cs.AI · 2026-10-07 · No. 136
Artificial Intelligence, 2026-10-07.
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
Sherpa: Teaching LLMs to Teach Adaptively
Weixian Xu, Yanzhe Zhang, Zora Zhiruo Wang, Changyu Chen, Diyi Yang
cs.AI · cs.CL
Large language models (LLMs) have become increasingly capable problem solvers, but being able to solve a problem is not the same as being able to teach it. Existing approaches to training LLMs as teachers rely on demonstrations, preference data, or predefined pedagogical criteria that specify what good teaching looks like. However, these signals are often not grounded in individual student learning outcomes, where effective teaching...
-
02
Agent in a Bottle: Can LLM Agents Turn Their Capabilities Into Cheap, Scalable Artifacts?
Ankit Sonthalia, Haritz Puerto, Alexander Rubinstein, Martin Gubri, Seong Joon Oh
cs.AI
Large language models (LLMs) can solve many narrow tasks, but querying them separately for millions of related instances can be prohibitively expensive. Can LLM agents autonomously create cheaper solutions for such workloads? We call this ability "bottling": the ability to turn general capabilities into task-specific solutions that balance answer quality and amortised cost. We introduce BOTTLED, a benchmark in which agents receive an entire...
-
03
VeriFine: Scaling Verification for Self-Improvement in Embodied Reasoning
Zewei Zhou, Rachel Luo, Yulong Cao, Chaowei Xiao, Chensheng Peng, Boyi Li, Thomas Tian, Zheng Lian, Yan Wang, Jiaqi...
cs.AI · cs.RO
Self-improving policies continually expose new failure patterns, changing what their judges must be able to verify. However, current fixed judges constrain both optimization feedback and the discovery of useful training examples, limiting further self-improvement. This challenge is even more acute in embodied reasoning, where reliable evaluation must account for spatial grounding, causal reasoning, and safety-aware decision-making. We...
-
04
Does an Agent's History Tell You When Compaction Will Hurt? A Modest, Bounded Effect on the TRACE Paired-Replay Corpus
Egor Pakhomov, Erik Nijkamp
cs.AI · cs.LG
Many long-horizon agents compact their context on a global rule, usually a token budget, blind to what the agent was doing. We ask whether the agent's recent behaviour predicts when a compaction will hurt. TRACE's public corpus of 590 harness-triggered AppWorld compaction boundaries replays each boundary from a re-executed prefix state under the pre-compaction context and under the summary, and records the burden of the next actions: calls...
-
05
WorldSolver: Can LLM Agents Simulate the Physical Dynamics via Solver Generation?
Siru Jiang, Yongzhe Lyu, Shuo Lu, Yubin Wang, Yuxiang Zhang, Yue Liao, Bin Wang, Jian Liang, Tieniu Tan
cs.AI
LLM-based agents are increasingly advancing scientific and engineering problem solving, with physics simulation emerging as a challenging yet practical testbed for reproducing complex physical phenomena with application in embodied AI, games and films. As the workhorse of such simulation, a solver computes how the state of a dynamic system evolves over time. Building such solvers requires physical understanding to identify appropriate models,...
-
06
nanoMuse: An Open-Source Personal Agent for Every Device You Own
Guangyi Liu, Yong Liu, Jiangning Zhang
cs.AI
Assistants from 2011 answered and waited, and agents from 2023 did a task and stopped. In September 2026 Meta's Muse showed an agent for one person, with accounts, devices, memory and a conversation that lasts, closed, in a vendor's cloud, in one country. Such an agent is expected to act on a person's accounts and devices, remember them across weeks, speak first when it is worth it, and answer for what it did. It is a kind of software, not a...
-
07
ScienceClaw: Benchmarking Continual Self-Evolution of AI-for-Science Agents Across the Natural and Social Sciences
Mingda Zhang, Wenjin Liu, Tiesunlong Shen, Zikai Xiao, Zhenghong Lin, Qing Xu, Erik Cambria, Xiaoying Tang, Haoran Luo
cs.AI
Large language model agents are accelerating scientific automation, yet verified executions rarely become persistent program-level improvements, and existing evaluations do not examine this process across sequential tasks in both the natural and social sciences. We formalize ScienceClaw as fixed-parameter program self-evolution that unifies task solving, scientific verification, and program updates. ScienceClaw-Eval spans 23 disciplines and...
-
08
Coupled but Late: Turn-Taking Between Full-Duplex Speech Models in Unscripted Dialogue
Lichen Zhu, Yueqian Lin, Yiheng Wang, Hai "Helen" Li, Yiran Chen
cs.AI
Full-duplex speech models are trained to converse with a person, but they are increasingly made to converse with each other, in self-play data generation, agent societies, and model-based evaluation. In that loop no human absorbs a timing error: each model's turn-taking is the other's input. We ask what timing the loop settles into. Two PersonaPlex-7B instances exchange audio tokens on a shared clock in unscripted conversation, and one...
-
09
ParanoiaEval: Benchmarking Unnecessary Defensive Work in Agentic Coding
Hanjun Luo, Xiucheng Zhang, Zhuoning Xu, Zhimu Huang, Yingbin Jin, Xinfeng Li, Hanan Salam
cs.AI · cs.SE
As coding agents increasingly undertake real-world work autonomously, judging whether their risk treatments are warranted has become important. Existing work evaluates related agent behaviors from separate perspectives, but lacks a systematic framework for unifying these behaviors. To bridge this gap, we introduce ParanoiaEval, the first benchmark for unified evaluation of risk-treatment capabilities in coding agents. Grounded in the...
-
10
SquidAgent: Parallelize Wisely, Coordinate Efficiently
Yexiong Lin, Shanshan Ye, Yu Yao, Zhen Fang, Bo Han, Tongliang Liu
cs.AI · cs.CL · cs.LG
LLM-based agents solve complex multi-step tasks, but sequential execution incurs substantial latency. In principle, parallelizing work across multiple agents should yield near-linear speedups. Yet existing parallel multi-agent systems often run slower than a single-agent baseline. We attribute this gap to two hidden costs that parallel execution incurs but a serial agent avoids. First, there is a re-exploration cost: redundant effort spent by...
-
11
Parallel Predictive World Models for Accurate and Efficient Long-Horizon Planning
Wanjin Feng, Baobin Zhang, Ao Yu, Shibo Feng, Xi Wang, Xingyu Gao
cs.AI
Long-horizon world-model planning typically relies on autoregressive rollouts, where predicted states are repeatedly fed back into the model. This preserves temporal structure but creates a horizon-length sequential path and exposes later predictions to recursive decoded-state feedback. We introduce Parallel Predictive World Models (PPWM), which predict a finite-horizon trajectory in parallel while retaining causal interaction among future...
-
12
Recursive Game Creator: An Agentic Product-Level Experience-Oriented Game Harness
Jiajun Chen, Haoyu Wu, Mingda Jia, Xihui Liu
cs.AI · cs.MA · cs.SE
Recent game design agents have made substantial progress in generating playable games. However, program correctness does not ensure an enjoyable experience for players. We present Recursive Game Creator, an experience-oriented harness to advance agentic game development from rough game prototypes into entertaining games. Recursive Game Creator organizes recursive development around four components: Designer, Builder, Player, and Reviewer. The...
-
13
MINDSET: Energy-based Schema Evolution for Long Conversational Agent Memory
Sujato Dutta, Sreekruthy Tummala, Shashank Vanga, Ayushmi Pavani
cs.AI
Long conversational agents have become essential in our daily lives. They must remember what was said long back in order to help us efficiently complete a task without needing the user to repeat instructions and context repeatedly. However, the main issue is that instructions and context change over time and so the agents must be able to adapt accordingly. A useful memory system should preserve both current and historical states, distinguish...
-
14
Adaptive Power Sampling for LLM Reasoning
Bingnan Xiao, Chenhao Yang, Bingcong Li, Wei Ni, Xin Wang
cs.AI
Sequence-level power sampling has recently emerged as a training-free approach to reasoning by sampling from a sharpened output distribution of a base large language model (LLM). Nevertheless, existing methods typically sharpen the base model distribution uniformly across queries, overlooking variations in query difficulty and in how well the base model already handles each query. The goal of this work is to equip power sampling with query...
-
15
AnyBottle: A Recipe to Only Keep the Concepts You Really Need
Wolfgang Stammer, Sukrut Rao, Hevra Petekkaya, David Steinmann, Bernt Schiele
cs.AI · cs.LG
Concept bottleneck models (CBMs) make predictions inspectable and intervenable by routing them through human-interpretable concepts, but originally required concept annotations. Annotation-free variants remove this requirement, but typically use large concept vocabularies, static at both training and inference, producing bottlenecks larger than any task or prediction needs and harder to inspect. We propose AnyBottle, a single recipe for...
-
16
Toward Alignment Scaling Laws: A Framework and First Preregistered Measurements
Jeremy Canale
cs.AI · cs.CL · cs.LG
Whether alignment gets easier or harder as models grow is often argued from isolated findings, as if alignment were one property. We treat it as a family of measurable scaling relations: for each risk category r, the alignment burden needed to hold a fixed safety target is modeled as B_r(N)=a_rN^alpha_r, with N a capability proxy; against a budget proportional to N, scaling helps if alpha_r<1, keeps pace if alpha_r~1, and accumulates...
-
17
How Much Evidence Should a Coding Agent's Self-Correction Carry? Adaptive Dirichlet Evidence for Self-Distillation
Yunbo Long, Guangya Hao, Yuhan Liu, Yiting Duan, Longyan Tan, Yunchen Long, Hao Wu
cs.AI · cs.SE
Execution feedback lets coding agents revise programs and learn from their own corrections. A correction's learning weight should reflect both the transitions supported by its executions and the amount of evidence behind that support. We introduce Effective-Evidence Self-Distillation (EESD), which represents these quantities separately. Normalized execution relevance determines relative transition support and an effective pseudo-count mass; a...
-
18
Cylindrical Geodesic Flow Matching for Quasiperiodic Physiological Signal Transformation
Onur Selim Kilic, Afra Nawar, Cem Okan Yaldiz, Michael J. Cho, Ahmet Rasim Emirdagi, Demet Tangolar, Amirali...
cs.AI
Paired translation between quasiperiodic physiological waveforms (i.e., recovering a target oscillatory signal from the source) is central to the interpretation of cardiovascular signals derived from wearables placed at different body locations. This source-to-target mapping in these problems carries inherent geometric structure: the phase wraps around the cycle and must be treated as a circular variable, the amplitude remains strictly...
-
19
AssemState: Manual and Physical-State-Guided Reasoning for Zero-shot Furniture Assembly
Zhiyuan Qi, Jierui Li, Yifan Shen, Cheng Qian, Jiateng Liu
cs.AI
Multimodal large language models (MLLMs) have made significant progress in visual understanding, but precise 3D spatial reasoning integrated with physical environment remains difficult. Furniture assembly requires not only recovering step-level operations from diagrammatic manuals, but also translating semantic attachment relations into 6D pose updates that enable parts to physically interact with the environment and previously assembled...
-
20
EMHO: EMbodied Agent Harness Optimization via Experience Traces
Hyun Jung Lee, Jungtaek Kim, Jongwon Jeong, Tae-Eui Kam, Donghyun Kim, Yong Jae Lee
cs.AI
Improving embodied agents often focuses on optimizing the underlying model through training, while the surrounding agent harness that controls planning, context, and tool use is typically engineered. We ask whether this harness can instead improve itself directly from experience traces under sparse environmental feedback. We propose EMbodied Agent Harness Optimization (EMHO), a self-evolving framework that keeps the embodied model frozen and...
-
21
Transect: Retaining Observability for Long-Horizon LLM Agent Evaluations
Toby D. Pilditch, Konstantinos Voudouris, Alexandra Abbas, Cozmin Ududec
cs.AI
Frontier AI evaluations increasingly use open-ended, agentic, long-horizon tasks whose transcripts can span hundreds of pages of outputs and actions from complex multi-agent networks. The observability envelop-the range of what evaluators can reliably infer about an agent's behaviours-is therefore narrowing. Language model assistants can help classify and interpret agent behaviour but also afford human evaluators significant analytical...
-
22
Explainable Failure Prediction and Prevention in Maritime
Dionisis Kalogeropoulos, Georgia Sovatzidi, Panagiotis G. Kalozoumis, Dimitris K. Iakovidis
cs.AI
Maritime systems operate in highly dynamic environments where unexpected equipment failures can compromise safety, reliability, and operational efficiency. Recent advances in artificial intelligence (AI), machine learning, digital twins, and predictive maintenance enable proactive failure prediction and prevention. However, ensuring trustworthy and explainable decision-making remains a major challenge in safety-critical maritime applications....
-
23
MoF: Preference-Aware Mixture Modeling for Black-Box LLM Personalization
Hun Park
cs.AI
Proprietary Large Language Models (LLMs) have demonstrated remarkable capabilities across a wide range of tasks, yet aligning their outputs with diverse user preferences remains challenging. Existing personalization approaches for black-box LLMs often rely on user-specific scoring heads, causing the number of personalized parameters to grow linearly with the number of users and requiring additional adaptation for unseen users. To address...
-
24
An AI-Assisted Formalization of the Poincaré Conjecture
Zhiyuan Zhang, Axel Delaval, Leheng Chen, Jinxuan Chen, Jie Xu, Yuxuan Liao, Jiedong Jiang, Chunlei Liu, Bin Dong
cs.AI · math.GT
We present an AI-assisted Lean 4 formalization of the Poincaré conjecture. The project began with limited reusable formal infrastructure for the geometric analysis behind the proof. To organize this work, we combined a proof blueprint prepared by mathematicians with explicit milestone statements. These milestones enabled parallel agent work and gave mathematicians clear points to locate blockers and provide effective mathematical guidance....
-
25
MedZERO: Self-Evolving Agents for Open-Ended Medical Reasoning Through Controlled Knowledge Accumulation
Xilin Dang, Weilin Ruan, Xue Yang, Jinghao Wang, Xiaowei Hu, Jinpeng Li, Pheng-Ann Heng
cs.AI
Large language models (LLMs) have shown promise in medical question answering and clinical reasoning, yet their improvement remains constrained by static parametric knowledge and costly expert supervision. Self-evolving agents offer a promising alternative by enabling models to improve through iterative task generation and problem-solving. However, most existing self-evolving methods are designed for easily verifiable domains such as...
-
26
SCOPE: Certified Theorem Proving with a Language Model as the Policy Planner
Hanchao Zhou, Jialei Li
cs.AI
In proof assistants such as Lean, a generated proof must pass machine compilation checks, so evaluation needs no human scoring. Direct generation fails on multi-step numeric propositions: a proof is valid only if every content integer is correct, so the pass rate is bounded by the k-th power of the per-integer accuracy. Controlled corruption across 2,617 reference proofs confirms this power law. SCOPE (State-Conditioned Operator Planning and...
-
27
The Standardization Trap: Certifying Joint Label Processing in Tabular Foundation Models
Duong Nguyen, Nicolas Chesneau, Milan Bhan
cs.AI · cs.LG
Linear regression and kernel smoothing offer tractable explanations of in-context learning: in both, the features determine the weight assigned to each context label. However, whether this fixed-weight account describes pretrained tabular foundation models (TFMs) remains unclear. Testing this account using derivatives runs into a standardization trap: public TFM packages standardize the labels before the model sees them, yet ordinary...
-
28
CoDe-LoRA: Mitigating the Orthogonality Dilemma in Continual Learning of LLMs via Knowledge Consolidation and Decoupling
Maoqi Liu, Quan Fang, Yufei He
cs.AI · cs.CL · cs.LG
Continual learning (CL) is essential for Large Language Models (LLMs) to sequentially adapt to evolving tasks. To mitigate catastrophic forgetting, recent advances implement low-rank adaptation with orthogonal projections (e.g., O-LoRA) to isolate task parameters. However, we reveal that such strict geometric constraints trigger an "Orthogonality Dilemma": rigid parameter isolation impedes the transfer and accumulation of shared...
-
29
zkLLMPoT: Efficient Zero Knowledge Proof of Training for Large Language Models
Junkai Liang, Zhanpeng Guo, Pengfei Wu, Qingni Shen, Jiaheng Zhang, Zhonghai Wu, Haiyang Xue, Shengfang Zhai
cs.AI
Auditing the claimed outcomes of large language model (LLM) training is challenging when model weights and training data are private, while cryptographically proving the full training process is prohibitively expensive at Transformer scale. We present zkLLMPoT, a zero-knowledge framework that certifies auditor-defined properties of a trained checkpoint through forward evaluation rather than verification of its optimization trajectory....
-
30
MASC: A Multi-Agent Self-Calibration Framework with Latent Construct Alignment for Consistent Client Role-Playing in Psychological Counseling
Shixin Peng, Kun Jiang, Jiaxing Zheng, Qihao Yang, Jingying Chen
cs.AI
Large language models are increasingly used to simulate clients for counselor training and psychological counseling research, but reliable simulation requires clients to remain psychologically coherent across extended interactions. Existing role-playing methods largely rely on static profile prompts and may exhibit persona drift, unrealistic cooperativeness, or inconsistent psychological states, communicative actions, and emotions. Existing...
-
31
LeanPlan: Optimal Planning with LLM-Generated Heuristics and Admissibility Proofs
André G. Pereira, Augusto B. Corrêa, Felipe Meneguzzi, Jendrik Seipp
cs.AI · cs.LG · cs.SC
Frontier large language models (LLMs) can generate heuristic functions that guide search to achieve state-of-the-art performance in satisficing planning, where any plan is acceptable. However, these heuristics are not guaranteed to be admissible and can lead to suboptimal plans. We introduce LeanPlan, the first planning system that finds optimal plans with LLM-generated heuristics whose admissibility is machine-checked. Given a domain...
-
32
Sensor-Language-Action Models
Yuekai Xu, Zitao Shuai, Yuzhe Yang
cs.AI
Sensors are useful not only for understanding the world but also for deciding what to do next. Existing sensor models however largely stop at perception: they recognize states or predict outcomes, leaving actions modeled separately through task-specific and often closed label spaces. We introduce Sensor-Language-Action (SLA) modeling, a framework that connects multimodal sensor observations, natural language, and actions within a unified...
-
33
OSFP4: Joint Optimization of Diagonal Smoothing and Block Scales for NVFP4 Quantization
Neriah Ben David, Ori Meir, Or Ordentlich
cs.AI
NVFP4 is an attractive datatype for large language model (LLM) inference, offering compact storage and native tensor-core acceleration. However, preserving accuracy using NVFP4 requires careful quantization. In this work we develop a novel quantization scheme called Optimized Smoothing and Scaling for NVFP4 (OSFP4). For each linear projection it uses a diagonal smoothing matrix whose entries are optimized to minimize the squared...
-
34
Confidence-Ordering Reversal under Contextual Priors in Neural Decoding
Xinyu Zhang, Sichao Liu
cs.AI · cs.IR · q-bio.NC
Contextual priors improve neural-to-language decoding by reshaping candidate scores. However, confidence is read from the same reshaped scores, so the errors a prior leaves behind can become more confident with no change in accuracy to reveal it. We study how a prior shapes confidence in speech retrieval on MEG-MASC and MOUS using local decoding scores, a contextual prior combined by additive shallow fusion, and the fused top-two margin as...
-
35
Quantum Entangled Multimodal Fusion Networks (QEMFN): Resource-Aware Hybrid Vision-Language Fusion via Trainable Entanglement
Srikar Alla, Ali Shiri Sichani, Chi-Ren Shyu
cs.AI · quant-ph
Multimodal vision-language systems typically fuse image and text embeddings through classical operators such as concatenation, attention, bilinear pooling, or tensor interactions. We propose Quantum Entangled Multimodal Fusion Networks (QEMFN), a hybrid quantum-classical framework that introduces parameterized entanglement as a structured inductive bias for multimodal fusion. Pretrained visual and textual features are projected into compact...
-
36
Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments?
Yibo Li, Jinhang Qiu, Zhi Zheng, Qianyun Guo, Jiaying Wu, Shuo Ji, Bryan Hooi
cs.AI
Learning from experience is essential for LLM agents to adapt to unfamiliar and dynmaic environments. Evaluating this ability is therefore important for understanding how effectively agents acquire and use new knowledge. Existing benchmarks have sought to evaluate this ability, but they primarily evaluate tasks whose rules are provided in the instructions or already familiar to pretrained models, making it difficult to distinguish learning...
-
37
Mathematical Proof Assistants for Teaching Logic: The LogiKEy Methodology
Christoph Benzmüller, David Fuenmayor, Luca Pasetto
cs.AI · cs.LO
We report on an approach to teaching logic to mixed groups of computer science, mathematics, and philosophy students, based on the logico-pluralistic LogiKEy methodology, used for more than a decade in courses, summer schools, and tutorials. LogiKEy uses classical higher-order logic (HOL) as a universal metalogic in which object logics, classical and non-classical alike, are encoded by defining their semantics; through these semantical...
-
38
LFHE: Local-First Heuristic Evolution for Bounded Local Topology Search in Decentralized Learning with Non-IID Data
Yin-Kuan Liang, Yan Gao, Yang Long
cs.AI · cs.LG
Decentralized learning is highly sensitive to communication topology under non-IID data. Adaptive peer-selection methods can exploit local model information, but broader peer discovery may require increasingly large control state, whereas direct spectral optimization typically relies on graph-wide information. We study the intermediate setting of bounded local topology search and propose Local-First Heuristic Evolution (LFHE), a...
-
39
Which alloy composition,what process parameters? Inferring the recipe from optimized metallic microstructure and texture
Mahish K. Guru, Jan Bohlen, Louam Lemjid, Marius Tacke, Roland Aydin, Noomane Ben Khalifa
cs.AI · cond-mat.mtrl-sci · cs.CE
The mechanical properties of a metallic alloy are set by its microstructure and texture: the size and shape of its grains and the orientation of their crystals. That structure is in turn set by a recipe, the alloy composition together with the processing parameters. Alloy development runs this chain forwards, tuning the structure until a target property is met. Running it backwards, from an optimized structure to the recipe that would produce...
-
40
Partially Observable Zero-shot coordination by Predicting Intention of Partner
Jinnyeong Yang, Yuhwan Jeong, Hoyong Kwon, Minseok Kim, Jihun Kim, Kuk-Jin Yoon
cs.AI · cs.MA
Zero-shot coordination in embodied settings requires acting while the partner is intermittently out of view, leaving existing methods with ambiguous partner representations and uncertainty over hidden partner states. We propose Predicting Intention of Partner (PIP) to jointly address these challenges. PIP uses a Joint-view VAE to distill richer training-time evidence from the union of both agents' local observations into a partner...
-
41
Test-Time Agent Evolution for Long-Horizon Legal Reasoning
Haotian Chen, Shuaicheng Niu, Haocong Rao, Kaisong Song, Jun Lin, Lizhen Cui, Zhiqi Shen, Yonghui Xu
cs.AI
Legal intelligence aims to support reliable decision-making across long-horizon legal processes involving evolving case states and multiple roles. However, real-world legal deployment exhibits substantial case heterogeneity in facts, evidence, and procedural contexts, exposing the limitations of static agent strategies. Moreover, legal reasoning is inherently interdependent across roles and procedural stages, making global reliability...
-
42
ChartBmkAgent: Harness-Governed Multi-Agent Construction of Chart QA Benchmarks from Sparse Error-Taxonomy Specifications
Langxi Huang, Pingping Zhang, Lanyun Zhu, Chunyang Jiang, Jiawei Shao, Haocheng Yuan, Peilin Chen
cs.AI
Multimodal large language models (MLLMs) advance rapidly, while conventional benchmark development lags behind, delaying investigation of newly observed capability gaps. Such investigation requires an expressive task format and an on-demand construction process: information-rich charts make chart question answering (Chart QA) suitable for probing coupled perception and reasoning. Automated Chart QA construction is intended to shorten the...
-
43
DSV-Mem: Evaluating Multimodal Memory in Professional Workflows for MLLM Agents
Jike Zhong, Ritwick Chaudhry, Xuanbai Chen, Tianchen Zhao, Linghan Xu, Yifan Xing, Nishant Sankaran
cs.AI
Conversational MLLM agents are increasingly expected to assist in professional workflows, from AI research and engineering design to product management and business operations. Yet this capability remains underexplored: existing benchmarks largely focus on informal, everyday interactions and personal-life scenarios featuring photographic natural images, isolated static artifacts, and recall-oriented questions. In contrast, professional...
-
44
Beyond Corrected Memory: Execution Consistency in Multi-Agent Systems
Zhe Yu, Zixuan Wang, Peidong Wang, Hehai Lin, Ruochen Zhao, Chengwei Qin
cs.AI
Shared memory coordinates agents' actions, but correct records do not establish that those actions satisfy task requirements. Memory governance and failure diagnosis regulate or inspect recorded information; they do not by themselves establish whether it is sufficient to judge task duties. We define execution consistency through duties governing state use, information handoffs, and final-state agreement, with explicit evidence conditions for...
-
45
Natural Language Questions as an Interface for Knowledge Graphs: QRAKEN Graph Distillation and Semantic Self-Healing
Remo Grillo, Lukas Klic, Giovanni Colavizza
cs.AI · cs.CL
Natural-language access to RDF knowledge graphs is a core Semantic Web ambition. Large language models (LLMs) have advanced Text-to-SPARQL, yet on unfamiliar graphs they often generate valid queries that misrepresent the populated data model. QRAKEN is a training-free, ontology-agnostic neurosymbolic pipeline grounding generation in empirical graph evidence rather than schema expectations. An offline distiller produces TTQL, a compact...
-
46
POLAR: Ontology-Guided Risk Prevention for Tool-Calling LLM Agents
Yunju Kang, Seonghyeon Cho, Irene Li, Yeo-Chan Yoon, Chanjun Park
cs.AI · cs.CL
LLM tool-use agents operate in dynamic environments where many actions carry operational risk. However, most safety mechanisms react only after errors manifest. Existing pre-emptive approaches either fine-tune the agent on chain-of-thought deliberation or compile natural-language guardrails into runtime checks, but they do so without exposing a structural, auditable verdict. We propose POLAR, a guardrail framework for small tool-calling...
-
47
Self-Retrospection Distillation: Turning Post-hoc Experiences into Prior Foresight
Haoxiang Zhang, Qinglin Chen, Hiroaki Hayashi, Zhuofeng Li, Siming Zhang, Jiaxin Zhang, Jixuan Chen, Fang Wu, Pan...
cs.AI · cs.CL · cs.IR · cs.LG
Reinforcement learning with verifiable rewards (RLVR) turns agent experience into learning signals primarily through scalar outcome rewards after interaction. For group-relative objectives, however, this signal vanishes when all rollouts receive the same reward, even though their trajectories may reveal useful information about what the task requires and how the agent fails. We ask a complementary question: can hindsight teach an agent what...
-
48
SpeedrunBench: Challenging LLM Agents with Video Game Speedrunning
Yoshinari Fujinuma, Keisuke Kamahori, Ryuto Koike, Abdelrahman Madkour, Varun Prashant Gangal, Monty Bichouna,...
cs.AI
Frontier LLM agents have been shown to be capable of solving increasingly complex tasks for which humans have measurable solutions. This begs the pertinent question of whether LLM agents can go beyond what humans have already solved. The ability to develop sophisticated strategies to tackle consequential problems becomes paramount as well-trodden, human-developed solutions become insufficient for problems for which we lack context or enough...
-
49
DAEDALUS: Bootstrapping Agent Memory from Self-Generated Tasks
Antoine Edy, Max Conti, Victor Xing, Marc-Antoine Allard, Nawfal Benhamdane, Gautier Viaud
cs.AI · cs.CL · cs.LG
LLM agents often lack the operational knowledge to act reliably in new environments, as they must discover specific tool behaviors or environment conventions on their own. Without memory of past attempts, they repeat the same mistakes across tasks, leading to more task failures and longer trajectories. To address this, agentic systems typically rely on human-written guidelines or on procedural memory built from training tasks and an oracle...
-
50
Same Feedback, Different Answer: Measuring Run-to-Run Instability in Frontier-Model Customer Feedback Analysis
Viraj Bagal, Raviraja Ganta, Prabhath Chellingi
cs.AI
AI agents are increasingly being programmed to automate knowledge work over large collections of unstructured data. Such automation requires repeatability: when the underlying evidence is unchanged, the agent's categories, priorities, and counts should not shift materially between runs, even if each individual answer appears plausible. We introduce a repeat-run evaluation framework that aligns semantically equivalent categories and focuses on...
-
51
Learning in Dreams, Winning in Reality: A Continuous Dyna Loop for a Ten-Hero MOBA
Jordy Kieto
cs.AI
World models are usually judged from the inside: by prediction loss, by the return a policy earns in imagination, or by how convincing their frames look. We judge one from the outside. We learn a structured, multi-agent world model of a complete ten-hero MOBA (206 units, every hero acting every tick, games of up to 6,000 ticks), train a policy only inside it with 1,400-tick free-running imagined episodes, and measure that policy in the real...
-
52
Learning from Revision Consequences: Hindsight Meta-Experience Distillation for Self-Improving Agents
Qianhan Feng, Zhongzhen Huang, Yakun Zhu, Xiaofan Zhang, Qi Dou
cs.AI
As agents continuously improve by generating and revising Skills, the process that discovers and refines those Skills becomes a learnable object in its own right. Task-Skills directly act on task execution, whereas Meta-Skills govern how agents discover and improve future Skills; their value therefore emerges through the subsequent search processes they induce. Existing approaches improve Meta-Skills from observed raw Skill-search...
-
53
Can Agents Work for Everyone? Cross-User Reliability for Mobile GUI Agents in Personalized User Interfaces
Yeji Park, Jaeyun Shim, Taesik Gong
cs.AI
Mobile GUI agents increasingly operate on interfaces influenced by users' histories and preferences, but their reliability across different users remains underexplored. We introduce PAIR (Personalized Application-state Instantiation and Rendering), a pipeline for constructing user-conditioned application states that enables controlled evaluation of the same task across different users. We further introduce RePAIR (Reinforcement learning with...
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.