cs.CL · 2026-08-04 · No. 74
Computation and Language, 2026-08-04.
10 new papers in cs.CL. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
10 entries-
01
LiveMem: Maintaining Memory State Continuity in Long-Running LLM Inference
Zhichen Liu, Ruihan Sun, Hengjie Yang, Zipeng Wu, Zhaohan Chen, Xiaofan Zhang, Yang Xu
cs.CL · cs.LG
Long-running assistants and agents consume interaction streams that eventually outgrow the context. Existing context retention, summarization, and retrieval preserve access to selected history, but do not provide a persistent state over the full lifecycle when working context changes. We formulate this missing inference capability as \emph{state continuity under context turnover}: carrying computation forward through a fixed-capacity memory...
-
02
Cultural Awareness is Represented but Not Decoded: Tracing Mythological Knowledge across 18 Open-Source LLMs
Iaroslav Chelombitko, Ekaterina Chelombitko, Mika Hämäläinen
cs.CL · cs.CY · cs.LG
Open-source LLMs reliably name Zeus, Jupiter, and Thor, but recover their counterparts in less-represented traditions like Finnish, Slavic, Egyptian, or Chinese mythology far less consistently. We ask where inside the model this cultural default is produced. On a parallel cross-cultural substrate of Thompson-motif entities, we instrument 18 open-source LLMs from 8 architecture families with linear probing, logit lens, activation patching, and...
-
03
Can AI Agents Simulate A/B Test Outcomes? A Validation Framework for Agentic Experimentation
Stefan Hut, Lorenzo Masoero
cs.CL · cs.AI · stat.AP
A/B testing remains the standard for rolling out new features in the technology industry. Each experiment, however, consumes real traffic, engineering effort, and weeks of wall-clock time. Can AI agents---conditioned on behavioral profiles and contextual descriptions of the intervention---simulate outcomes accurately enough to vet candidate treatments before committing live traffic? We formalize this question as a \emph{Simulated Randomized...
-
04
Domain-Specific Evaluation of Text-to-Speech Systems: A Multi-Metric Benchmarking Study
Ali Jafar, Amal Sarmad, Shifa Yousaf, Maryam Bashir
cs.CL · cs.LG
Recent advances in neural text-to-speech (TTS) systems have substantially improved speech naturalness and intelligibility across many languages. However, comprehensive evaluation methodologies that jointly assess perceptual quality, speaker similarity, and acoustic fidelity across diverse speech domains remain limited, particularly for low-resource and underrepresented languages. This paper presents a reproducible, multi-metric benchmarking...
-
05
Self-Improving Large Language Models via Progressive Experience Evolution
Shijie Ren, Xiting Wang, Meng Li, Yujie Guo, Yunhang Yao, Ziheng Peng, Xunlong Wang, Yuetan Chen, Haoyang Zhou,...
cs.CL · cs.AI · cs.LG
Large language models (LLMs) capable of self-improvement require not only effective policy optimization, but also a principled mechanism for transforming transient interaction experience into persistent model capabilities. Existing self-improvement paradigms remain fragmented: test-time methods can explicitly extract experience but cannot internalize it into model parameters, whereas training-time optimization methods can update model...
-
06
IACM-RL: Intent-Aware Context Management and Reinforcement Learning for Complex Tool Invocation under Dynamic Intent Fluctuations
Dingwei Zhu, Jiahan Li, Chengjun Pan, Yunxian Yang, Yunbin Zhao, Yunke Zhang, Zhonghang Lu, Zhuohui Sheng, Chenhao...
cs.CL · cs.AI
Executing long-horizon tool invocations in real-world environments is severely challenged by dynamic user intent noise. Existing methods attempt robustness via implicit history scanning or text compression, yet predominantly assume perfect instructions in simplistic scenarios. Inevitably, under fluctuating contexts, obsolete constraints dilute model attention, triggering catastrophic intent deviation and infinite API loops. To resolve this,...
-
07
TextNCA: Neural Cellular Automata for Language Modeling via Hierarchical Local Attention
Avni Mittal, Avinash Anand, Ashutosh Kumar, Dikshant Kukreja, Kritarth Prasad, Sushane Dulloo, Erik Cambria, Timothy...
cs.CL · cs.AI · cs.LG
Can a strictly local, iterated, weight-shared computation primitive support language modelling, and which of those three properties actually drives the model's behaviour? We define \textsc{TextNCA}, a 1D causal windowed-attention realisation of the Neural Cellular Automaton primitive, and study a hierarchical variant that cascades three stages with windows $w \in \{8, 32, 128\}$ and $T_s$ shared-weight iterations per stage, all on...
-
08
CompanionBench: A Theory-Anchored, Real-World-Grounded Benchmark for AI Emotional Companionship
Yao Liu, Guangjia Chai, Yuming Huang, Jihao Huang, Lei Wang, Junchen Wan
cs.CL · cs.AI
LLM companions are deployed at scale in personally consequential settings, yet poorly evaluated. Existing benchmarks use hand-authored scenarios and prompted simulators, aggregate empathy into one score, and overlook judge biases such as same-family favoritism and scale drift. We introduce CompanionBench, an interactive bilingual benchmark. To our knowledge, it is the first companion benchmark to ground both its scenarios and a trained user...
-
09
Look Ahead Before You Distill: Future Trajectory Validation of Teacher Guidance for Agentic On-Policy Distillation
Chishui Chen, Yaoyou Fan, Te Sun, Yi Yang, Chenghao Sun, Delin Mao, Hongbo Qiao, Zuowei Zhang, Junxi Wang, Chenxing...
cs.CL · cs.LG
On-policy distillation (OPD) provides teacher supervision on states visited by the student, reducing the distribution gap between training and inference. However, in multi-turn agentic tasks, student deviations may accumulate over time, gradually moving the trajectory away from states where teacher guidance remains effective. Our quantitative analysis further shows that high-disagreement states offer promising opportunities for teacher...
-
10
Automatic Annotation of Ancient Greek Vowel Length
Albin Thörn Cleland, Eric Cullhed
cs.CL · cs.AI · cs.LG
Prior work in Ancient Greek NLP relies on corpora that do not disambiguate the phonemic vowel length of alpha, iota, and ypsilon, together known as the dichrona. Depending on lexeme, morphology, sandhi, syntax, and conventions of period, genre, and verse form, each of these letters can represent either a long or a short vowel. Deciding and marking the correct length is known as "macronizing", a long-tail problem given the sheer mass of word...
This edition is part of The Daily Abstract — cs.CL 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.