundreds of pages, yet existing systems remain limited by static retrieval and fragile cross-round memory. Mainstream single-round methods commit to a fixed top-$k$ page set at the outset and struggle to recover from early retrieval errors; recent iterative approaches allow multi-round evidence acquisition, but they do not investigate the propagation...
-
34
PTQ4SNN: Membrane-Aware Post-Training Quantization for Spiking Neural Networks
Hui Xie, Tong Shi, Haotong Qin, Aishan Liu, Xiaode Liu, Jinyang Guo
cs.AI
Spiking neural networks (SNNs) enable sparse and event-driven computation, but their low-bit deployment remains incomplete because recurrent membrane states are commonly retained in floating point even after weight quantization. Quantizing these states is challenging because their distributions differ across channels and from the preceding weights, while small perturbations near the firing threshold may alter spike decisions and accumulate...
-
35
BONSAI: Evolvability-Guided Tree Search over Skills
Yash Priya Shastri, Anand Eswaran, Adnan Qidwai, Pankaj Thorat, Sachin Joshi
cs.AI
A skill is a naturallanguage document that steers a frozen agent whose weights cannot be updated so any capability the agent lacks must be supplied in prose Optimising a skill is therefore optimising text against a score and the standard recipe which keeps any edit that raises a heldout score is blind in a specific way a single score cannot tell a document perched on a narrow overfit spike from one resting on a broad plateau even though only...
-
36
Unsupervised Adaptation of PDE Foundation Models
Ziye Song, Zhao Wei, Xin Yu, Ivor Tsang, Yueming Lyu
cs.AI
Pretrained partial differential equation (PDE) foundation models can generalize across different equations, but adapting them to unseen PDE systems typically requires dense solution data, which is often expensive or unavailable. To address this limitation, we propose an unsupervised PDE-based finetuning framework that eliminates the need for ground-truth solutions. We first pretrain a neighborhood attention Transformer on diverse...
-
37
Not All Problems Are Best Modeled as MILP: A DSL-Centric Framework for Flexible and Accurate Optimization Modeling
Shaofeng Zhang, Hongyuan Su, Qingwen Peng, Zefang Zong, Shengcai Liu, Ke Tang, Yong Li
cs.AI
Solving combinatorial optimization problems (COPs) requires not only efficient algorithms but also carefully crafted formulations. While recent works have leveraged LLMs to automate optimization modeling, current frameworks predominantly rely on a rigid mixed-integer linear programming (MILP) paradigm. In this paper, we argue that not all problems are best modeled as MILP, as forcing complex domains into linear constraints can induce...
-
38
ZIPBrain: Can EEG Foundation Models Be Faster, Locally Deployable, but Accurate?
Lingwei Li, Yirong Kan, Peng Chen, Xu Cao, Zheng Chen, Yasuhiko Nakashima
cs.AI
This work investigates whether Electroencephalograph (EEG) foundation models (EFMs) can be made faster and locally deployable without sacrificing accuracy. EEG foundation models are a major trend, offering strong general-purpose representations. However, their computational burden grows quadratically with input length, hindering deployment on resource-constrained scenario, particularly for real-time clinical monitoring. EEG's low SNR further...
-
39
ReQuant: Fixed-Grid Discrete Refinement for Post-Training Quantization
Yongge Ma, Guoan Wang, Feiyu Wang, Yaoming Li, Qian Zhang, Zihan Yan, Yinjun Han, Tong Yang
cs.AI
Post-training quantization (PTQ) is widely used to reduce the memory and computational cost of large language models. Existing PTQ methods typically obtain an initial quantized model through heuristic rules or greedy optimization, and once quantization is completed the resulting integer assignments are usually treated as final. This observation motivates a complementary optimization stage within PTQ that keeps quantized weights improvable...
-
40
FedLBW: A Loss-Based Weighting Strategy for Federated Learning on Non-IID Data in Wireless Networks
Majid Kundroo, Tinku Singh, Taehong Kim
cs.AI · cs.DC · cs.ET · cs.LG
Federated Learning (FL) enables collaborative machine learning (ML) across distributed clients while preserving privacy. However, efficient model convergence in FL remains challenging, especially in wireless networks where non-independent and identically distributed (non-IID) data and frequent client dropouts are common. Traditional FL algorithms, such as FedAvg, rely solely on dataset size to weight client updates. This introduces biases...
-
41
Finding Usable Weight Mechanisms with Tiled SVD
Ash Manvi, Samreena Tajreen
cs.AI
The dominant approach to mechanistic interpretability trains proxy dictionaries such as sparse autoencoders and labels features from max-activating text. The best such atlases identify con- cepts, but that identity lives in the learned dictionary rather than in the network weights them- selves. We propose extracting mechanism mounts directly from linear sites by column-tiled SVD: each mount is a triple (v,u,σ) read as trigger, write, and...
-
42
Learning in Deep Networks under Dale's Constraint
Roy Abel, Shimon Ullman
cs.AI
Biologically plausible learning models aim to explain how neural circuits can implement effective learning under the constraints of real neurons. Although significant progress has been made, a major remaining challenge is that existing models often allow neurons or synapses to represent mixed-sign values, both positive and negative, in violation of a basic aspect of cortical circuitry -- Dale's constraint: biological neurons are either...
-
43
CAi Copilot: Reducing Operational Workload in Molecular Design through Intent-Driven Agentic Workflows
Zhu Wang, Jiangyu Chen, Yingjun Shang, Yuhui Yao, Laiao Lu, Tianfan Fu, Na Zou
cs.AI · cs.LG
Early-stage molecular design is an iterative process, not just a task of generating molecules. Researchers turn broad goals into design strategies, refine candidates, assess many properties, and gather evidence before synthesis and tests. AI methods can generate molecules, optimize several goals, predict properties, dock compounds, and account for synthesis. Yet these functions are spread across specialized tools. Experts must still...
-
44
Critical Acclaim Orientation in Large Language Models: Evidence from Film Preference Elicitation
Jonghyun Jee, Aaron Shaw
cs.AI · cs.CY
Large language models (LLMs) are trained on corpora that contain expressions of human judgment about films, books, music, and more. Yet whether LLMs systematically reproduce evaluative hierarchies remains unclear. Prior research on cultural bias in LLMs suggests competing expectations: models may mirror the popularity signals of internet texts, or may reproduce forms of prestige embedded in critical discourse. We probe this question through a...
-
45
Does Splitting a Triage Decision Across Agents Hide Bias or Help Catch It? A Multi-Agent Simulation Study of LLM-Based Resource Allocation Under Audit Capacity Constraints
Paul-Peter Arslan
cs.AI
Prior benchmarking work has shown that a single large language model (LLM), forced to make life-or-death resource-allocation decisions, exhibits measurable demographic bias. Real deployments, however, rarely use a single agent: they use pipelines, with review steps meant to catch exactly this kind of failure. We study what happens to bias when the same decision is distributed across a role-differentiated multi-agent pipeline (assessment,...
-
46
LMM Modality Transfer: A Pre-requisite for Autonomous GIS Agents
Ivan Majic, Zexian Huang, Franziska Hübl, Krzysztof Janowicz, Meilin Shi, Mina Karimi, Zilong Liu, Alexandra Fortacz-Lazan
cs.AI
AI models are becoming increasingly adept at understanding and processing spatial information, thereby facilitating agentic problem-solving in spatial tasks and workflows. However, most of the research on their spatial capabilities (e.g., spatial reasoning) has focused on the textual modality as input and output. This contrasts with the human approach to GIS workflows, where text and visual modalities are often used together, interchangeably,...
-
47
Blind to the Pivotal Vote: Aggregate Independence Metrics Miss Where Verification Actually Helps
Yang Shu
cs.AI
LLM judge panels are a standard evaluation tool, but prior work reports highly correlated panel errors: nine judges provide roughly the effective information of two independent ones, and aggregation closes only a small fraction of the gap. A natural remedy--a signal from a different evidence source, e.g., executing a test suite--produced no distinguishable change in the panel's effective-vote count at scale (-0.04, 95\% CI [-0.10, +0.02])....
-
48
Science Edge Evaluation: SEE the Missing Step Toward Real Scientific Discovery
Taolin Han, Yuchen Zhang, Jinghang Wang, Yun Wu, Wai Yuet Chiu, Zhaohai Li, Yifei Zhang, Jinxin Wang, Yuhao Zhou,...
cs.AI
Large language models (LLMs) are increasingly involved in scientific discovery, yet it remains unclear whether they can support complex real laboratory science. Here we introduce Science Edge Evaluation (SEE), a multimodal benchmark of expert-curated questions grounded in peer-reviewed literature and experimental practice in chemistry, biology, and materials science. Evaluation of 19 multimodal large language models (MLLMs) shows that even...
-
49
TRIBE: Predicting Team Performance via Communication Behavior Ensembles
Ali Jalal-Kamali, Nikolos Gurney, David V. Pynadath, Fred Morstatter
cs.AI
Designing autonomous agents that effectively assist human teams hinges on understanding team dynamics, often without task specific knowledge. We present TRIBE, a domain independent approach that reveals team behavioral dynamics invisible to traditional performance metrics. We show that communication patterns can categorize teams into performance predictive behavioral tribes, as early as 10% into the task, enabling timely interventions. We...
-
50
Deal Me Maybe: The Role of Emotions in Multi-Agent Negotiation
Massimiliano Luca, Apoorva Singh, Bruno Lepri
cs.AI
Negotiation is a demanding social task for LLM agents, requiring strategic reasoning, persuasion, and interpersonal adaptation. Yet existing benchmarks often treat agents as emotionally neutral, overlooking a key driver of human bargaining behavior. We study how prompt-conditioned emotions affect LLM-based price negotiation. In a controlled framework, buyer and seller agents are independently assigned one of six emotional states and negotiate...
-
51
ReGraph: Learning to Generate Recipe Graphs from Food Images
Guoshan Liu, Bin Zhu, Pengkun Jiao, Jingjing Chen, Chong-Wah Ngo, Yu-Gang Jiang
cs.AI
Recent Large Multimodal Models (LMMs) have achieved impressive performance in recipe generation from food images.However, cooking is a structured transformation process in which ingredients undergo state changes through ordered actions,while free-form recipe language leaves the corresponding entities, intermediate states, and dependencies largely implicit and entangled.A graph representation makes this procedural knowledge explicit and...
-
52
Fast LapSum: Exact Differentiable Top-k at Million Scale
Łukasz Struski, Joanna Wojciechowicz, Jakub Antczak, Marcin Mazur, Kamil Książek, Jacek Tabor
cs.AI
The top-$k$ operation is a fundamental building block of modern sparse computation, enabling token routing, expert activation, memory selection, and attention pruning. Yet standard hard top-$k$ blocks gradients, while existing continuous (soft) relaxations remain too costly for large-scale models. We introduce Fast LapSum, an exact-budget soft top-$k$ primitive whose GPU solver runs in linear time after sorting. Unlike prior linear-time...
-
53
Long-Horizon Agent Trajectory Attribution: A Unified Benchmark and Fine-Grained Annotation Framework
Jing Chen, Yang Sun, Li Zhang, Lin Xu, Jie Shi
cs.AI
Large language model (LLM) agents increasingly operate through long-horizon trajectories involving user instructions, tool use, external observations, and memory. Existing benchmarks primarily evaluate behavioral outcomes but provide limited support for fine-grained attribution analysis. We introduce trajectory attribution and develop a benchmark and annotation framework for this task. The benchmark organizes heterogeneous trajectories under...
-
54
From Points to Edges: Edge-Conditioned Spectral Operators for Physics-Sensitive PDE Learning
Zhentao Tan, Ruijie Quan, Yi Yang
cs.AI · cs.CV
Neural operators have become a central tool for solving partial differential equations (PDEs), with spectral operators offering efficient global mixing across spatial locations. However, many PDEs contain physics-sensitive local structures that are critical to the underlying physical behavior. For example, in Darcy flow, local material interfaces are often reflected by sharp changes in the permeability field and can strongly influence the...
-
55
SkillEval: Decomposing Agent Skill Quality into Interpretable Signals
Jiahui Han, Qinuo Li, Ziheng Peng, Haotian Wu, Haoze Liu, Danfeng Shan, Guanchu Wang, Huiqi Deng, Ninghao Liu
cs.AI
Agent skills provide reusable procedural knowledge that helps agents solve specialized tasks. As their use expands, evaluating skill quality becomes increasingly important. Existing evaluations often measure skill quality by testing whether a skill improves performance on specific downstream tasks. However, a reusable skill may apply to multiple task scenarios. Downstream evaluation mainly reflects the compatibility between a skill and the...
-
56
CEDAR: Agent-Orchestrated Tree Search for Goal-Directed Optimization of Complex Systems
Yingtao Tian
cs.AI
Complex systems, core objects of study in artificial life, model diverse phenomena through nonlinear, feedback-driven interactions that produce emergent behavior, with applications from population dynamics and biology to economic policy and strategic decision-making. Yet the difficulty of predicting how feedback structure gives rise to emergent behavior, a central open problem in artificial life, makes goal-directed design exceptionally...
-
57
Gated-BEPO: Confidence-Gated Bellman Credit Assignment for Large Language Model Agents
Hongxi Yan, Ziyue Huang, Shichao Fan, Qingjie Liu
cs.AI
Training large language model agents in long-horizon environments requires assigning credit from sparse terminal outcomes to individual actions. Existing critic-free methods propagate trajectory-level rewards uniformly across steps, while recent approaches construct step-level groups by matching repeated states and compare actions within each group. The former cannot distinguish useful actions in failed trajectories from ineffective actions...
-
58
Evolving Parallel Algorithm Portfolios via Potential-Aware Instance Generation with LLMs
Shaofeng Zhang, Shengcai Liu, Zhiyuan Wang, Ke Tang
cs.AI
The Automatic Construction of Portfolios via Large Language Models (LLM-ACP) suffers from poor generalization in practical few-shot scenarios when solving complex combinatorial optimization problems. Instance and algorithm co-evolution frameworks address this by expanding the training dataset with generated hard instances on which the current algorithm portfolio underperforms, thereby enhancing generalization. However, this paradigm faces two...
-
59
Surg-UniWorld: A Unified Surgical World Model with Multimodal Control Experts
Rulin Zhou, Wanhao Liu, Guoheng Ma, Liangjin Shao, Qiujie Song, Yidu Wang, Guankun Wang, Tong Chen, Long Bai, Luping...
cs.AI · cs.CV
Controllable surgical world models can provide a generative foundation for surgical artificial intelligence and simulation by synthesizing realistic instrument--tissue interactions. However, existing methods lack a unified multimodal control paradigm, while direct fusion of heterogeneous visual conditions often causes anatomical distortion, instrument appearance drift, and temporally inconsistent interactions. In this work, we propose...
-
60
LiFTER: A Grounded Neuro-Symbolic Microscope for Continuous-Time Dynamic Graph Forecasting
Minwoo Yu, Young-guk Ha
cs.AI
Continuous-time dynamic graph models predict future links by compressing past interactions into neural states. Although effective for forecasting, this computation obscures which entities are shared across events and how temporal patterns contribute to a prediction. We treat this gap as a property of the predictive architecture rather than a problem to be addressed after prediction. Link-Fact Temporal Rule Inducer (LiFTER) is a neuro-symbolic...
-
61
Capek 0.5: An Execution-Centric Vision-Language Model for Embodied Intelligence
Ying Chen, Weizhen Li, Zhe Hu, Zhenjiang Li, Rui Jiang, Zhifeng Gu, Lihuang Fang, Jiangping Liu, Lei Yi, Jie Chen
cs.AI
Vision-language models are increasingly serving as the reasoning core of embodied agents. Robot execution is inherently iterative: each action reshapes the scene and physical state, continually renewing what must be perceived, reasoned about, and verified. Meeting these demands requires complementary capabilities that differ in supervision signals, prediction formats, and verification criteria. Existing approaches typically develop these...
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.