cs.CL · 2026-11-16 · No. 173
Computation and Language, 2026-11-16.
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
Interactive Program Induction with Language Model Priors
Robin Shing Moon Chan, Ryan Cotterell
cs.CL · cs.AI · cs.LG
Program induction refers to the process in which a learner aims to recover a program from a few given input-output examples. This paradigm broadens programming access by letting users demonstrate the rule-based behavior they want to apply to unseen data, instead of having to implement it themselves. However, recovering a program from finite input-output examples is fundamentally ambiguous, as a finite set of input-output examples is...
-
02
Do Verifier Judgments Survive Abstraction? Measuring Verification Transport for LLM Agent Evaluation
Disha Sheshanarayana, Sai Linisha Reddy Goli
cs.CL · cs.AI
LLM-based verifiers are increasingly used to evaluate agent executions, but their reliability is typically measured under a single representation of the trajectory. In deployed agent systems, the same execution may be exposed through composed tools, delegation boundaries, or compacted histories, changing what execution evidence is directly observable to the verifier. It therefore remains unclear whether correct verifier judgments persist...
-
03
Gamer: A Generalist Vision-Language-Action Foundation Model for Long-Horizon Real-Time Game Agent
Run Luo, Kuan Zhang, Qi Deng, Yukun Chen, Zhihao Yang, Yufei Zhang, Renrong Hu, Yi Zhang, Guiyu Ma, Tianyu Fan,...
cs.CL · cs.AI · cs.CV
We introduce Gamer, a generalist agent framework built for long-horizon tasks in complex interactive environments. Its end-to-end architecture combines perception, memory management, and multi-step reasoning. A shared training and deployment pipeline supports interaction with both conventional 2D graphical interfaces and complex 3D simulated worlds. We first continue pre-training on a dataset constructed from tens of thousands of hours of...
-
04
Can You Trust Your Finance Agent? Drift, Diagnosis and Auditable Intervention on One Shipped Financial Research Agent
Cosimo Galeone, Anna Ettorre, Ginevra Mariani, Minsu Park, Giuseppe Ettorre, Daniele Ligorio
cs.CL · cs.AI
Can you trust a finance agent you did not build? We take the reference agent shipped with the Vals Finance Agent Benchmark v2, leave it untuned, and ask four questions a leaderboard score does not answer. Is the score stable? Seven identical runs on 18 questions pass between 105 and 123 of 149 rubric criteria, and the bill varies by up to 17%. When the agent fails, who owns the fix? We classify 20 failed trajectories, from three runs of nine...
-
05
MineralExp: Benchmarking LLM Agents for Experimental Design in Real-World Mineral Exploration
Bing Wang, Mingyang Wang, Yuanhang Mi, Yue Xu, Kaibo Su, Li'ang Xiao, Chunguo Wu, Changchun Li, Ximing Li, Kun-Feng...
cs.CL · cs.AI · cs.CE
In mineral exploration, verifying geological hypotheses relies on designing a variety of geochemical experiments. While large language model (LLM) agents increasingly automate downstream geoscientific data analysis, a crucial upstream capability remains largely unexplored: automated geochemical experimental design, i.e., deciding which experiments to conduct before committing to costly laboratory work. Evaluating this capability of LLM agents...
-
06
UltraBERT-JEV: Encoder models for System One Applications
Astarag Mohapatra
cs.CL · cs.AI
We study encoder models that pick one of several options in a single forward pass, without generating text. This technical report compares recipes for fine-tuning UltraBERT-380M with one mask per option. The four recipes differ in how an option is scored and how the scores become probabilities; one follows the expert gate of DeepSeek-V3. Trained on the same data as Qwen3-0.6B with the LLM-as-Jev recipe (67.6% test accuracy), the encoder...
-
07
CarryOn: Learning What to Keep in Context for Long-Horizon LLM Agents
Lihuan Li, Ruiyi Yang, Jiru Wang, Yifan Duan, Xiachong Lin, Hao Xue, Yang Song, Flora Salim
cs.CL · cs.AI
Long-horizon LLM agents can coordinate tools and applications to complete complex, multi-step tasks. As their interaction histories grow, effective context management becomes essential for reliable and efficient execution. Existing methods reduce context through summarization, pruning, or history selection. However, shorter contexts do not necessarily support better decisions: summaries can omit exact details needed for later actions, while...
-
08
LuthorSQL: A One-Pass Text-to-SQL Model as System 1 for a Slower LLM Agent
Ibrahim Memon, Armin Karamzade, M. Hanif Jhaveri, Roy Fox
cs.CL · cs.AI · cs.DB · cs.LG
Frontier LLM agents that query databases with tools are among the most accurate text-to-SQL systems, but per-query calls to a hosted model are slow, costly, and expose sensitive organizational queries to external APIs. For example, a Claude Opus 5.5 agent serving 10,000 queries a day costs over $70,000 a year at list price. To what extent can local hardware already owned by an organization offload this burden without compromising the agent's...
-
09
Activation Steering the Nan-Shan in Typhoon
Megan Wei, Damon Pham, John Cayley, Ellie Pavlick
cs.CL · cs.AI · cs.LG · cs.SD
Typhoon is an audiovisual installation based on Joseph Conrad's novella, in which Captain MacWhirr steers the steamer Nan-Shan directly into and through a catastrophic storm. The novella is a study of what happens when the scale of a phenomenon exceeds the practical and conceptual frameworks available to comprehend it and of the paralysis that sometimes follows a demand for action in such overwhelming circumstances. We chose the text of...
-
10
GDP.xlsx: Benchmarking Frontier Models on Professional Workbooks
Suhaas Garre, Sushant Mehta, Edwin Chen
cs.CL · cs.AI
We introduce GDP_xlsx, a benchmark of 70 realistic workplace requests written by professionals in 13 domains, each paired with an expert rubric of binary criteria and with the complete workbook or CSV file it refers to. Together the files hold 2.18 million populated cells, and the rubrics 791 criteria. Agents work in a container with spreadsheet tools, and an agentic judge that can open the file applies the rubric. Completeness and...
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.