cs.AI · 2026-08-19 · No. 89
Artificial Intelligence, 2026-08-19.
53 new papers in cs.AI. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
53 entries-
01
On the Fragility of Self-Improving Agents: Variance, Task Order, and Underspecification
Qinyuan Ye, Yu Li, Yada Pruksachatkun, Jiaxin Zhang, Chien-Sheng Wu
cs.AI · cs.CL · cs.LG
Memory-based self-improving agents--those that learn from an online stream of tasks and improve over time by maintaining a textual memory bank--have shown great promise in recent literature. However, the reliability aspects of these methods have been critically overlooked. In this work, we conduct a comprehensive re-evaluation of two memory-based methods, broadening the scope of evaluation along two axes: (1) including multiple runs to...
-
02
Delegation Asymmetry in Agentic Recommender Systems: Measuring Two-Sided Receptivity in Online Dating
Daria Leshchikova, Valentina V. Kuskova, Dmitry Zaytsev, Valerii Klimov
cs.AI
Autonomous LLM agents that converse on a user's behalf are an emerging design pattern in matching platforms, yet their viability depends on a condition rarely examined: users must accept not only delegating conversation to an agent, but also receiving agent-mediated communication from others. We study this condition using two large-scale surveys of active users of a major dating platform (N=2,894 on generative profile features; N=2,617 on...
-
03
HLSR: Hybrid Live Forecast Selective Dynamic Vehicle Rerouting for Real-Time Congestion Avoidance
Xiao Wang, Shun Ren Yang, Hui Nien Hung
cs.AI
Urban traffic congestion reduces productivity and increases travel cost and emissions. Network-wide live travel-time shortest-path rerouting can be highly effective in simulation, but assumes that essentially every on-road vehicle is replanned every decision period. We propose HLSR, a selective hybrid live--forecast vehicle rerouting framework that fuses live edge speeds with short-horizon forecasts under limited intervention scope. Building...
-
04
StagedWorkspace: A Versioned Workspace for Knowledge-Work Agents
Yining Hua, Hongbin Na, Yifan Zhou, Akshay Kalose, Cyrus Ayubcha, Levi Lian
cs.AI
AI agents increasingly perform knowledge work (i.e., produce and modify persistent digital artifacts such as code repositories, documents, spreadsheets, slides, reports), yet the parsed views they search, the native files they edit, the changes they review, and the artifacts they submit can refer to different versions of the same work product. We formulate this as a workspace-state contract: every view should be explicitly tied to a version...
-
05
Can Large Language Models Explain Flight Safety Events? A Prior-Guided Semantic LLM-based Approach
Lu Xu, Xu Li, Linjiang Zheng, Fan Li, Riquan Zhang, Jiaxing Shang
cs.AI
Improving flight safety with flight data requires not only accurate detection of risk events, but more importantly, clear interpretation of their underlying causes at the level of pilot control behavior. Existing explainable AI techniques, such as feature importance maps, often require considerable domain knowledge to translate them into operationally meaningful explanations. Large Language Models (LLMs), which excel at language reasoning,...
-
06
Towards Zero-Shot Task Transfer with Neurosymbolic World Models
Isidoro Tamassia, Lennert De Smet, Giuseppe Marra
cs.AI · cs.LG
State-of-the-art model-based reinforcement learning methods learn neural world models that allow policy improvement by planning in a latent space, without assumptions on the structure of the underlying environment. While expressive, these models are generally task-dependent: they learn uninterpretable latent representations that are tied to the training task and thus hard to generalize to new tasks. In this work, we present a novel world...
-
07
Procedural Content Metageneration via Program Search and Continual Abstraction Discovery
Matthew Siper, Ahmed Khalifa, Julian Togelius
cs.AI · cs.LG · cs.NE
Large language models can generate executable programs, which makes it possible to search directly over procedural content generators rather than individual levels. We study this approach in Sokoban, Zelda, Dangerous Dave, and Lode Runner. Each run evolves complete Python generators through language-model mutation and crossover. We introduce Continual Abstraction Discovery, or CAD, which extracts reusable primitives from high-fitness programs...
-
08
EvoTS-Agent: A Self-Evolving LLM Agent for Financial Time Series Change Point Detection
Lei Jiang, Ye Wei, Xinyu Xi, Jordan Langham-Lopez, Yifan Bao, Raad Khraishi, Yihao Ang, Anthony K. H. Tung, Lukasz...
cs.AI · cs.CE
Financial time series exhibit non-stationary and heterogeneous statistical properties, making change-point detection challenging because no single unsupervised algorithm performs consistently across assets and market regimes. Conventional workflows consequently depend heavily on expert-driven model selection, feature design, and hyperparameter tuning, limiting their scalability and adaptability. We propose EvoTS-Agent, a validation-guided...
-
09
Adaptive Policy Portfolios for Robust Markov Decision Processes
Kasper Engelen, Sebastian Junges, Guillermo A. Pérez, Marnix Suilen
cs.AI · cs.LO
Robust Markov decision processes optimize one policy against a set of plausible transition functions. This can be conservative when the unknown dynamics are fixed and become partially identifiable after deployment. We study adaptive policy portfolios: finite sets of memoryless randomized policies synthesized offline and paired with a lightweight online selector. Robust regret is a natural measure of portfolio quality: for each plausible...
-
10
AutoResearch: Insight In, Hallucination Out
Yiming Ren, Xiang Liu, Qumeng Sun, Xiao Zhang, Jiahao Li, Haoyang Zhang, Junjie Wang
cs.AI · cs.MA
Autonomous research systems are increasingly capable of executing long research workflows, yet automation alone does not ensure that the resulting process remains scientifically grounded. We introduce AutoResearch, a two-stage system that connects Idea Generation with Idea Execution to address both how research ideas are formed and how they are reliably established through experimentation. In Idea Generation, AutoResearch continuously...
-
11
ARASH: Adaptive Retrieval And Shot Selection for Tabular Prediction
Samirasadat Jamalidinan, Yue Xu, Kazem Cheshmi
cs.AI
Tabular prediction is a critical task across numerous applications. The recent success of large language models has sparked various approaches for adapting them to the tabular domain. A prevalent strategy involves training or fine-tuning specialized Tabular Foundation Models (TFMs) such as TabPFN. However, TFMs require substantial computational resources, and frequent model retraining is often impractical. In-context learning (ICL),...
-
12
StartupBench: Benchmarking General-Purpose Agents on Market-Validated End-to-End Workflows
Liya Zhu, Xin Ma, Tao Liu, Haodong Wang, Ge Zhang, Jingzhe Ding, Qingshui Gu, Yongjie Zhong, Jinxiang Meng, Yuan...
cs.AI
Recent advances in Large Language Models(LLMs) and agents have substantially improved the ability of AI systems to execute complex tasks. Yet existing benchmarks largely rely on researcher-selected tasks, leaving uncertain whether such progress extends to the work that real-world users actually demand from AI systems. We introduce \textbf{StartupBench}, an E2E agent benchmark grounded in market-validated AI startup products. Rather than...
-
13
D$^2$ACCI: A Dual-Loop Diagnostic Protocol for Evidence-Preserving Agent Memory
Xule Liu, Yijun Liu, Chao Li, Shao Kun
cs.AI
Memory is a key capability of LLM agents. Persistent memory extends this across sessions---enabling recall, revision, and personalization. Yet its multi-stage pipeline (ingestion, retrieval, filtering, generation) makes failures difficult to localize: end-to-end evaluation reveals that an error occurred, but not which stage caused it. Existing evaluations often report aggregate performance without paired statistical comparisons, slice-level...
-
14
The Curious Case of Exploding DecPOMDPs: Containing the Fire through Policy Counting
Nazlı Nur Karabulut, tanya Braun
cs.AI
Decentralised partially observable Markov decision processes (DecPOMDPs) provide a general framework for modelling multi-agent decision making under uncertainty. However, DecPOMDPs are known to suffer from exponential complexity in the number of agents. One way to combat this intractability in agent numbers is to look at partitions of agents that exhibit a form of symmetry among agents, allowing for a compact encoding by counting. However, a...
-
15
Neuro-symbolic learning over OWL 2 DL via consequence-based compilation to differentiable circuits
Olga Mashkova, Asaad Mohammedsaleh, Fernando Zhapa-Camacho, Robert Hoehndorf
cs.AI
OWL 2 DL ontologies, grounded in the description logic $\mathcal{SROIQ}$, express large knowledge bases in biomedicine and the Semantic Web. Neuro-symbolic (NeSy) learners over description logics either embed the ontology in a continuous space, abandoning classical entailment, or restrict to the Horn fragment $\mathcal{EL}^{++}$, which has a single canonical model. We present Baobab, which compiles a $\mathcal{SROIQ}$ ontology with a finite...
-
16
Evaluating the Diversity of AI-Generated Content with Diversity Profiles
Xiuyuan Hu, Xuege Hou, Guoqing Liu, Yang Zhao, Jieran Li, Dongbiao Sun, José Miguel Hernández-Lobato, Hao Zhang, Xue Liu
cs.AI
Diversity is a fundamental criterion for evaluating generative artificial intelligence (AI) systems, yet its measurement remains inherently ambiguous. Existing approaches typically represent generated samples in an embedding space, compute pairwise distances or similarities, and aggregate them into a single scalar score. Such scalar summaries are convenient, but they often encode different inductive biases and may yield contradictory rankings...
-
17
Beyond Suspicious Steps: Ontological Trust in Long-Horizon Agents
An He, Yao Wang, Haibin Zhang
cs.AI
Long-horizon agents increasingly operate across many steps, tools, and observa- tions. In this setting, the relevant oversight question is not only whether each action is locally valid, but whether the evolving trajectory still corresponds to the task the user authorized. Drift can accumulate quietly: an agent may call the right tool with plausible arguments at every step, while its prefix moves toward a broader role, an adjacent objective,...
-
18
Accuracy and Robustness of Model Cascades Under Data Perturbations
Pallavi Mitra, Jai Kushwaha, Felix Biessmann
cs.AI
Prediction cascades significantly reduce energy consumption of Artificial Intelligence (AI) models while maintaining high predictive performance. The idea is that easy inputs are routed through a lightweight small model, and difficult uncertain cases are deferred to a larger model. While this design can improve computational efficiency on clean data, its effectiveness depends on the reliability of confidence-based routing. Input degradations,...
-
19
Mixture-of-Expert Blocks Contain Strong Hallucination Detection Signals
Joao Fonseca, Rodrigo Rodrigues, Paolo Romano
cs.AI · cs.LG
Despite their widespread use, Large Language Models (LLMs) remain limited by a fundamental problem: the generation of plausible but false content, known as hallucinations. Most existing detection methods operate at the answer or sentence level, yet per-token detection is essential for localizing hallucinated spans and enabling fine-grained interventions. In this paper, we explore the use of the Mixture-of-Experts (MoE) paradigm to address...
-
20
Auditing Self-Evolution in Financial Agents: Capability Gains, Security Drift, and Execution-Interface Mismatch
Jialong Li, Jialing Zhu
cs.AI
Self-evolving agents turn experience into reusable skills, workflows, or memories, but post-evolution accuracy alone does not show whether learned behavior preserves previously correct behavior or security. We audit SkillOpt, Agent Workflow Memory (AWM), and ReasoningBank in simulated e-banking using matched benign acquisition trajectories, sealed evaluation endpoints, execution-grounded checks, and independent state replay. On Qwen 3.7...
-
21
GraphWake: Group Polarization via Memory-Mediated Polarization Cascade in LLM-Agent Communities
Haoran Bu, Zejian Chen, Litian Zhang, Xi Zhang
cs.AI
LLM-driven agents can autonomously exchange opinions on online platforms and form communities. Such agent-operated social platforms raise a new security concern: attackers may manipulate agents to induce group polarization. Existing methods manipulate agent prompts or construct echo chambers, both of which are difficult to realize in practice. We therefore formulate a new threat, Memory-Mediated Polarization Cascade, which uses agent memory...
-
22
LLM-Derived Preference Judgments Are Not Self-Consistent
Matthew T. Ford, Francis Bahk, Jingjing Wang, Adam S. Jovine, Tinghan Ye, David B. Shmoys, Peter I. Frazier
cs.AI · cs.CL
Agents increasingly interpret a person's natural-language preferences by querying an LLM for numerical preference judgments, e.g., by asking how much the person would be willing to pay for an item. A growing body of work estimates a utility function from these judgments and then chooses actions based on their estimated utility. This pipeline assumes the judgments are approximately self-consistent: that a single utility function can reproduce...
-
23
Beyond the Trace: Coupling an Interpretable Reasoning-State Readout to Native MoE Routing
Kang Chen, Sihan Zhao, Yixin Cao, Yugang Jiang
cs.AI
What a reasoning model writes is only a partial record of the process that produces it. We introduce a two-level internal readout for mixture-of-experts reasoning. We first distill vocabulary-scale J-space into J64, a 64-axis semantic frame learned from the model's own reasoning states. J64 reveals readable process state that the emitted trace does not show: it separates inference effort from problem-induced strain. It also adds 0.096 to...
-
24
Graph Surgery and the Do-Operator: A Precise Correspondence for Acyclic Structural Causal Models
Satpreet Makhija
cs.AI · cs.PL
The $\operatorname{do}$-operator is described graphically by deleting arrows into its targets and functionally by replacing their mechanisms with constants. To call these operations equivalent is not yet a mathematical statement: one returns a graph and remembers only the targets, whereas the other returns mechanisms and also remembers the imposed values. We make a dependency-level comparison precise for deterministic acyclic structural...
-
25
Validated Adaptation for Aerial Crowd Monitoring at Mass Gathering Scale: A Deployment Protocol, a Severity Law, and a Diagnostic for Label-Free Drone Crowd Counting, Toward the FIFA World Cup 2034 (Saudi Arabia)
AlAnoud AllGhayth, AlJawharh AlOtaibi, Jude AlSubaie
cs.AI
Saudi Arabia will host the 2034 FIFA World Cup and already operates crowd management at Hajj scale. Drone-based counting must hold accuracy on footage unlike anything in its training corpus, without labels, and must warn of dangerous inflow before a crush forms. We deliver a validated answer built on 525 controlled runs, a full-resolution corpus study, five falsification ablations, and a five-condition safety-interlock evaluation. Label-free...
-
26
MoNe: Modular Neural Memory for Efficient Long Context Inference
Wonguk Cho, Kyubyung Chae, Tribhuvanesh Orekondy, Sunghyun Park, Hyoungwoo Park, Jeongho Kim, Arash Behboodi,...
cs.AI · cs.CL · cs.LG
We present MoNe, a lightweight modular neural memory that attaches to any frozen pretrained Transformer to enable long-context inference without retraining. MoNe reads context in fixed-size segments via test-time learning of fast-weight neural memory networks with layer-localized gradient updates; at inference, the memory generates keys and values from the query tokens alone, with no context tokens re-read. This two-phase design decouples...
-
27
TRUSS: Towards Task-Reliable and User-Safe Automated Agent Skill Generation
Zhibo Zhang, Zhen Ouyang, Ling Shi, Kailong Wang
cs.AI · cs.SE
Agent Skills package reusable natural language procedures with executable resources, enabling software agents to acquire task specific capabilities without model adaptation. Automatically generating such Skills can improve task performance, yet evaluating a candidate solely from its artifact or final task outcome leaves unresolved which actions the equipped agent will perform and which side effects those actions will produce. We present...
-
28
Quantifying Risk Under Evolving Uncertainty: Belief-Dependent Robustness for Safe Sequential Decision Making
Deep Kumar Ganguly, Jan Kretinsky
cs.AI
How cautious should an agent be while it is still learning its environment? We propose RATTL (Risk-Adversarial Total-Reward Learning), which ties caution to epistemic uncertainty: the agent holds a Bayesian posterior over unknown dynamics and plans against a Wasserstein ambiguity set whose radius is a monotone function of that posterior. The radius contracts with evidence, so behaviour interpolates continuously between worst-case robustness...
-
29
When to Review: Spaced Repetition for Continual Pre-Training of Language Models
Alankar Atreya, Devesh Batra, Yoages Kumar Mantri, Geremy Bantug, Greig A Cowan, Raad Khraishi
cs.AI · cs.LG
Continual pre-training of large language models must acquire new information without erasing old knowledge. Existing replay methods often choose a global old/new mixture and sample uniformly, ignoring that examples differ in how quickly they are forgotten. We formulate continual pre-training as adaptive review scheduling: the training loop should decide not only how much history to replay, but which examples should return at each step. We...
-
30
Agent Lightning v1.0: Towards Harnessed Agentic RL
Zhiyuan He, Siwei Zhang, Zhiwen Zhou, Yuqing Yang, Yu Kang, Yuge Zhang, Luna K. Qiu, Tin Yan Tsui, Jiahang Xu, Chong Luo
cs.AI · cs.SE
Modern agents operate inside agent harnesses that manage tools, context, and control flow, making the harness a critical part of the agent system. Our original Agent Lightning introduced a disaggregated architecture that connects arbitrary agents to RL training through an LLM endpoint proxy, an approach later adopted by frameworks such as verl Uni-Agent, AReaL 2.0, slime, and Polar. We refer to this paradigm as harnessed agentic RL, where the...
-
31
SGHA: Evidence-Grounded Research Problem Discovery with Local Language Models
Sarvesh Gharat, Junpei Komiyama
cs.AI · cs.LG
Recent efforts toward fully automated AI scientists have demonstrated that language-model agents can generate hypotheses, execute experiments, and draft scientific manuscripts. However, during the early stages of research, when research problems are formulated, these AI scientists often rely heavily on proprietary frontier models. Their proposals are shaped by opaque parametric knowledge and by literature searches conditioned on the proposals...
-
32
Towards Better Agents for Multi-Turn User Interaction: The Next User Turn Is More Than Context
Yiwen Zhao, Zhihao Wen, Yuchen Mao, Mingxuan Jiang, Yihao Hu, Pan Wang, Xin Zhang, Wei Wu
cs.AI
User-facing tool agents must coordinate dialogue and tool use as user goals unfold over multiple turns. Yet interactive reinforcement learning typically reduces each rollout to a terminal reward, assigning the same credit to effective elicitation, errors, and later repair. The next user turn is more than context: it also provides noisy, temporally local evidence about the preceding user-to-user segment. We introduce...
-
33
When AI Designs AI: Innovation or Imitation?
Yikang Yang, Zhengxin Yang, Luzhou Peng, Minghao Luo, Yanqi Kan, Wanling Gao, Jianfeng Zhan
cs.AI · cs.LG
Recent advances in LLM agents have made them increasingly capable of designing methods for complex AI tasks. This raises two central questions about agent-designed methods relative to human-designed methods: how well they perform, and how different their algorithmic designs are. To study these questions, this paper introduces an analysis that derives task-specific algorithmic design spaces from human-designed methods, maps both human- and...
-
34
SAGE: Self-Evolving Storyboard Skills via Attribution-Guided Rule Evolution
Maolin Ran, Xiaoyang Lu, Jiaqi Liu, Jian Wang, Weiwen Liu, Jianghao Lin, Yong Yu, Weinan Zhang
cs.AI
Storyboards turn screenplays into visual shot plans for automated short drama production. Professional storyboarding relies on tacit directorial expertise and remains an industrial bottleneck. Large language models can automate this step, but methods for supplying directing knowledge face three challenges: (1) Knowledge acquisition: the craft remains implicit in exemplars or must be written manually. (2) Knowledge refinement: authored...
-
35
Structure-Internalized Rule Language Model for Faithful Knowledge Graph Reasoning
Xingrui Zhuo, Jiapu Wang, Manzong Huang, Gongqing Wu, Xindong Wu
cs.AI
Knowledge Graph Reasoning (KGR) aims to discover latent facts by leveraging the structural evidence available in KGs, posing a challenge to the structural semantic understanding capability of KGR models. Recent studies have demonstrated that Large Language Models (LLMs) can achieve remarkable progress on KGR tasks via flexible in-context learning. However, the inherent representation inconsistency between KG structural context and LLM...
-
36
Depth Enables Local Entropy: Quadratic Depth Dependence in Deep Variation-Norm ReLU Regression
Tao Jiang, Minbo Gao, Shaowei Cai
cs.AI
We study Gaussian regression over the explicit vector-valued Parhi--Nowak deep-RBV^2 architecture with depth L, width w, layer-sum variation budget A, and output bound B. For this O(L w^2)-parameterized architecture, the known lower and upper bounds differ by one factor of depth. We construct a local packing showing that the quadratic depth dependence is intrinsic under an explicit sample-size-dependent radius condition. The packing has...
-
37
Task-Aware Harness Provisioning for LLM Agents in Mission-Critical Infrastructure Operations
Liangtao Lin, Qingang Zhang, Zhaomeng Zhu, Tianwei Zhang, Yonggang Wen
cs.AI · cs.MA
LLM agents have been widely adopted to operate mission-critical infrastructure (MCI). These agents normally rely on a harness that determines what information they can access, which tools they can use, and what actions they can take. Existing systems often expose the same comprehensive harness to every task, which may not be necessary and cause resource wastes. In this paper, we focus on the identification of optimal harness configurations,...
-
38
LEGO-RL: Harness-Native Reinforcement Learning for Coding Agents
Yiming Du, Yuxin Jiang, Tao Yuan, Jianbo Dai, Shaowei Wang, Jierun Chen, Chaofan Tao, Xianzhi Yu, Lifeng Shang,...
cs.AI
Reinforcement learning for coding agents increasingly relies on long-running agent harnesses to manage tool integration, repository contexts, and execution feedback. However, the native execution environments of these harnesses are inherently misaligned with policy-gradient training: environmental crashes and reward hacking corrupt outcome signals, while train-inference discrepancies decouple rollout behavior from policy updates. To address...
-
39
Cognitive Graph Intelligence for Adaptive and Robust DDoS Attack Detection in Next Generation Networks
Mohammad Arif Hossain, Yeahia Sarker, Md Jafrin Hossain, Most. Humayra Khanom Rime, Nirwan Ansari
cs.AI
Distributed Denial-of-Service (DDoS) attacks threaten network availability, requiring a cognitive detection process that senses traffic, infers intent, and supports an adaptive response under severe class imbalance and non-stationary conditions. This paper proposes a Graph-based Generative Adversarial Network (GraphGAN) that serves as the cognitive detection engine for this task. GraphGAN captures the relational structure among traffic flows...
-
40
LLM-Only PDDL Domain Repair with Open-Weight Models
Nader Karimi Bavandpour, Pascal Bercher
cs.AI
AI planning is concerned with finding a sequence of actions that achieves a specified goal. It relies on explicit models of the world, commonly represented in the Planning Domain Definition Language (PDDL). An active line of research investigates how errors in such models can be detected and repaired. For example, users may provide positive test plans that are solutions, and negative test plans that fail during execution. Automated repair...
-
41
TileMix: Tile-Centric Mixed-Precision Attention for LLM Inference Acceleration
Hanzhi Zhang, Qiao Zhang, Qinglei Cao, Heng Fan, Yan Huang, Kewei Sha, Yunhe Feng
cs.AI
Long-context prefill in large language models (LLMs) incurs substantial computation and memory traffic because dense self-attention computes quadratic query-key scores. Existing methods either use a uniform low-precision path or select token interactions, leaving spatial precision routing over hardware-aligned score tiles outside fused dense attention. We introduce TileMix, a tile-centric precision-routing kernel that makes numerical...
-
42
LLMs for Medical Consultation Are Evaluated Too Late: The Preformulation Gap
Yining Hua, Cyrus Ayubcha, Hongbin Na, Levi Lian, Alon Gorenshtein, Yiftach Barash, Eyal Klang
cs.AI · cs.CL · cs.CY
Large language models for medical consultation are often evaluated after a clinical problem has already been made clear, although real consultations may begin with a vague, minimized, or misframed concern. We evaluated three API models across four physician-authored, multi-turn vignettes under baseline and entry-to-care instruction conditions, yielding 24 fixed-script transcripts; two cases also used adaptive standardized-patient simulation,...
-
43
Wuying-Browser-Agent: Real-World Centric Fundamental Long-Horizon Browser Agents
AIMAE Team, Tianxiang Chen, Yan Cheng, Zhangye Han, Xiaowei Li, Chang Liu, Cheng Liu, Zhongqiang Ma, Long Peng,...
cs.AI
Browser agents perform well on short, clean demonstrations, but real deployment is fundamentally different: agents must sustain dozens of decisions on live websites while recovering from mistakes and navigating complex UIs. We argue that closing this gap requires alignment at every level of the pipeline, including execution, supervision, optimization, and evaluation, rather than scale alone. We present Wuying-Browser-Agent, a unified...
-
44
SignalReasoner: Assessing the Upper Bound of 3B Models for Signal Mathematical Reasoning
Guozheng Sun
cs.AI
Post-training with supervised chain-of-thought fine-tuning and reinforcement learning from verifiable rewards has substantially improved the mathematical reasoning capabilities of large language models (LLMs). However, their application to signal processing problems remains relatively under-explored. This report investigates reinforcement fine-tuning strategies for adapting Qwen2.5-3B-Base to graduate-level signal mathematical problems from...
-
45
LiveHouse-TS: An Open-world Living Benchmark for Time Series Foundation Models
Haomin Wen, Ziyu Zhou, Qingxiang Liu, Siru Zhong, Yuxuan Liang
cs.AI
Time Series Foundation Models (TSFMs) have recently emerged as a highly promising paradigm for cross-domain zero-shot forecasting. However, existing evaluation protocols predominantly rely on static benchmarks with fixed historical test windows. While these benchmarks provide a valuable baseline snapshot, they evaluate an average performance on a fixed history, failing to capture how models behave in continuously evolving real-world...
-
46
PlanPO: Group Planning-Aware Policy Optimization for Multi-Turn Agentic LLMs
Dayang Liang, Liyuan He, Xuan Feng, Shuxin Li, Bo An, Yunlong Liu
cs.AI
Group-relative policy optimization has emerged as a key paradigm for training agentic large language models (LLMs) on multi-turn interactive tasks. However, most existing variants fail to distinguish advantages among successful trajectories even when these trajectories differ substantially in their interaction efficiency. For instance, circuitous successes are often assigned the identical outcome reward, causing advantage collapse and severe...
-
47
DeAR: Decentralized Agentic Reasoning via Capability Grounding and Collaborative Thought Navigation
Xing Wei, Changmeng Zheng, XiaoYong Wei, Xiufen Ye, Qing Li
cs.AI
Existing agentic reasoning systems typically rely on centralized protocols. This design introduces routing bottlenecks and static role allocations that often fail when handling complex multimodal queries. We propose DeAR (Decentralized Agentic Reasoning), a framework that shifts from central control to autonomous peer-to-peer collaboration. DeAR is built on three mechanisms: (1) decentralized capability grounding for query-dependent agent...
-
48
ASI-Bench: At the Dawn of Artificial Superintelligence
Junwei Zhou, Zhen Sun, Binyu Li, Jiangyu Zhou, Yuexi Pan, Hengyu Wang, Honghe Ren, Xiaohan Jia, Xueyang Zhou, Xiaoyu...
cs.AI
Artificial superintelligence (ASI) requires AI to move beyond mastering existing knowledge toward exploring the unknown, creating new knowledge, and turning new ideas into verifiable results. However, the capabilities of today's AI systems are still largely built on learning, compressing, and applying existing human knowledge. Accordingly, existing benchmarks primarily test whether AI can produce correct answers based on learned knowledge, or...
-
49
Do LLMs Know a Good Hypothesis When They See One? Logit-Based Energy Scoring Outperforms Prompted LLM-as-Judge for Scientific Hypothesis Ranking
Swati Rajwal, Sanjay Das, Tirthankar Ghosal
cs.AI
Large language models (LLMs) are increasingly used for scientific hypothesis generation. However, evaluating generated hypotheses remains a challenge for trustworthy AI-enabled scientific workflows. Existing approaches often use LLMs as judges or rely on semantic similarity, which can favor familiar ideas over novel ones. We propose a logit-based energy scoring method that evaluates hypotheses using a language model's intrinsic confidence...
-
50
Explicit State Elicitation Is Not Enough: A Controlled Audit of Memory-Policy Classification
Yihang Chen, Pin Qian, Su Wang, Chong Peng, Huan Xu, Shuaiting Li, Yiqi Sun
cs.AI
Personalized agents must decide whether retrieved user memory should be used, ignored, updated, or queried before it affects a current task. We use this setting to develop an empirical audit protocol for structured intermediate outputs: first audit dataset shortcuts, then isolate bundled prompt changes, check whether intermediate labels are answer-associated, test decomposed semantic evidence, and audit provider-level execution failures. A...
-
51
Fool's Gold: Defensive Deception Against Safety-Removal Attacks on Open-Weight Models
Mark Russinovich
cs.AI · cs.CR
Safety alignment in open-weight language models is trivially removable: abliteration projects a refusal-mediating direction out of the weights in minutes, and no release-time defense we are aware of prevents it durably. What cannot be prevented can be deceived. Our defense, decoy hardening ("Fool's Gold"), concedes the refusal strip and poisons its payoff: once refusal is stripped, most answers to hazardous operational requests are confident,...
-
52
Benchmarking the Benchmarks: Evaluating Automated Safety Benchmarks for Small Language Models
Nyamtulla Shaik, Fengjun Li, Bo Luo
cs.AI · cs.CR
Small Language Models (SLMs) are increasingly deployed in resource-constrained, privacy-sensitive settings, where safety and bias failures can cause security and societal risks. However, existing AI safety\slash security\slash compliance benchmarks are designed for large language models that may not transfer reliably to SLMs. We therefore ask: Can these benchmarks effectively and reliably evaluate SLMs? To answer this question, we conduct a...
-
53
Synthesizing Feature Extractors: An Agentic Approach for Algorithm Selection
Hai Xia, Carlos Ansótegui, Stefan Szeider
cs.AI
Algorithm selection for constraint satisfaction problems requires extracting features that capture problem structure. Manually designing feature extractors demands deep domain expertise and quickly becomes a bottleneck when new problem classes appear. We present an automated approach that uses Large Language Models (LLMs) in an agentic check--fix--verify loop to synthesize executable Python scripts that act as interpretable, problem-specific...
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.