cs.AI · 2026-10-09 · No. 138
Artificial Intelligence, 2026-10-09.
49 new papers in cs.AI. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
49 entries-
01
On the estimation and validity of AI time horizons---a statistical look at the METR plot
Drew T. Nguyen, William Fithian
cs.AI
METR's 50\% time horizon measures the human completion time of software tasks that an AI solves with 50\% probability, allowing AI capabilities to be expressed in interpretable units. On 228 tasks and 26 AIs, we recompute the time horizons using splines and item-response theory to relax the assumption that the AI difficulty of a task depends linearly on the log of human time. Our fitted spline can be interpreted as a function that...
-
02
BrickBench: Evaluating Agentic Brick Design
Peter Kulits, Yiqing Xu, R. Kenny Jones, Cordelia Schmid, Jiajun Wu
cs.AI · cs.CV · cs.GR
We propose BrickBench, a benchmark for agentic text-conditioned LEGO-set design. Given a prompt, an agent is tasked with producing an assembly that not only satisfies semantic and design criteria, but that can also be physically built. To do so, it must select parts from a discrete library and reason jointly about local and global constraints. We score validity, alignment, and design across three settings that vary in scale and part...
-
03
Ecology of AI Agents: Collaboration Creates a Population Threshold for Takeoff
Erin Crawley, Hidenori Tanaka
cs.AI · cond-mat.dis-nn · cs.MA · physics.bio-ph
AI agents can now conduct real-world cyberattacks, scale up capabilities with the number of agents, and collectively pursue misaligned goals to obtain rewards. Together, these factors raise the risk of a population explosion of misaligned agents: agents could compromise computers and secretly deploy additional agents, creating a self-reinforcing cycle where larger populations develop greater collective cyber capability and expand further....
-
04
Searching for "Harmful Refusal": A Psychometric Audit of an AI Safety Benchmark
Christopher M. Stewart, Preston Botter, Natalie Sarabosing, Muye Zhang, Rachel Phinnemore, Shalini Ghosh, Hong Shen,...
cs.AI
Safety benchmarks typically report one overall score for a suite of datasets, each of which may target one or more safety-related attributes, so models with similar overall scores can have very different attribute profiles. Comparing models is more tractable at the level of individual attributes, yet it is often unclear whether even a single dataset's scores isolate any single attribute. One plausible candidate for such an attribute is...
-
05
HRIL: Learning Multimodal Synergy via Higher-Order Tensor Modeling
Qun Dai, Liangjian Wen, Jiang Duan, Yong Dai, Dongkai Wang, Maolin Wang, Mingjie Wang, Jianzhuang Liu, He Yan, Zhao Kang
cs.AI · cs.LG
Self-supervised multimodal representation learning has achieved remarkable success across diverse domains, yet capturing synergistic information remains challenging due to the complexity of cross-modal interactions. Unlike the shared information across individual modalities, synergy arises when task-relevant signals emerge only from the joint configuration of multiple modalities and cannot be recovered from any modality in isolation. This...
-
06
GeoReform: Reflective Formalization Evolution for Multimodal Geometry Problem Solving
Jialu Wang, Ruichen Zhang, Xiaoou Liu, Hua Wei, Tianlong Chen
cs.AI
Multimodal large language models (MLLMs) often struggle to identify and use geometric relations in diagrams. Recent methods address this challenge by converting geometric entities, relations, and constraints into explicit textual representations for the model to reason over. However, effective formalization is highly non-trivial: on Geometry3K, structure injection fixes 28 errors but introduces 13 new ones among 200 examples. Redundant...
-
07
OnTrack: Real-Time Monitoring and Intervention in LLM Agent Trajectories via Streaming Structure-Aware Optimal Transport
Babak Barazandeh, Connor Swanson, Chinmay Kulkarni, Nikhil Mungel
cs.AI · cs.CL · cs.CY · cs.LG
Agents are deployed in applications from trip planners and stock trading to IT incident triage. In most cases, LLM agents work autonomously with minimal rule-based safeguarding, leading to cost and safety issues from irreversible actions. Recent works resolve this either by using a safeguard agent to monitor behavior or evaluating logs post-hoc. The first adds cost and latency to every step; the second delivers its verdict after the run, when...
-
08
HANS: A Handwritten Answer Sheet Dataset for Noisy Hybrid Document Parsing
Xiazhen Wu, Wansong Qin, Yangbin Zheng, Liangda Fang, Zhan Li, Xiujie Huang, Liushen Zhou, Quanlong Guan
cs.AI · cs.CV
Intelligent grading and automated scoring technologies constitute critical infrastructure for smart education. However, existing document parsing and handwriting recognition benchmarks are predominantly designed for well-structured printed documents or isolated mathematical expressions, lacking datasets that capture the complex characteristics inherent to student answer sheets, including multi-line derivation processes, heterogeneous mixtures...
-
09
Cited but Not Consulted: A Counterfactual Audit of Legal Chain-of-Thought Faithfulness
Saisab Sadhu, Shreeyans Arora, Pratinav Seth
cs.AI · cs.CL · cs.CY
Large language models increasingly justify legal decisions by naming the statute or precedent behind a verdict, treated as evidence that the decision follows from it. We test this directly: holding case facts fixed, we substitute the named legal authority for an unrelated one and decode a model's evolving verdict from its hidden states. Across seven open-weight models (8B-70B) and four benchmarks spanning judicial and contractual reasoning,...
-
10
Accurate but Not Humble: Evaluating Epistemic Humility in LLM Agents under Knowledge Conflict
Kaiser Sun, Bernal Jimenez Gutierrez, Hongjun Liu, Jingyu Zhang, Jie Gao, Mark Dredze, Daniel Khashabi
cs.AI · cs.CL
When retrieved evidence contradicts an agent's prior beliefs, does it revise its answer, acknowledge uncertainty, or persist with an incorrect conclusion? Existing evaluations of agentic systems focus primarily on task success, offering limited insight into how agents handle such conflicts. We propose to evaluate agents on epistemic humility (EH): the agent's willingness to recognize, act on, and communicate uncertainty during task execution....
-
11
Overcoming Prior Barriers: Supervised Fine-Tuning under Long-Tail Distribution
Haohui Wang, Jiahao Xu, Wangzhi Zhan, Tong Zeng, Dongqi Fu, Hong Li, Swastik Roy, Naren Ramakrishnan, Chris North,...
cs.AI · cs.CL · cs.LG
Supervised fine-tuning (SFT) adapts pretrained large language models (LLMs) to downstream tasks, but the required concepts can receive substantially different levels of pretrained support. Frequent concepts are more likely to be well learned, whereas rare concepts may remain weakly represented. We introduce a novel notion named prior barrier to quantify how strongly the pretrained model supports competing concepts over the target concept. We...
-
12
Can AI Agents Learn Their Way to the Top? Evaluating Heuristic Learning in a Long-Running Game Agent Competition
Kaisen Yang, Qingle Liu, Kejin Wang, Yicheng Zhao, Jieming Li, Shenghan Zheng, Ruize Yang, Bojun Yang, Heng Gong,...
cs.AI · cs.CL
Adversarial games have driven advances from heuristic search to reinforcement learning, yet learning and adapting strategies from limited samples remain challenging. AI agents offer an alternative by turning game experience into revisions of executable policies. Building on heuristic learning (HL), we formalize Adversarial Heuristic Learning (AHL), a paradigm that uses AI agents as learning engines to refine game policies and supporting...
-
13
Prior or Feedback? What an LLM Uses When Adapting Neural Operators
Julian Chan, Javier Mora Jimenez
cs.AI · cs.LG · physics.comp-ph
Do LLM scientific agents rely only on their initial task context, or do they adapt their decisions in response to experimental feedback? We study this question in neural operator adaptation, where a large language model (LLM) selects fine-tuning configurations under a limited trial budget. Across transfers within and between partial differential equation (PDE) families, the LLM achieves lower held-out test nRMSE than random search and...
-
14
Verdict Without the Rule: Diagnosing and Auditing Regulatory Rule Sensitivity in LLM Compliance Systems
Saisab Sadhu, Aadit Sengupta, Vinay kumar Sankarapu, Pratinav Seth
cs.AI · cs.CL · cs.CY
Large language model compliance systems are deployed on the assumption that a verdict depends on the regulatory rule it is given. We test this directly across five models and 20 regulatory and platform-policy domains: delete, swap, or negate the governing rule while holding the case fixed, and check whether the verdict changes (OCS) or the model's internal representation of compliance shifts at all (ICS-delta). Neither moves much: models'...
-
15
A Structural Theory of Cognitive Representation and Problem Solving,Contexts, Invariance, and the Knowledge Space
Antal Jakovác, András Telcs
cs.AI
Learning and problem solving depend critically on the structure of internal representations. While many modern data-driven artificial systems achieve strong predictive performance, their learned representations often lack explicit structure for expressing abstraction, invariance, and task-relevant regularities. We propose a minimal structural framework in which representational operations relevant to problem solving, such as context...
-
16
Looking Inside LLMs: Small-World Connectivity as a Signature of Reasoning Performance
Zheng Huang, Sansheng Cao, Enpei Zhang, Weikang Qiu, Elynn Chen, Xiang Zhang, Yaoqing Yang, Rex Ying, Dawei Zhou, Yujun Yan
cs.AI
Understanding large language model (LLM) reasoning requires looking beyond behavioral performance to examine how reasoning ability is reflected in internal organization. Inspired by neuroscience findings linking higher intelligence to stronger small-world organization in functional brain networks, we investigate small-world connectivity as a structural signature of LLM reasoning. We construct functional graphs from attention-head activation...
-
17
Learning Probabilistic Logic Programs with Functional Gradient Guided Language Models
Saurabh Mathur, Sahil Sidheekh, Bhavan Vasu, Farbod Tavakkoli, Prasad Tadepalli, Kristian Kersting, Sriraam Natarajan
cs.AI
Declarative logic programs offer a powerful and interpretable abstraction for encoding relational structure and neurosymbolic reasoning, by expressing dependencies as weighted compositional rules. However, inducing them from data remains fundamentally hard, bottlenecked by the combinatorial explosion of symbolic search spaces. LLMs have recently emerged as powerful hypothesis generators, but when used in isolation, they lack the capacity to...
-
18
One Word Opens the Gate: The Option-Channel Attack on Typed Decision Models as Agent Guardrails
Seyedarmin Azizi, Erfan Baghaei Potraghloo, Massoud Pedram
cs.AI
A typed decision model reads a piece of text and returns a probability over caller-defined options, each with a short written definition, generating no text. Recent work places these models in agent systems as guardrails: the component that reads a proposed tool call or incoming message and decides whether to allow it. We evaluate seven open-weight models in that role and report the two error directions separately: a fail-open error allows a...
-
19
When Has a Bayesian Neural Network Sampled Enough? Adaptive Inference Time with Statistical Guarantees
Fabian Denoodt, Sibylle Hess
cs.AI
Bayesian neural network predictions are commonly approximated using a fixed number of Monte Carlo samples per input, without controlling the resulting error that comes from this finite sample. We propose the use of confidence sequences to dynamically determine how many samples are needed while maintaining statistical guarantees. We consider several ways in which predictive probabilities are used, including identifying the most likely class,...
-
20
Recursive Self-Improvement through Multi-Agent Self-Supervision
Hyunin Lee, Jinglue Xu, Jeffrey Seely, Donghyun Lee, Somayeh Sojoudi, Matei Zaharia, Yujin Tang
cs.AI
Recursive self-improvement (RSI) of a model on non-verifiable tasks, such as open-ended research, faces a supervision bottleneck when its outputs exceed what even human experts can reliably assess, leaving the model itself (optimizee) as the best available optimizer and evaluator. However, a single model instance struggles to critique and improve its own complex reasoning under this homogeneous loop. To address this, we propose Multi-Agent...
-
21
Learning to Plan by Looking Back: Hindsight Hierarchies for Training Reasoning Models
Lars Simon, Holger Eble, Manuel Radons
cs.AI · cs.LG · cs.LO
We introduce a self-improvement loop for reasoning models based on the following observation: Even when the difficulty of a problem exceeds the model's current solving abilities, an additionally supplied solution might enable the model to extract useful solution ideas in hindsight. We operationalize this by jointly training the same model to exhibit the following three capabilities: predicting solution ideas from problems alone,...
-
22
Instruction-Conditioned Electromagnetic Spectrum Understanding via Budget-Adaptive Signal Tokenization
Lei Zhai, Zhihao Chang, Shuyuan Yang, Zhixi Feng
cs.AI · eess.SP
Electromagnetic spectrum monitoring increasingly requires flexible analysis beyond task-specific recognition and detection. Multimodal large language models offer a unified interface, but extending vision-language models (VLMs) to raw I/Q signals requires tokenization that balances fidelity against a strict budget. For signals, dense encoding causes token costs to grow with observation length, whereas fixed-resolution compression may discard...
-
23
Q-Shaped Options for Hierarchical Reinforcement Learning
Clarisse Wibault, Antoine Gorceix, Antonio Léon Villares, Alexey Zakharov, Evangelos Chatzaroulas, Michael Matthews,...
cs.AI
Learning to tackle long-horizon, goal-conditioned tasks requires an agent to reason over extended timescales and act across a broad range of states. In principle, Hierarchical Reinforcement Learning (HRL) addresses both challenges through the interaction between action (temporal) and state (spatial) abstraction. First, using an action abstraction to represent temporally extended behaviour as options reduces the effective decision horizon....
-
24
OA-MAP: Evidence-Grounded Multi-Agent Multimodal Framework for Interpretable Knee Osteoarthritis Progression
Sixu Chen, Mingrui Yang, Qiang Guan, Xiaojuan Li
cs.AI · cs.MA
Knee osteoarthritis (KOA) progression prediction can support patient monitoring, requiring the integration of multimodal data and multidomain expertise. Moreover, isolated risk estimates provide limited insight underlying a prediction. To automate the progression assessment workflow and reduce manual effort while providing interpretable findings and supporting evidence, we present OA-MAP, an autonomous multi-agent framework for...
-
25
An Investigation of Model Coherence: Narrow Finetunes Contradict Themselves Under Resampling
Robert Graham, Yariv Barsheshat, Phil Blandfort, Sabri Alouache
cs.AI
A large body of research measures model coherence based on output variance without adequately considering competing causes. We identify two such causes, ambiguity and indifference, and we introduce a set of 175 questions where contradicting answers cannot easily be explained by either. We then measure incoherence in terms of contradictions when resampling answers to the same question. In contrast to other methods our metric has high...
-
26
Use and Disuse: Intent-Structured Experience Consolidation for Memory and Learning in LLM Agents
Xiangyi Zeng, Baihang Liu, Xutong Wang, Ze Jin, Yunpeng Li, Qixu Liu
cs.AI
The evolution of Large Language Model agents from single-task execution to long-term autonomous operation highlights the critical challenge of transforming continuous experiences into reusable knowledge. To address this, we propose Hippocam, a hierarchical memory and continual learning architecture. Hippocam draws inspiration from two characteristics of human memory: cognitive processes selectively maintain information relevant to current...
-
27
Universal Textual Teaching for LLMs
Zhanyi Lu, Huan Wang
cs.AI
Knowledge distillation (KD) transfers knowledge from stronger Teacher models to weaker Student models, but most methods require training the Student parameters, thereby binding the distilled knowledge to a specific architecture and checkpoint. This implicit representation is difficult to interpret or reuse across models and limits KD for API-only or costly-to-train models. This paper studies knowledge transfer for large language models...
-
28
Recompose and Refine Latent Reasoning Flows for Vision-Language-Action Models
Hongyu Shi, Sen Zhao, Zuyu Zhang, Lifeng Shen, Ding Zou, Xinyu He, Xu Zhang, Qinghua Zhang
cs.AI
Latent reasoning enables vision-language-action (VLA) models to transform multimodal observations into task-relevant internal states before generating continuous robot actions. While existing methods learn to generate or refine such states for each policy query, they discard successful reasoning after execution and therefore reconstruct similar computation from scratch. We present Reasoning and Flow Memory (FLOWMEM), a unified VLA model that...
-
29
EvoAlloc: A Self-Evolving Resource Allocation Agent for Efficient Program Evolution
Yanning Dai, Yuhui Wang, Nanbo Li, Wenyi Wang, Jürgen Schmidhuber
cs.AI
LLM-based program evolution relies on evaluation feedback to guide the iterative search for high-performing programs. However, evaluation is often computationally expensive, making it essential to allocate limited resources to candidates that can most effectively advance the search. Existing LLM-based methods typically rely on fixed allocation strategies throughout the search, potentially wasting resources on low-value candidates while...
-
30
Is Memorization Context-Sensitive? Prefix-Based Extraction Beyond Isolated Prefixes
Ali Satvaty, Narjes Sharafi, Jirui Qi, Suzan Verberne, Fatih Turkmen
cs.AI
Large language models (LLMs) can expose memorized training sequences under prefix-based extraction: given a prefix from a training example, the model may assign high probability to the original continuation. In deployed systems, however, prefixes are rarely evaluated in isolation. They often appear together with instructions, retrieved documents, or other task-specific context, as in retrieval-augmented generation (RAG). This motivates...
-
31
When Should Agents Think? Adaptive Reasoning via Cross-Turn Estimation
Yiruo Cheng, Shen Huang, Xiaoshuai Song, Jiejun Tan, Guanting Dong, Pengjun Xie, Ji-Rong Wen, Zhicheng Dou
cs.AI · cs.CL
Large language model (LLM)-based agents have demonstrated strong capabilities on complex tasks. They typically perform reasoning before each action throughout an interaction trajectory. However, reasoning may not be necessary at every turn, as reasoning produced earlier can continue to support subsequent actions. A key challenge is therefore to determine when existing reasoning remains sufficient and when a new reasoning step is needed,...
-
32
Structure Tax: How Structured Output affects LLMs Performance
Vineet Kumar, Kanishka, Bhuvanesh Mandora
cs.AI
Deploying large language models in production often requires constraining outputs to structured formats such as JSON or XML, and prior work treats the resulting accuracy loss as an inherent `structure tax'. We re-examine this claim by evaluating a battery of models, datasets and schemas, measuring task accuracy, confidence calibration, and hidden-state geometry. The tax turns out to depend on schema design rather than on structure per se:...
-
33
InterviewPlayground: A Simulation Environment for Evaluating AI Interviewers
Jonathan Ivey, Aimee Liang, Arthur Y. S. Wang, Madeline Mandell, Ziang Xiao, Anjalie Field
cs.AI · cs.CL
Increasingly, AI interviewers are being developed to elicit open-ended responses in applications like market research, public polling, preference elicitation, and social science research. However, evaluating AI interviewers is challenging because they function in extended, multi-turn interactions where they must adapt to participant behaviors. To address this need, we develop InterviewPlayground, a simulation environment for evaluating AI...
-
34
PulseBound: Future-Beat State Forecasting Under an Explicit Information Boundary
Chenyang Xu, Donglin Xie, Xi Xiang, Xiaoyu Li, Yufan Lu, Jiqiun Gao, Yi Zhao, Xin-Yi Li, Guangpu Zhu, Zijian Wang,...
cs.AI
Predictive representation learning from photoplethysmography (PPG) can violate causal information access even with causal attention, as normalization, nonlocal transforms, or companion views may depend on withheld samples. We introduce PulseBound, a PPG representation learner combining physiologically structured future-beat prediction with an explicit stored-window information boundary. A content-independent cutoff separates the visible...
-
35
Complexity of Grounded Semantics and Preferred Semantics in Finitary Argumentation Frameworks
Jinfan Xu, Jieting Luo
cs.AI · cs.LO
Abstract argumentation frameworks (AFs) introduced by Dung provide a formal foundation for non-monotonic reasoning in artificial intelligence. While decision problems for general infinite AFs typically reside at high levels of the analytical hierarchy ($Σ_1^1$ or $Π_1^1$), restricting the framework to be computably finitary reduces some of the complexity to the arithmetical hierarchy. In this paper, we present a complexity mapping of grounded...
-
36
An Interpretable Approach to PDE Solution Discovery via Structural Experience Distillation
Yunpeng Gong, Huolong Wu, Can Yang, Min Jiang
cs.AI
PDE solution discovery aims to identify explicit symbolic expressions for unknown physical fields from observations under known physical constraints. Existing methods, however, collapse data fidelity and physical consistency into a single terminal score used as the sole feedback signal, providing little information about which subexpressions are responsible for a candidate's final performance. This opaque terminal feedback severely limits the...
-
37
MetaOPD: Meta-Learned Token Weighting for On-Policy Distillation
Zipeng Wang, Xinpeng Dong, Yuefan Wang, Pingchen Lu, Xian Wei, Kun Kuang, Fei Wu, Zhongxiang Dai, Min Zhang
cs.AI
On-policy distillation (OPD) trains a student on its own generated responses using token-level teacher supervision. However, uniform weighting overlooks differences in token learning value, while existing weighting methods rely on predefined mappings from prediction signals to token weights. These mappings are not learned from the effectiveness of the resulting student updates, limiting their ability to adapt to evolving learning needs. In...
-
38
MindFlow: Mind Supernet Powered Thinking Flows for Research Idea Innovation
Mengdi Liu, Wenjue Chen, Wenyue Chen, Cheng Yang, Fanqi Kong, Zhangyang Gao, Xiaoxue Cheng, Yiheng Li, Yujian Yuan,...
cs.AI · cs.CL · cs.MA
Research idea innovation is a fundamental engine of scientific progress, yet it remains difficult to generate and evaluate in a scalable and controllable way. This challenge lies in its inherently open-ended and multi-objective nature, where ideas should balance novelty, plausibility and feasibility. While recent LLM-based approaches have made progress through carefully designed prompts or agent pipelines, they are constrained by predefined,...
-
39
How Is Automated Research Evaluated? A Survey of Benchmarks and Evaluation Practices
Liulei Zhang, Dejing Zhou, Chuyue Huang, Guanhua Chen, Yutong Yao, Lidia S. Chao, Chi Man Vong, Derek F. Wong
cs.AI
Automated research systems support literature synthesis, ideation, experiments, writing, and peer review, but their evaluation is dispersed across tasks, benchmarks, and studies that are difficult to compare directly. We review this literature from the perspective of evaluation design and evidence, covering six targets: literature synthesis, research ideation, executable workflows, scholarly writing and communication, automatic peer review,...
-
40
LEVER: Adaptive Cost-Aware Proof Search Over AND/OR Graphs
Nihal Jain, Shuangjie Yao, Begum Cicekdag, Zhuo Zhang, Suman Jana
cs.AI
Mathematicians value proofs for more than correctness: among correct proofs, simplicity, purity and the computational cost of finding them vary widely. Yet LLM-powered theorem provers largely search for any correct proof, and improve its quality only after it is found. We propose LEVER, a proof search algorithm that makes the objective over correct proofs programmable and optimizes it during search. LEVER scores partial proofs over an AND/OR...
-
41
Probability-Signature Dynamics: Unpacking Modular Addition Learning Within Two-Layer Networks
Yunji Wang, Junjie Yao, Linyu Liu, Pinyan Lu, Zhi-Qin John Xu
cs.AI
Neural networks trained on modular addition tasks often develop Fourier-structured representations that support exact generalization. While prior work has identified these Fourier circuits, the mechanism by which gradient-based training selects them from the data distribution remains unclear. We address this question using probability signatures, which express leading gradient interactions through conditional statistics of the training...
-
42
Memento 3: Model-Based Recursive Self-Improvement through Reflective Rulebooks
Haoyu Zhao, Zhengxu Yu, Zhiyuan He, Meng Fang, Rasul Tutunov, Haitham Bou-Ammar, Weilin Luo, Jun Wang
cs.AI · cs.CL · cs.CV · cs.LG
Learning to act in unfamiliar environments requires agents to infer how the world works and revise that understanding as new evidence arrives. Yet limited observations can support multiple world models that explain past interactions but predict different outcomes in unseen states. We introduce Memento 3, building on the Memento series to enable frozen LLM agents to continually learn explicit world models through external memory. The agent...
-
43
RouterInterp: Understanding Superposed Specialisation in Mixture of Experts Routing
Ilya Lasy, Nora Yinuo Cai, Kola Ayonrinde
cs.AI · cs.CL · cs.LG
Sparse Mixture of Experts (MoE) models scale more efficiently than dense models by routing tokens to modular expert networks that are only active for processing a fraction of tokens. A leading hypothesis for the performance of MoE models is that each expert specialises in a single, coherent domain. However, interpretability efforts that assume this hypothesis have generally been unsuccessful. We propose and present evidence for an alternative...
-
44
Safe Actions Alone Do Not Ensure Safe Agents: Identifying Unfulfilled Obligations with Guard Models
Youwei Feng, Yitong Zhang, Yuetong Liu, Jia Li
cs.AI
Guard models are increasingly used to safeguard LLM-based agents, primarily by identifying actions that agents are forbidden to perform. However, identifying forbidden actions alone is insufficient to ensure agent safety. In this paper, we argue that agent safety also depends on identifying required yet unperformed safety-critical actions, which we call obligations. Our preliminary study on a popular benchmark for evaluating safety shows that...
-
45
What Output-Only Review Cannot Verify: Study Contracts for Research Agents
Eitan Waks, Ben Glocker
cs.AI
Some defects in an AI-generated study can be identified from its artifacts; others require knowledge of what was approved before execution. We propose study contracts that bind declared experimental choices, run obligations and claim scope to recorded execution evidence, and distinguish this contract-relative verification from scientific truth. A diagnostic using eight self-authored clean/mutated pairs illustrates the information boundary. A...
-
46
Where Draft Trees Lose Target Mass: Exit-Guided Speculative Decoding
Shijing Hu, Xuancheng Ren, Zhihui Lu, Pan Zhou
cs.AI
Tree-based speculative decoding verifies multiple draft continuations in one target-model pass, but finite trees built from draft scores face a fundamental draft-target mismatch. We ask whether better exact verification can increase acceptance on a fixed tree and how target feedback can improve the tree itself. Through a target-flow view, we identify a canonical exit law and prove that one plus target coverage sharply bounds the expected...
-
47
Scalable AI Uncertainty Quantification via Generalized Laplace Active Subspaces
Wouter N. Edeling, Peter V. Coveney
cs.AI
Reliable uncertainty quantification (UQ) is essential for deploying neural networks in scientific and high-stakes applications, but full Bayesian inference over the network parameters is computationally infeasible. We propose a low-rank generalized Laplace approximation for neural-network UQ based on a small number of data-informed curvature directions. Starting from a generalized Bayesian posterior defined through an empirical loss, we...
-
48
Onboard Marine Anomaly Detection on $Φ$sat-2: From Simulation-Based Development to In-Orbit Demonstration
Clotilde Szywala, Thomas Goudemant, Marjorie Bellizzi, Benjamin Francesconi, Adrien Girard
cs.AI · cs.CV
Onboard Artificial Intelligence can improve responsiveness and bandwidth efficiency of Earth Observation systems by processing data directly on the satellite. This paper presents the experience gained from the development, onboard integration, and post-launch adaptation of a lightweight marine anomaly detection pipeline deployed on the European Space Agency's $Φ$sat-2 mission. The application combines sea segmentation, self-supervised feature...
-
49
MemTrial: Learning When to Trust Memory in LLM Portfolio Agents
Guanghao Wu, Zhuo Cai, Shoujin Wang
cs.AI
Large language model (LLM) agents for portfolio management learn from experience: they credit each experience in their memory with the outcome of the decisions that used it. In financial markets, however, this outcome mostly reflects the market move shared by all decisions on that date, so the credit tracks the market rather than the experience, and these agents often do worse than simply holding the equal-weight (1/$N$) portfolio. We ask how...
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.