Upgrade to Pro — share decks privately, control downloads, hide ads and more …

論文読み会 SNLP2026 Tau2-Bench: Evaluating Conversat...

Avatar for S S
August 19, 2026
Research
2
0

論文読み会 SNLP2026 Tau2-Bench: Evaluating Conversational Agents in a Dual-Control Environment

Avatar for S

S

August 19, 2026

More Decks by S

See All by S
論文読み会 SNLP2025 Learning Dynamics of LLM Finetuning. In: ICLR 2025
Avatar for S s_mizuki_nlp
0
490
論文読み会 SNLP2024 Instruction-tuned Language Models are Better Knowledge Learners. In: ACL 2024
Avatar for S s_mizuki_nlp
1
630
埋め込み表現の意味適応による知識ベース語義曖昧性解消
Avatar for S s_mizuki_nlp
2
610
論文読み会 SNLP2018 Sequence to Action: End to End Semantic Graph Generation for Semantic Parsing
Avatar for S s_mizuki_nlp
0
140
論文読み会 SNLP2019 Ordered neurons: Integrating tree structures into recurrent neural networks
Avatar for S s_mizuki_nlp
0
150
論文読み会 SNLP2020 ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators
Avatar for S s_mizuki_nlp
0
210
論文読み会 SNLP2021 A Distributional Approach to Controlled Text Generation
Avatar for S s_mizuki_nlp
0
170

Other Decks in Research

See All in Research
[IR Reading 2026春 論文紹介] LLM-based Listwise Reranking under the Effect of Positional Bias (ECIR 2026) /IR-Reading-2026-Spring
Avatar for Kohei Shinden koheishinden
PRO
0
330
Language and AI
Avatar for Ayana Niwa ayaniwa
0
210
2025年度秋葉原ウォーカブルプロジェクト調査報告 「アキバらしいウォーカブル」とは何か
Avatar for 日本大学 都市計画研究室（泉山ゼミ） izumiyama_lab
1
180
AIで最適化を解けるか？
Avatar for MIKIO KUBO mickey_kubo
0
150
[CV勉強会＠関東 CVPR2026] PSDesigner: Automated Graphic Design with a Human-Like Creative Workflow / kantocv 67th CVPR 2026
Avatar for Shunsuke KITADA shunk031
0
250
多様なデータを許容し学習し続ける模倣学習 / Advanced Imitation Learning for VLA
Avatar for PRIN Lab prinlab
0
280
マーケットストリート 社会実験2024 in 秋葉原ジャンク通り 調査報告書
Avatar for 日本大学 都市計画研究室（泉山ゼミ） izumiyama_lab
1
110
260624_NLP-colloquium: Hubness
Avatar for Hiroyuki Deguchi de9uch1
1
180
Anthropic が提案する LLM の内部状態を自然言語で説明可能にした Natural Language Autoencoders / Natural Language Autoencoders Produce Unsupervised Explanations of LLM Activations
Avatar for Shunsuke KITADA shunk031
0
170
AIエージェント時代のLLM-jpモデルのあるべき姿
Avatar for Kouta Nakayama k141303
0
570
Fukui Shibiten 39 - AI Art
Avatar for IWABUCHI Yu(u)ki butchi butchi
0
180
EIRによる不正端末のブロッキング 5G時代におけるデバイス識別と不正対策の進化
Avatar for Stellar Craft, Inc. stellarcraft
0
120

Featured

See All Featured
The Psychology of Web Performance [Beyond Tellerrand 2023]
Avatar for Tammy Everts tammyeverts
49
3.5k
Google's AI Overviews - The New Search
Avatar for Barry Adams badams
0
1.1k
The agentic SEO stack - context over prompts
Avatar for schlessera schlessera
0
870
End of SEO as We Know It (SMX Advanced Version)
Avatar for Michael King ipullrank
3
4.4k
Understanding Cognitive Biases in Performance Measurement
Avatar for Philip Tellis bluesmoon
32
3k
[SF Ruby Conf 2025] Rails X
Avatar for Vladimir Dementyev palkan
2
1.3k
Creating an realtime collaboration tool: Agile Flush - .NET Oxford
Avatar for Marc Duiker marcduiker
35
2.5k
The Cost Of JavaScript in 2023
Avatar for Addy Osmani addyosmani
55
10k
The #1 spot is gone: here's how to win anyway
Avatar for Tamara Novitovic tamaranovitovic
3
1.1k
First, design no harm
Avatar for Per Axbom axbom
PRO
2
1.3k
GraphQLの誤解/rethinking-graphql
Avatar for sonatard sonatard
75
12k
個人開発の失敗を避けるイケてる考え方 / tips for indie hackers
Avatar for panda_program panda_program
123
22k

Transcript

  1. ICML2026 Spotlight Tau2-bench: Evaluating Conversational Agents in a Dual-Control Environment.

    In: ICML 2026 Victor Barres, Honghua Dong, Soham Ray, Xujie Si, Karthik R Narasimhan 第18回 最先端NLP勉強会 Hottolink/SciTokyo Okazaki Lab/AIST: Sakae Mizuki 2026-08-30

  2. 概要 2

  3. まとめと考察 3