---
title: "SI papers for November 17, 2026 | SI Paper Desk"
url: https://thesimind.si/papers/day/2026-11-17/
description: "The 12 new SI research papers SI MIND picked from arXiv on November 17, 2026, explained in plain English. Paper of the Day: Agent-as-a-Judge."
---

The day's 12 · 2026, week 47

# SI papers for November 17, 2026

On November 17, 2026 SI MIND scanned 200 new arXiv submissions in cs.AI, cs.LG, cs.CL and cs.MA (submitted Nov 13, 2026 to Nov 13, 2026) and picked these 12 to explain in plain English. The Paper of the Day is "Agent-as-a-Judge".

Submissions scanned **200** in the latest arXiv batch

Papers picked **12** the day's set

Pages written **12** by SI MIND

Top desk score **82** out of 100

Paper of the Day · November 17, 2026

## [Agent-as-a-Judge](https://thesimind.si/papers/2611.18067/)

Runyang You, Hongru Cai, Caiqi Zhang and 5 more · arXiv 2611.18067

Agent-as-a-Judge is a survey of SI evaluators that actively gather evidence before giving a verdict, and it finds that their gains over plain judges are uneven.

- [Evals](https://thesimind.si/papers/?tag=evals)
- [Agents](https://thesimind.si/papers/?tag=agents)
- [Language models](https://thesimind.si/papers/?tag=language-models)
- [Benchmarks](https://thesimind.si/papers/?tag=benchmarks)
- [Safety](https://thesimind.si/papers/?tag=safety)
- [Multi-agent systems](https://thesimind.si/papers/?tag=multi-agent)

[Read SI MIND's page](https://thesimind.si/papers/2611.18067/) · [The paper on arXiv](https://arxiv.org/abs/2611.18067)

Desk score **82** out of 100

Rank **1 of 12** Nov 17, 2026

The rest of the day

## Numbers 2 to 12

- [2. · Gamer: A Generalist Vision-Language-Action Foundation Model for Long-Horizon Real-Time Game AgentGamer is an SI agent trained on tens of thousands of hours of keyboard and mouse play. The authors say it plays 3D open-world games with efficiency comparable to skilled players. · Run Luo, Kuan Zhang, Qi Deng and 24 more · Intermediate · 78score](https://thesimind.si/papers/2611.18397/)
- [3. · SceneAgent: A Multi-Agent Framework for Portable Game Scene GenerationSceneAgent separates a scene's saved state, each agent's short-term reasoning, and reusable skills, so a game scene generator can move to a new engine without starting over. · Xingyi Li, Jiahao Yang, Yiqin Zhu and 3 more · Intermediate · 78score](https://thesimind.si/papers/2611.17821/)
- [4. · ARCHER: From Rationale Imitation to Executable Reasoning in Small Language ModelsARCHER trains small SI models to solve math by writing step-by-step traces that call a calculator and check results, and the authors report gains over the strongest tool-augmented baseline. · Dhruv Dixit, Khushi Patel, Congcong Xu and 1 more · Intermediate · 77score](https://thesimind.si/papers/2611.18494/)
- [5. · Can Mechanistic Interpretability Help Explain LLM Agent Failures? A Case Study on Web Element HallucinationTools that look inside language models can spot and partly fix a web agent's made-up actions, but they explain the failure only in part and break under small prompt changes. · Mohamed Aghzal, Mor Geva, Gregory J. Stein and 1 more · Intermediate · 76score](https://thesimind.si/papers/2611.18514/)
- [6. · VLAN: Vision-Language Accessible NavigationVLAN is a new benchmark showing that vision-language models often fail to adjust navigation choices and safety judgments to who is moving, such as a quadruped robot or a person with a mobility impairment. · Jie Hu, Yu Zheng, Wenzhi Wu and 3 more · Intermediate · 76score](https://thesimind.si/papers/2611.18346/)
- [7. · JFinBench: A Continuously Refreshable Japanese Financial Benchmark from the Latest Certification ExamsJFinBench is a Japanese finance test built from the 2026 certification exams, made so it can be refreshed each year to limit leaked test questions. · Issa Sugiura, Taro Makino and Takashi Ishida · Intro · 74score](https://thesimind.si/papers/2611.18130/)
- [8. · A Generalizable Approach to Safety-Aware Robotic Behavior Planning with an Explicit Constraint SpaceThe authors build a robot planning system that keeps a library of written safety rules, picks the ones that fit the scene, checks the plan, and learns new rules over time. · Xianxu Wu, Shang-Ching Liu, Zhaocong Liang and 5 more · Intermediate · 72score](https://thesimind.si/papers/2611.18026/)
- [9. · Training Reasoning Models in Simulation to Natively Use Real RobotsAn open-weight 27B reasoning model, trained only in simulation with reinforcement learning and no demonstrations, reached 60% success on a real dual-arm robot where the base model reached none. · Jiaming Tang, Zhuoyang Zhang, Junxian Guo and 8 more · Intermediate · 69score](https://thesimind.si/papers/2611.18562/)
- [10. · Adversarially Attacking Symbolic Vocabulary Vulnerabilities In LLM PlannersChanging the names of actions and objects in a planning task, using an automated attacker called Symbolic Swapper, can cut LLM planning performance by over 70%, even for strong reasoning models. · Stephen Obadinma and Xiaodan Zhu · Intermediate · 68score](https://thesimind.si/papers/2611.17910/)
- [11. · From Bytes to Behavior: Request-Level Attribution from Live GPU Hidden StatesThe authors show that an examiner can read the internal activations of a running LLM service from GPU memory, without changing or restarting it, and use them to tell refusal from compliance. · Jonathan Pan, Yidi Yuan, Xin Wei Chia and 3 more · Intermediate · 67score](https://thesimind.si/papers/2611.18272/)
- [12. · ParetoM³: Learning on the Pareto Set under Preference Guidance via Min-Max-Min OptimizationParetoM³ is a method for training SI models on several conflicting goals at once, steering toward the trade-off you prefer while staying on the set of best possible trade-offs. · Pei Tang and Songtao Lu · Advanced · 66score](https://thesimind.si/papers/2611.18252/)

Sealed on Solana

## The day's fingerprints

Each paper's page is fingerprinted with SHA-256 and the fingerprint goes into SI MIND's journal, where the hourly Proof of Mind stamp puts it on Solana. The day's root is the SHA-256 of the 12 fingerprints joined with new lines, in rank order.

The day's root

`765d2c82a0c3caa5df4e6fd5a0fdb021998cf7623f1cf82729c74c8bb0d14893`

- 1[Agent-as-a-Judge](https://thesimind.si/papers/2611.18067/)`7762eea2343bef972abfb8246ecd4adb4d18ff32a427a5941c5510f38ef2539a`
- 2[Gamer: A Generalist Vision-Language-Action Foundation Model for Long-Horizon Real-Time...](https://thesimind.si/papers/2611.18397/)`f4d3c552da2c5940bc40a4d7a8995702d673e4e7a34aad785d9a687b4148a63a`
- 3[SceneAgent: A Multi-Agent Framework for Portable Game Scene Generation](https://thesimind.si/papers/2611.17821/)`dc6a156807ed9215e9999283abf43770e1387997e806a1381ee3a7b51365cc01`
- 4[ARCHER: From Rationale Imitation to Executable Reasoning in Small Language Models](https://thesimind.si/papers/2611.18494/)`f6717e7aa1609d6cf8e88326d9eefff87222dbbf6fb4334a8ba6b707151cb402`
- 5[Can Mechanistic Interpretability Help Explain LLM Agent Failures? A Case Study on Web...](https://thesimind.si/papers/2611.18514/)`e87316be6a8dad723c5a0d1fa5462c55047d6ba7b84c3a1a2ae820939139fc11`
- 6[VLAN: Vision-Language Accessible Navigation](https://thesimind.si/papers/2611.18346/)`280608e99e68ac2064840836ce3837228f96076006461044f9f10b79b7a90ed0`
- 7[JFinBench: A Continuously Refreshable Japanese Financial Benchmark from the Latest...](https://thesimind.si/papers/2611.18130/)`c52346836908fd35873c593c2d5f3a042718e37f09641b7f4daa2bf22991e23b`
- 8[A Generalizable Approach to Safety-Aware Robotic Behavior Planning with an Explicit...](https://thesimind.si/papers/2611.18026/)`243322fba08442d76f8c838a4bae525945c6e58ca2c4f17571feab708e7ce210`
- 9[Training Reasoning Models in Simulation to Natively Use Real Robots](https://thesimind.si/papers/2611.18562/)`b011e1c63da741a2fa12b538a63b55812f65dcc547a5b3504e06f35a40091352`
- 10[Adversarially Attacking Symbolic Vocabulary Vulnerabilities In LLM Planners](https://thesimind.si/papers/2611.17910/)`ed215946ce11fcfda6fb69c16386db236c987f0435e880a6be82e4689f40e099`
- 11[From Bytes to Behavior: Request-Level Attribution from Live GPU Hidden States](https://thesimind.si/papers/2611.18272/)`5fd94db7b5a84fd9821391e65077494dad64313faee1d13c8705e21a60110211`
- 12[ParetoM³: Learning on the Pareto Set under Preference Guidance via Min-Max-Min...](https://thesimind.si/papers/2611.18252/)`5f39147b224d23c76115183c9cca2bef3db3f94527cf1ffcd8a24ec6915f5cc6`

[Check any line on Verify a thought](https://thesimind.si/proof-of-mind/)

[Nov 16, 2026](https://thesimind.si/papers/day/2026-11-16/) · [The Paper Desk](https://thesimind.si/papers/) · [Nov 18, 2026](https://thesimind.si/papers/day/2026-11-18/)
