#benchmark evaluation

32 results
cs.AI2026

AgenticASR: Refining Speech Recognition in Real-World Scenarios via an Agentic Approach

Zixuan Jiang, Binghao Qiang, Jiaying Chi +3

The paper introduces AgenticASR, an architecture that continuously refines speech recognition output to remove disfluencies and preserve speaker intent during live audio streams.

#agentic speech recognition#disfluency removal#online transcription#refiner architecture
cs.AI2026

Albilich: Steerable Proof-State Orchestration for LLM-Based Mathematical Research with CAS Integration

Ting Gong, Michael Ruofan Zeng, Yong Yang

Albilich is an open‑source agentic framework that lets large language models conduct long‑horizon mathematical research by integrating computer algebra systems, literature retrieva…

#mathematical reasoning#large language models#computer algebra systems#proof automation
cs.AI2026

When Specifications Conflict: A Symmetry-Based Framework for Measuring LLM Preferences

Tairan Wang, Liang Zhou, Zikang Zhan +1

The paper presents a symmetry‑based experimental framework for measuring how large language models resolve conflicts between competing specifications, and evaluates systematic pref…

#large language models#conflict resolution#specification analysis#symmetry design
cs.AI2026

Rethinking Inference-Time Scaling in Local Computer-Use Agents: Failure Modes and Compute Tradeoffs

Woongkyu Lee, Jungwook Choi

The paper empirically studies how different inference-time scaling strategies affect the performance and failure modes of locally deployed autonomous computer-use agents under hard…

#autonomous agents#computer-use agents#inference scaling#resource-constrained models
cs.AI2026

How Benchmarks Mis-Score Computer-Use Agents

Zihan Dong, Zhiyuan Ma, Zekun Wang +5

The paper examines how current benchmarks for computer-use agents often give inaccurate scores due to issues in task design, trajectory observation, scoring, and reporting, and pro…

#computer-use agents#benchmark evaluation#reliability#error analysis
cs.AI2026

Evidence-Ledger Adjudication for Claim-Evidence Traceability

Gengyu Chen, Yongjie Yu, Weiling Wang

The paper introduces evidence-ledger adjudication, a workflow that pairs AI‑generated claims with evidence packets, assigns support relations, and routes unsupported or contradicto…

#claim verification#evidence retrieval#AI‑assisted writing#traceability
cs.CV2026

See2Think: Do Multimodal Models Really Use Intermediate Visual States?

Siyu Yan, Zhuoran Yan, Haiying Xu +10

The paper presents See2Think, an evaluation framework and benchmark for testing whether multimodal large language models actually use intermediate visual states during reasoning, a…

#multimodal models#visual reasoning#intermediate visual states#benchmark evaluation
cs.CR2026

MemSecBench: Tracking Agent Memory Poisoning from Persistence to Consequence and Repair

Xuanze Chen, Xukang Xie, Wentao Fu +3

The paper presents MemSecBench, a benchmark that evaluates how malicious instructions can persist, be executed, and be repaired in agent memory systems across different memory and…

#agent memory security#memory poisoning#benchmark evaluation#large language models
cs.SE2026

MindForge: Teaching Small Language Models Whole-Life-Cycle Software Engineering via Source-Free Program Synthesis

Yihao Chen, Shi Chang, Khaled Chawa +4

MindForge automatically turns open‑source command‑line programs into source‑free environments that expose only compiled executables and documentation, enabling the training of smal…

#source-free program synthesis#software engineering lifecycle#code generation#model fine‑tuning
cs.AI2026

Automated Transcript Analysis for Detecting Flaws in Agentic Benchmarks

Jeff Mohl, Nelson Gardner-Challis, Magda Dubois +6

The paper presents automated AI scanners that analyze benchmark transcripts to detect validity flaws such as ground‑truth leakage, tool failures, guessing vulnerabilities, and ambi…

#benchmark evaluation#automated auditing#transcript analysis#model validation
cs.CV2026

Visual Credit Audit for Multimodal Spatial Reasoning

Feixiang Liu, Qiang Qiu, Lanbo Sun +3

The paper introduces Visual Credit Audit (VCA), a method to quantify how much an image actually contributes to a multimodal model’s answer on spatial reasoning tasks, separating co…

#visual credit audit#multimodal spatial reasoning#benchmark evaluation#large language models
cs.AI2026

When benchmark inferences do not compose: Projectibility in AI evaluation

Brett Reynolds

The paper examines how AI benchmark results are extrapolated to broader claims, introducing a non‑composition principle that warns against automatically chaining supported inferenc…

#benchmark evaluation#projectibility#inference composition#validity assessment
cs.CV2026

Seeing or Knowing? Visual Context Sensitivity in Multimodal Large Language Models

Jiaang Li, Chengzu Li, Zhaochong An +4

The paper investigates why multimodal large language models often ignore visual evidence, using image reconstruction and a new benchmark (WhatIfVis) to measure how well models bala…

#multimodal large language models#visual context sensitivity#image reconstruction#benchmark evaluation
cs.SE2026

Do Code Language Models Use Tests? A Behavioral and Representational Study of Test-Driven Code Generation

Yunhao Liang, Chengguang Gan, Ruixuan Ying +3

The paper investigates how code language models respond to test cases in prompts, analyzing whether tests act as executable specifications or merely extra context, and finds that t…

#test-driven code generation#code language models#prompt engineering#benchmark evaluation
cs.CL2026

The Tool Illusion: Rethinking Tool Use in Web Agents

Renze Lou, Baolin Peng, Wenlin Yao +5

The paper presents a large, controlled empirical study of tool use in web agents, examining how different tools, backbone models, and frameworks affect performance across multiple…

#web agents#tool use#empirical study#benchmark evaluation
cs.AI2026

Can We Trust Item Response Theory for AI Evaluation?

Han Jiang, Sunbeom Kwon, Jinwen Luo +2

The paper investigates how well item response theory (IRT) works for evaluating large language model benchmarks, highlighting challenges when benchmark data differ from traditional…

#item response theory#benchmark evaluation#large language models#simulation study
cs.SI2026

Overlapping Network Community Detection Using Sparse Backbones

Zihe Zhou, Samin Aref

The paper introduces Highway, a scalable algorithm that detects overlapping communities in networks by leveraging a sparse backbone representation to improve both accuracy and effi…

#overlapping community detection#network backbones#scalable algorithms#benchmark evaluation
cs.LG2026

The Joint Effect of Quantization and Sampling Temperature on LLM Safety Alignment: A Factorial Analysis

Hari Prasad, Ritam Pal

The paper investigates how model quantization and higher sampling temperatures jointly affect the safety alignment of instruction-tuned large language models, finding that quantiza…

#large language models#quantization#sampling temperature#safety alignment
cs.AI2026

Do Agent Optimizers Compound? A Continual-Learning Evaluation on Terminal-Bench 2.0

Wenxiao Wang, Priyatham Kattakinda, Soheil Feizi

The paper evaluates whether gains from agent-optimization methods compound over successive optimization phases in a continual‑learning setting, using hard tasks from Terminal‑Bench…

#continual learning#agent optimization#benchmark evaluation#regression control
cs.LG2026

What Do Temporal Graph Learning Models Learn?

Abigail J. Hayes, Tobias Schumacher, Markus Strohmaier

The paper investigates which structural and temporal properties of graphs are actually captured by state‑of‑the‑art temporal graph learning models, using systematic tests on synthe…

#temporal graphs#graph representation learning#model interpretability#benchmark evaluation
cs.LG2026

PRISM Edit: One Vector for All Temporal Answers

Chen Huang, Qi Zheng, Ruiqin Zheng +2

The paper proposes PRISM Edit, a method that updates large language models to handle changing temporal facts by learning a single representation that can be modulated for different…

#model editing#temporal reasoning#large language models#causal tracing
cs.CV2026

What Does a Temporal Benchmark Score Measure? Decomposing Channel Use in Video VLM Evaluation

Farrukh Rahman

The paper examines how temporal video QA benchmark scores conflate task difficulty with the model's reliance on positional encodings versus visual sequence order, and introduces a…

#temporal video understanding#video question answering#benchmark evaluation#positional encoding
cs.CV2026

Image Matching Filtering and Refinement by Planes and Beyond

Fabio Bellavia, Zhenjun Zhao, Luca Morelli +1

The paper evaluates state‑of‑the‑art filtering and refinement techniques for image matching, introduces a new method that combines planar constraints with cross‑correlation, and sh…

#image matching#filtering#refinement#planar constraints
cs.AI2026

Measurement Risk in Supervised Financial NLP: Rubric and Metric Sensitivity on JF-ICR

Sidi Chang, Peiying Zhu, Yuxiao Chen +1

The paper investigates how the wording of evaluation rubrics and the choice of metrics affect the reliability of supervised financial NLP benchmarks, using a Japanese implicit‑comm…

#financial nlp#benchmark evaluation#rubric sensitivity#metric selection
← Prev1 / 2Next →