cs.AI · 2026-09-09 · No. 110
Artificial Intelligence, 2026-09-09.
52 new papers in cs.AI. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
52 entries-
01
Procedural Graphs: Self-Evolving Execution Structures for LLM Agents
Yuxing Lu, Yicheng Chen, Shanchan Wu, Sercan Ö. Arık
cs.AI · cs.CL · cs.MA
Large language models are increasingly deployed as agents that plan over long horizons and act through external tools. Most agents select actions through unconstrained generation over an accumulating history, leaving implicit the procedural knowledge of what to do, in what order, and under which conditions. As trajectories lengthen, agents can lose track of their objectives, invoke tools out of order, and repeat unproductive actions. We...
-
02
A Data-Driven Framework for Identifying and Prioritizing RPA Opportunities in Healthcare Processes
Maria Alejandra Gomez, Juan Manuel Castillo
cs.AI · cs.CL
Robotic Process Automation (RPA) is widely used to reduce administrative burden in United States hospitals, yet an estimated 30-50% of RPA initiatives underperform because processes are selected informally, without a repeatable method to catalogue candidates, prioritize them, match each to an automation tier -- a Python bot, an open-source orchestrator such as n8n, or an enterprise platform such as UiPath -- and forecast financial return...
-
03
Co-Evolving Harnesses and Models: On-Policy Correction Helps Weaker Models Catch Up Where Imitation Fails
Zhou Yu, Bin Bi, Shiva Kumar Pentyala, Shubham Mehrotra, Sougata Chaudhuri, Shilpa Bhagavath, Zeyuan Chen, Ran Xu,...
cs.AI
Agent harnesses (the system prompt, tool set, execution hooks, and context-management scaffolding around a model) are a critical determinant of agentic task success. Automated harness evolution can enable smaller models to perform well on domain-specific tasks at a fraction of frontier-model cost. Since both the harness and model weights shape behavior, we ask how harness evolution and lightweight fine-tuning should be combined. Across seven...
-
04
ExecCritic: Learn to Test, Test to Improve for Coding Agents
Leitian Tao, Baolin Peng, Haorui Wang, Hang Wang, Hao Cheng, Wenlin Yao, Qianhui Wu, Tao Ge, Sharon Li, Jianfeng Gao
cs.AI · cs.CL · cs.SE
Execution feedback can guide coding agents toward correct repository repairs, but only when the tests capture the behavior requested by the issue. Agent-generated tests can encode incomplete or incorrect behavioral targets; when the same trajectory writes both the patch and the test, their errors can agree and create false confidence. We introduce ExecCritic, combining a test--verify--revise scaffold with a role-specific reinforcement...
-
05
A Generalization of Amari's Bayesian Duality
Mohammad Emtiyaz Khan, Thomas Möllenhoff
cs.AI · cs.LG · stat.ML
Amari's contributions to information geometry and machine learning are well known. Here, we revisit Amari's work on Bayesian duality which has not received as much attention. We connect Amari's Bayesian duality to a convex duality of Bayes' rule. Using this connection, we present a generalization of Amari's Bayesian duality and discuss its relevance for modern artificial intelligence.
-
06
MeClear: Cooperative Game-Theoretic Attribution and Risk-Aware Memory Clearance for Long-Horizon LLM Agents
Boyu Yang, Jiazheng Sun, Zilong Lu, Zhi Qiu, Xin Peng, Jun Zheng
cs.AI · cs.SE
Long horizon Large Language Model (LLM) agents rely on external memory systems to preserve user preferences and task knowledge across extended interactions. Conventional retrieval mechanisms optimize semantic compatibility rather than downstream utility, frequently introducing outdated, misleading, or conflicting evidence into the active context. We present MeClear, a task conditioned memory clearance framework that identifies memories...
-
07
SAEScientist-Bench: Can AI Agents Conduct Autonomous SAE Interpretability Research?
Yuqiao Tan, Shizhu He, Jun Zhao, Kang Liu
cs.AI · cs.CL · cs.LG
While research on recursive self-improvement (RSI) has predominantly automated model training pipelines, reliable autonomous development demands a missing pillar: post-hoc monitoring and auditing to understand what models learn and ensure safe alignment. Mechanistic interpretability tools are essential to bridge this gap, among which Sparse Autoencoders (SAEs) serve as a cornerstone by isolating interpretable features for model inspection and...
-
08
The Surprising Effectiveness of Approximate Value Iteration in Self-Play
Raphael Boige, Amine Boumaza, Bruno Scherrer
cs.AI
Combining search with function approximation has driven major advances in game-playing programs, making self-play algorithms more competitive than ever. Still, the computational overhead of the most popular methods, based on Monte Carlo Tree Search (MCTS), can be substantial. In this work, we investigate whether simpler methods remain competitive in non-trivial, moderately sized games such as Connect Four, Hex(7x7) and synthetic games. We...
-
09
Everything in Moderation: Per-Domain Coverage Optima and Alignment-Resistant Domain Gaps in Multi-Domain Mid-Training
Yunpeng Xu, Kun Zheng
cs.AI
Mid-training, the stage between pre-training and alignment, is where a model's per-domain data composition is typically set by data availability rather than principled design. We ask what that decision buys, and whether a later alignment pass can undo it. In a controlled logical-reasoning setting (Qwen3-8B-Base, with a 4B replication; five semantically rule-disjoint KOR-Bench domains) we train 30 allocations spanning the five-domain simplex,...
-
10
Time-Varying Data as Sheaves: an Invitation to Narratives
Wilmer Leal, Benjamin Merlin Bumpus, Jana K. Nickel, Johan García, James Fairbanks, Warren Dixon
cs.AI · cs.MA · eess.SY · math.CT
Modern science and engineering increasingly rely on time-varying data, yet the mathematical tools used to model temporal phenomena are often developed within separate disciplines, obscuring common principles and limiting the transfer of ideas across fields. This chapter presents the theory of narratives, an abstract framework for time-varying objects of any mathematical kind that supports both theoretical investigations and applications. To...
-
11
Answer-Distribution Trajectories: A Stochastic-Dynamics View of LLM Reasoning
Mar Gonzàlez I Català, Haitz Sáez de Ocáriz Borde, Davide Murari, Carola-Bibiane Schönlieb, Pietro Liò, George Montañez
cs.AI · cs.CL · cs.IT · cs.LG
Chain-of-thought reasoning provides a structured computation between a model's input and final answer. Yet it is often evaluated through endpoint accuracy, which ignores the path taken to reach that answer. An emerging line of work addresses this limitation using entropy profiles, which track how uncertainty evolves over the reasoning process but do not reveal which competing hypotheses account for that uncertainty. We introduce...
-
12
Deposon: An Auditable, Conservation-Guaranteed, Game-Theoretically Tested Scattering Layer over LLM Reasoning Paths
Qihao Yuan
cs.AI · cs.LG
Multi-step LLM reasoning lacks a machine-recheckable ledger: discarded reasoning paths leave no auditable record. We propose the Deposon scattering layer, which binds each node of an LLM-generated concept-decomposition graph to a two-parameter Deposon state; paths undergo three-channel scattering -- transmission, reflection, irreversible dissipation -- obeying T+R+A=1 for arbitrary parameters, with a maximum per-path energy-audit deviation of...
-
13
Good Pretraining, Bad SFT: Checkpoint Quality Across the Training Stack
Sohir Maskey, Philipp Scholl, Jonas Knupp, Pit Neitemeier, Sascha Wirges
cs.AI · cs.CL
Language-model checkpoints are commonly selected by pretraining loss or benchmark scores, assuming that the highest-scoring checkpoint will remain the best starting point for subsequent training. We show that this assumption can fail in a full 30B mixture-of-experts training pipeline. The checkpoints that perform better after the full downstream training stack also have higher solution density, i.e., retain downstream performance under local...
-
14
PlannerForge: LLM Agents for Scenario-Based Testing of Motion Planners in Autonomous Driving
Yuan Gao, Sebastian Müller, Mattia Piccinini, Marc Kaufeld, Yuchen Zhang, Finn Rasmus Schäfer, Qunying Song, Johannes Betz
cs.AI · cs.CL · cs.RO
Ensuring the safety of autonomous driving is a critical challenge. Scenario-based testing is a systematic process used to validate Autonomous Driving Systems (ADSs), but it remains a fragmented modular pipeline in which scenario generation, retrieval, modification, ADS execution, and results analysis are performed by separate tools with little interaction. Large Language Model (LLM) agents have shown promise across ADS sub-systems such as...
-
15
SkillAdam: Stable and Efficient Skill Evolution for Agents
Gaoyuan Li, Meihao Fan, Yizhe Liu, Shaolei Zhang, Ju Fan, Siyi Wang, Jiaheng Hou, Xudong Weng, Honghan Tian, Zang Li
cs.AI
Agent skills provide a lightweight way to equip frozen language-model agents with domain knowledge and procedural guidance, yet obtaining high-quality skills remains costly and difficult to scale. Expert-written skills require substantial human effort. Recent skill self-evolution methods automate an iterative loop that uses execution feedback to revise skills, but their heuristic update strategies often yield unstable optimization and low...
-
16
API Benchmark Scores Do Not Reliably Transfer to Chatbot Interfaces
Jennifer Wang, Joachim Baumann, Daniel E. Ho, Sanmi Koyejo
cs.AI · cs.SE
Benchmark scores are a central currency in model releases: they inform purchasing decisions, shape public trust, and influence policy. Yet, a key assumption underlying benchmark scores is that the model performance measured through APIs faithfully reflects the behavior of deployed systems. We challenge this assumption by auditing ChatGPT, Claude, and Gemini across seven systems and nine benchmarks spanning general capability, social bias, and...
-
17
Closing the Consistency Gap: Self-Evolving Agents That Learn to Stay on Course
Evelyn Duesterwald, Benjamin Elder, Lilian Ngweta, Shashanka Ubaru, Malgorzata Zimon
cs.AI
Large language model (LLM)-powered agents can be accurate on average yet unreliable in production, a discrepancy that has been observed but remains largely unaddressed. When given the same task five times, a ReAct agent on the AppWorld benchmark using GPT-4.1 succeeds in all five runs only 53% of the time, even though its per-run pass rate averages 77%. We call this 24-point shortfall the consistency gap, and we argue that addressing it is a...
-
18
It's All in the Way You Say It: The Role of Information Representation in LLM-Based Glycemic-Event Prediction
Andrea Apicella, Pasquale Arpaia, Matteo Orefice, Andrea Pollastro, Roberto Prevete
cs.AI
Large Language Models (LLMs) are increasingly being investigated for physiological time-series prediction, yet their effectiveness may depend not only on the model itself, but also on how physiological information is represented and presented at inference time. This study investigates prompt-based general-purpose LLMs for postprandial hyperglycemia and hypoglycemia prediction in individuals with type 1 diabetes. Using the OhioT1DM dataset, we...
-
19
When Can One Obtain Certificates of Optimality Using Positivstellensaetze?
Nayoon Kim, Allen Gehret, Shenyuan Ma, Jakub Marecek
cs.AI
We study certificates of positivity and optimality for learning problems whose objectives and constraints need not be polynomial. We isolate an axiomatic core of Fischer's constructive strict and weak Positivstellensätze and prove the resulting theorems for abstract function algebras over ordered fields. The framework separates two roles that can otherwise be conflated: objective and constraint functions may be built from broad classes of...
-
20
Application of curiosity driven exploration methods for hardware interference identification
Ludovic Matar, Clement Moulin-Frier, Pierre-Yves Oudeyer
cs.AI
The transition from single-core to multi-core architectures in safety-critical embedded systems introduces significant challenges due to inter-core interference caused by contention for shared hardware resources. Such interference affects execution times and complicates the verification of strict temporal requirements, particularly in domains such as avionics where standards require comprehensive identification of interference sources....
-
21
GoAnt: Quality-Diversity Multi-Agent Search for Alpha Factor Discovery in Market Microstructure Data
Stella Zhao, Tommy Sha
cs.AI
Automated alpha factor discovery searches symbolic trading signals from price-volume panels and order-book data under a fixed evaluation budget. Existing single- and multi-agent program-search systems can overfit predictive proxies that fail after execution costs and repeatedly explore redundant factor families, limiting execution robustness and behavioral diversity. We introduce GoAnt, a quality-diversity multi-agent search framework that...
-
22
CLAMP: Constrained Decoding for Vision-Language Embodied Planning
Tianyi Ma, Parisa Kordjamshidi
cs.AI
Embodied planning increasingly relies on vision-language models (VLMs) to translate instructions and visual observations into executable action sequences. However, fluent plans are not always executable. A VLM may refer to objects that are not visually observed, select actions whose required affordances are unavailable, or violate syntax and action constraints. We introduce CLAMP, a multimodal constraint-grounding framework that turns scene...
-
23
Graph-Based Personalized Memory for LLM Agents: Representation, Evolution, Retrieval, and Evaluation
Dac Duy Anh Nguyen, Zhangchi Qiu, Shigeng Chen, Alan Wee-Chung Liew
cs.AI
Large Language Model (LLM) agents are evolving from single-session tools toward long-term personal assistants that must adapt to individual users across tasks, contexts, and interactions. This shift makes memory a core requirement for personalization, since user preferences, goals, constraints, relationships, and past experiences are accumulated gradually and often change over time. Graph-based personalized memory provides a structured way to...
-
24
A Three-Tier Persona Vector for Controllable User Simulation in Agentic Evaluation
Rahul Khedar, Eshita, Sneha Teja Sree Reddy Thondapu, Mayank Malhotra, Arup Kumar Das, Jitesh Chandra Mishra, Arun...
cs.AI · cs.CL
Evaluating tool-augmented LLM agents requires diverse, realistic user inputs yet most evaluation frameworks use flat role descriptions ("you are an angry customer") that produce near-identical conversations regardless of the underlying scenario. In this paper, we propose a three-tier persona vector with 23 operationalized dimensions: 6 categorical demographics (jurisdiction, age, channel, device, language proficiency, time availability), 12...
-
25
AgentGrad: Intervention-guided Prompt Optimization for Multi Agent Systems
Jaewon Chu, Jinwoo Seo, Jaewon Cho, Jeehye Na, Yunyang Xiong, Youngdae Kim, Hyunwoo J. Kim
cs.AI
Large language model (LLM)-based multi-agent systems (MAS) achieve strong performance by employing specialized multiple agents, yet their performance depends on the prompt design of each agent. For MAS prompt optimization, textual gradient methods that guide prompt updates using natural-language feedback have emerged as a leading paradigm. In this paper, we identify limitations in two stages of existing textual gradient approaches: gradient...
-
26
BIO-MEMART: Biometric-Aware KV Cache Memory for Multi-User LLM Agents
Yanhong Qian, Xuanying He, Qingguo Meng, Shihao Ding, Xingbo Dong, Zhe Jin
cs.AI
KV cache is evolving from a serving optimization into an external memory substrate for long-term LLM agents. In a shared multi-user deployment, however, reusable KV blocks introduce a missing access-control question: semantic relevance alone cannot determine whether a memory block is authorized for the current physical user. We propose Bio-MemArt, a biometric-aware KV-cache memory framework for multi-user LLM agents. Bio-MemArt attaches a...
-
27
Personalizing LLM Agent Memory Using Biometrics
Yanhong Qian, Qingguo Meng, Shihao Ding, Xingbo Dong, Zhe Jin, Hanrui Wang, Isao Echizen
cs.AI
Personalized memory helps LLM agents deliver stable, tailored assistance by storing and reusing user-specific data across interactions. In multi-user scenarios, however, retrieval must consider not only semantic similarity but also whether the current requester matches the identity associated with the stored memory. We propose Bio-Memory, a biometric-aware memory architecture that conditions memory retrieval on both semantic similarity and...
-
28
SRPO: Setwise Relative Policy Optimization for Multi-Agent LLMs
Shengtian Yang, Ziyu Xiong, Yu Li, Yewen Li, Qingpeng Cai, Lei Feng
cs.AI
Multi-agent large language models solve complex tasks by coordinating several policies in a shared environment. However, existing reinforcement learning methods usually optimize each response or trajectory separately, even when several outputs jointly cause one state transition. Consequently, the update unit differs from the action executed by the system. To address this problem, we propose SRPO (Setwise Relative Policy Optimization), which...
-
29
EvolveScaler: Synthesizing Information-Evolution Contexts via Executable State Machines and Natural-Language Rendering
Ziliang Zhao, Zenan Xu, Shuting Wang, Zhao Wang, Bowen Cao, Minda Hu, Lincheng Li, Pluto Zhou, Zhicheng Dou
cs.AI · cs.SE
In persistent interactions, long contexts may encode an evolving process rather than a fixed record: later events can revise or revoke earlier information, changing what remains valid and what conclusions follow. We call this setting information evolution (IE). Solving IE requires identifying valid records, applying updates in order, and reconstructing the query-relevant state from the event history. Existing text-first synthesis pipelines...
-
30
Feyospace-v1: How the Cyber Mercury Seven Trained Frontier Cyber Models
Zongjie Li, Alan Z. W, John Nicolas J, Walter H. F, Scott Donald L, Gordon Y. P, Deke X
cs.AI
Training capable cyber agents is often treated primarily as a problem of model scale, yet open-weight post-training is constrained more directly by the cost of executable environments, reliable multi-turn supervision, and access to strong teachers. We present a data-centric framework that addresses these bottlenecks through five complementary systems: Choulea analyzes hidden reasoning signatures, SkyReal reduces teacher-sampling cost,...
-
31
FastE: Readout-Triggered Token Compression for LLM Embedding Inference
Jinsong Shu, Jinyong Wen, Baokun Wang, Zhongle Xie, Lidan Shou, Weiqiang Wang, Gang Chen
cs.AI
In this study, we identify depth-dependent prefix redundancy in final-readout LLM embedding models, notably across representative backbones including Qwen3-Embedding and Qwen3-VL-Embedding. We find that removing prefix states is substantially more damaging in shallow layers than at greater depth, showing that prefix states become increasingly compressible as the prefix and readout states propagate through the network. To this end, we...
-
32
LEBGen: An LLM-Enhanced Bayesian Network Framework for Few-Shot Travel Survey Data Generation
Zijian Shen, Bin Zhou, Jiguang Wang, Ya Zhao, Jintao Ke
cs.AI
Travel survey data are essential for transportation planning and travel behavior analysis, yet collecting large-scale representative samples is costly and time-consuming. A practical alternative is to generate synthetic survey records from a few-shot sample. However, such samples provide incomplete coverage of heterogeneous traveler groups and insufficient evidence for recovering the complex dependencies between demographic characteristics...
-
33
Beyond Coherence: Benchmarking Professional Editing-Technique Execution in Multi-Shot Audio-Video Generation
Tianyi Zeng, Junchao Liao, Yujie Wei, Ziying Zhang, Litao Li, Tianyi Wang, Zhichao Wei, Shuyao Xu, Wenwen Qiang,...
cs.AI
Recent multi-shot audio-video generators can produce increasingly coherent and cinematic outputs, but coherence does not imply the ability to execute editing techniques. Professional editing depends on shot structure, transition grammar, audio-video cut relations, and montage, yet existing benchmarks largely rely on proxies such as content quality, synchronization, or physical plausibility, systematically missing whether such editing...
-
34
MemForest: Efficient Agent Memory Management via EventTree Partitioning and Progressive Merging
Junxi Wang, Te Sun, Jiayi Zhu, Chen Zhang, Siyuan Li, Xuyang Liu, Zichen Wen, Xiaobing Tu, Jinkui Ren, Xiantao...
cs.AI
Agent memory systems have demonstrated significant potential in long-term dialogue, personalized assistants, and video understanding. However, continuously accumulated memory introduces substantial storage and retrieval costs during inference. To address this issue, we propose \textbf{MemForest}, a general memory compression framework adaptable to various agent memory systems. Specifically, MemForest partitions historical memory into...
-
35
Three Types of Negation of Triple and its Elements and an Extension of Triple
Zhenghua Pan
cs.AI
In various data models, the classical triple is a typical semantic data model. However, due to the design of the triple as a simple structure for representing positive assertions, it cannot sufficiently express different forms of negation present in the triple and its elements. This paper conceptually proposes that there are three distinct forms of negation within triples and their elements: contradictory negation, opposite negation and...
-
36
Evidence-Aligned Entity Verification for Hallucination Detection in Retrieval-Augmented Generation
Runsong Jia, Zhen Fang, Mengjia Wu, Jie Lu, Yi Zhang
cs.AI · cs.IR
Hallucination detection is crucial for large language models (LLMs), as hallucinated content creates significant barriers in applications requiring factual accuracy. Current detection methods mainly depend on internal signals like uncertainty and self-consistency checks, using the model's pre-trained knowledge to identify unreliable outputs. However, pre-trained knowledge may become outdated and has coverage limitations, especially for...
-
37
Revoked but Still Authoritative: An Empirical Study of Revocation Enforcement in Agent-Memory Systems
Yi Ting Shen, Kentaroh Toyoda, Alex Leung
cs.AI · cs.CR
Long-running language-model agents depend on persistent memory. Many agent-memory systems preserve history through soft revocation: a contradicted fact is marked invalid and retained rather than deleted. However, whether that mark is enforced at retrieval time is unexamined. In this paper, we measure five such systems: we load each with a revoked policy and its replacement, track whether the revoked fact is returned at retrieval and whether...
-
38
CircuTutor: Transforming Static Circuit Problems into Intelligent and Dynamic Tutoring
Ziyu Luo, Xiaorui Ma, Lin Chen, Xiaoming Chen
cs.AI
Learning direct current circuit concepts requires learners to connect invisible physical quantities, such as current, voltage, resistance, and power, with observable outcomes such as bulb brightness. Conventional textbook materials and general-purpose circuit simulators provide opportunities for problem solving and exploration but offer limited support for explaining why circuit behavior changes or diagnosing the reasoning behind incorrect...
-
39
Agentic ML Exploration (A-MLE) for Ads Ranking
Erwin Gao, Vinodh Kumar Sunkara, Jingyi Guan, Qinjin Jia, Hangjun Xu, Xiang Ji, Sherman Wong, Surya Teja Chavali,...
cs.AI
Modern industrial ads ranking stacks are increasingly bottlenecked not by model capacity or training compute, but by the throughput of human ML iteration - the cycles of research, implementation, training, debugging, evaluation, and launch required to surface a single statistically significant improvement. A typical ranking stack contains numerous differentiated models with heterogeneous data, architectures, and infrastructure constraints,...
-
40
zScore-N: A Neural Network for On-Chain Wallet Reputation Scoring
Girish G N, Ashutosh Sahoo, Akshay SP, Gurukiran S, Dhanashekar Kandaswamy
cs.AI
Wallet reputation scores decide who receives an airdrop, who can borrow, and who enters an allowlist across decentralised finance. They almost always begin as hand-written formulas: compositions of clamped logarithmic, linear and square-root transforms over behavioural features, with every threshold and point award set by hand. Such a formula is readable and deterministic, but it is piecewise and non-differentiable, it cannot improve as data...
-
41
Style Over Substance: Content-Invariant Wrappers Flip LLM Safety-Judge Verdicts
Yongxi Zhou, Wenbo Ye, Yuanzhe Liu, Zihan Dong, Junwei Yao
cs.AI
Automatic safety judges -- systems such as Llama Guard or a GPT-4o grading prompt that decide whether a model's reply is harmful -- produce the numbers behind almost every reported jailbreak success rate, defense evaluation, and safety leaderboard. We ask whether these judges grade what a reply contains or how it sounds. We keep a reply's content fixed and add content-invariant style wrappers: fixed strings placed before or after the reply...
-
42
SE-GoS: Self-Evolving Graph-of-Skills for Skill Library at Scale
Dawei Fu, Cheng Jiang, Sitian Qian, Huainan Wang, Zhongkai Hao
cs.AI · cs.CL
Modern LLM agents increasingly rely on reusable skills, yet as skill libraries scale to thousands of entries, effective retrieval becomes a bottleneck. Graph-of-Skills (GoS) addresses this challenge by exploiting dependency-aware graph structure for scalable skill retrieval, while SkillDAG further demonstrates that skill graphs can accumulate execution-backed structure online. However, these approaches leave open whether historical execution...
-
43
TTGBench: Benchmarking Topological Evolution and Semantic Drift in Text-attributed Temporal Graphs
Longfei Ma, Zemin Liu, Fei Wu
cs.AI
Temporal graph learning models the evolution of dynamic systems, where both structural interactions and semantic states change over time. However, existing benchmarks primarily emphasize structural evolution via temporal link prediction (TLP), while support for semantic evolution remains limited. Although temporal node classification (TNC) is sometimes included, it is typically restricted to simplistic binary settings that fail to capture...
-
44
Vision: Data-Centric Anchoring for Robust and Interpretable Agentic AI
Arun Vignesh Malarkkan, Xinyuan Wang, Yanjie Fu
cs.AI · cs.ET · cs.LG
Agentic AI systems built on large language models fail in two persistent ways that scaling does not fix: they break under distribution shift, and they cannot explain the decisions they make. We argue these are co-symptoms of one structural deficiency in the data lifecycle that governs how agents are trained, evaluated, and deployed. Observational interaction logs record what an agent did, not what it would have done otherwise. They encode...
-
45
A Better Spur Should Start From Each Objective
Shanwen Mao, Hao Zhang, Guangtao nie, Zhiheng Li, Huimu Wang, Sulong Xu, Gu Simiu
cs.AI · cs.LG
Real-world Multi-Objective Reinforcement Learning (MORL) often suffers from sparse rewards, reward conflicts, and late-stage reward tug-of-war, causing traditional linear scalarization to experience severe metric oscillations. To address optimization conflicts among multiple objectives in real-world deployment scenarios, we propose Multi-Marginal Preference Optimization (MMPO), a fine-grained framework that intervenes at the data, gradient,...
-
46
Qiushi Engine on AstaBench E2E-Bench-Hard
Wenhao Li, Shuxing Yang, Fujia Chen, Jincheng Mi, Yuang Pan, Rui Zhao, Zichen Li, Junyao Wu, Shenzhan Hong, Yaqi Li,...
cs.AI · cs.SE
This report analyzes Qiushi Engine v0.8 across all 40 test tasks in AstaBench E2E-Bench-Hard, a benchmark that requires autonomous agents to carry a research question through experimental design, code implementation, actual execution, result analysis, and report delivery. Qiushi Engine is model-configurable; this evaluation selected DeepSeek deepseek-v4pro-preview as the model backend. The official AstaBench leaderboard records a score of...
-
47
Do Dynamic Routers Need Memory? HeRo: History-Aware Routing for Efficient LLM Inference
Hongjin Lin, Wentao Wan, Keze Wang
cs.AI · cs.CL
Dynamic layer routing reduces the inference cost of Large Language Models (LLMs) by learning to skip layers for individual tokens. Existing methods, however, treat each routing decision as a local operation conditioned solely on the current hidden state which is a formulation that overlooks the sequential, path-dependent nature of routing across depth: earlier decisions shape the representations seen by downstream routers, and the layer-usage...
-
48
Bridging the Semantic-Utility Gap in Multimodal RAG via Generator-in-the-Loop Alignment
Zhan-Lun Chang, Dong-Jun Han, Seyyedali Hosseinalipour, Mung Chiang, Christopher G. Brinton
cs.AI · cs.IR
Vision-language models (VLMs) augmented with retrieval-augmented generation (RAG) benefit from access to external evidence. However, standard retrievers and rerankers optimize for semantic similarity rather than answer utility, creating a preference gap: documents that appear relevant may not help the generator produce a correct answer. Motivated by this, we propose a two-stage generator-in-the-loop alignment framework that closes this gap...
-
49
Does Deeper Reasoning Compromise Alignment? Revealing and Mitigating of Alignment Collapse in Large Reasoning Models
Yu-Hang Wu, Yu-Jie Xiong, Henghua Zhang, Bairui Zhang, Jia-Chen Zhang, Shaohua Li
cs.AI · cs.CL
The emergence of Chain-of-Thought (CoT) has established a robust foundation for Large Reasoning Models (LRMs). While deep reasoning is widely believed to enhance safety alignment, the stability of alignment mechanisms under extended reasoning remains underexplored. This paper challenges the prevailing view by revealing a critical vulnerability: Deep Reasoning May Induce Alignment Collapse. To rigorously quantify this phenomenon, we propose...
-
50
Less Is Personal: Learning Minimal Sufficient User Profiles for Personalized Language Models
Minghang Liu, Qiang Qiu, Yuanzhuo Wang, Huawei Shen, Xueqi Cheng
cs.AI
Retrieval-augmented personalization enables large language models to produce more accurate and preference-aligned outputs using relevant records retrieved from user histories. Personalized language models typically prepend a fixed number of retrieved user records, even when additional history is redundant, harmful, or unrelated to a user's distinctive behavior. We study minimal sufficient personalization: constructing the least costly ordered...
-
51
Safe Harness Self-Evolution: A Theoretical Analysis of Feasibility and Limits
Qianshu Cai, Yonggang Zhang, Jun Nie, Maohao Ran, Huajiang Zheng, Jun Song, Xinmei Tian, Yike Guo, Wei Xue
cs.AI
Harness self-evolution is the process by which an agent modifies its prompts, tools, code, or orchestration in response to task feedback while keeping the underlying language model frozen, with changes persisting across subsequent tasks. We provide a systematic theoretical analysis of the feasibility and limits of safe harness self-evolution, connecting modification generation, finite-data certification and selection, safe adoption, and...
-
52
OntologyBench: Can Dense Retrieval Satisfy Structured Biomedical Constraints?
Xiao Yu Cindy Zhang, Wyeth Wasserman, Jian Zhu
cs.AI
We introduce OntologyBench, a tiered biomedical retrieval benchmark comprising 471,854 training and 125,744 evaluation query-document relevance pairs across concept grounding, relational retrieval, and compositional phenotype-based retrieval. Although these tasks can be tractable using ontology-aware reference methods, across task tiers, embedding performance is generally lower on relational and compositional tasks than on concept-grounding...
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.