InterEvolve evolves reward programs at test time via an LLM agent and numerical optimizer to compose a humanoid controller's skills for novel loco-manipulation tasks. The approach releases latent controller competence through object-aware forward-backward models, generating novel strategies that tra

Zhuo Lin, Sirui Xu, Liuyu Bian, Yu-Xiong Wang and 1 more

Published Oct 1, 2026 · 0 citations · ▲ 61 on Hugging Face

– ReadersNo votes yet

11/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

80%Must read

?Must readVote to see the score

arXivWeb & GUI agents

AutoGUIWorld: Image Generators as Visual World Models for GUI Agent

AutoGUIWorld uses image generators to synthesize GUI interaction trajectories without running software, improving OSWorld scores to 40.8% and ScienceBoard success to 32.2%.

Cheng Yang, Yifan Wu, Yutao Huang, Zhaohua Zhang and 17 more

Published Oct 1, 2026 · 0 citations · ▲ 61 on Hugging Face · Code ★ 9

– ReadersNo votes yet

12/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

88%Must read

?Must readVote to see the score

arXivJilin LLM evaluation & benchmarks

More Choices, Fewer Decisions: Ordinal-Scale Bias in JEV-like Direct-Decision Models

Direct-decision JEV models show ordinal scale-utilization bias, compressing decisions to 26, 76% of gold support despite high accuracy, but BA-LoRA post-training improves utilization to 86%.

Tianxiang Gao, Jinzhe Li, Zhiyuan Li, Yi Chang and 1 more

Published Sep 30, 2026 · 0 citations · ▲ 60 on Hugging Face · Code ★ 3

– ReadersNo votes yet

15/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 15 of 20 reviewers recommend it

lenient 4/5

medium 8/10

strict 3/5

74%Highly rated

?Highly ratedVote to see the score

TMLR 2026Video generation

Video Generation Models: A Survey of Post-Training and Alignment

This survey reviews post-training and alignment strategies for video generation, framing them as implicit or explicit alignment across four methodological categories to improve controllability and reliability.

Chaoyu Li, Xiaoyi Gu, Yogesh Kulkarni, Eun Woo Im and 9 more

Published Sep 30, 2026 · ▲ 60 on Hugging Face · Code ★ 208

– ReadersNo votes yet

9/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 9 of 20 reviewers recommend it

lenient 5/5

medium 3/10

strict 1/5

83%Must read

?Must readVote to see the score

arXivLLM pretraining & scaling laws

Scaling and Distilling Text Embeddings for Better Diffusibility

Scaling and distilling text embeddings improves latent diffusion by yielding more connected, diffusible spaces that boost generative performance beyond autoregressive baselines.

Zekai Zhang, Yunjie Tian, Yanjin He, Xiaoyan Zhang and 3 more

Published Oct 1, 2026 · 0 citations · ▲ 57 on Hugging Face · Code ★ 3

– ReadersNo votes yet

13/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

84%Must read

?Must readVote to see the score

arXivAgent benchmarks & environments

CheckerBench: Can Long-Horizon Agents Synthesize Static-Analysis Checkers?

CheckerBench evaluates long-horizon agents on synthesizing static-analysis checkers across 300 CVE-derived tasks, finding best Pass@1 reaches 45.33%.

Hang He, Li Wang, Hao Chen, Yuchen Shao and 8 more

Published Oct 6, 2026 · ▲ 52 on Hugging Face · Code

100% Readers1 of 1 upvoted

12/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 12 of 20 reviewers recommend it

lenient 5/5

medium 5/10

strict 2/5

74%Highly rated

?Highly ratedVote to see the score

WWW 2026Seoul National Robot manipulation

Beyond the Current Scene: Event-Referential Grasping with Active View Selection

BeyondSCe enables zero-shot event-referential grasping via active view selection, achieving 76% and 77% success on visible and occluded targets versus 40% and 55% baselines.

Hyunjoon Lee, Haebeom Jung, Eunsung Cha, Daeun Lee and 3 more

Published Sep 30, 2026 · 0 citations · ▲ 51 on Hugging Face · Code ★ 8

– ReadersNo votes yet

9/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

83%Must read

?Must readVote to see the score

arXivAgent memory

Memadapter: Counterfactual Adaptation Against Memory-induced Sycophancy

MemAdapter counters memory-induced sycophancy via counterfactual induction, context-aware reflection, and evidence-based reasoning to improve memory reliability across diverse scenarios.

Ruqing Ning, Haibo Meng, Zhishang Xiang, Zerui Chen and 3 more

Published Oct 4, 2026 · ▲ 27 on Hugging Face · Code ★ 21

– ReadersNo votes yet

13/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 13 of 20 reviewers recommend it

lenient 5/5

medium 8/10

strict 0/5

83%Must read

?Must readVote to see the score

arXivVideo generation

Ego2Act: Evaluating Goal-Directed Manipulation in Egocentric Video Generation

Ego2Act evaluates egocentric video generation on multi-step goal-directed manipulation, showing models skip steps and fail at fine-grained physical dynamics.

Patrick Amadeus Irawan, Iskandar Muda Rizky Parlambang, Rava Maulana, Qinrong Cui and 9 more

Published Oct 1, 2026 · 0 citations · ▲ 32 on Hugging Face · Code ★ 3

– ReadersNo votes yet

13/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

88%Must read

?Must readVote to see the score

arXivLLM reasoning & chain of thought

Language Models that Play Chess and Explain Their Moves

Queen, a 4B-parameter chess-language model, plays at grandmaster level and explains moves via cross-attention to a silent expert encoder and iterative Bellman-style explanation distillation, surpassing larger frontier models.

Adithya Bhaskar, Jeffrey Cheng, Danqi Chen

Published Oct 2, 2026 · 0 citations · ▲ 31 on Hugging Face · Code ★ 18

– ReadersNo votes yet

15/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

80%Must read

?Must readVote to see the score

arXivVideo generation

In-Distribution Forcing for Long Video Generation at Test Time

In-Distribution Forcing prevents out-of-distribution key-value drift via self-caching to extend short video models to minute-scale generation.

Jeongwoo Shin, Youngyoon Choi, Sangwoo Jo, Hyunmog Kim and 4 more

Published Oct 2, 2026 · 0 citations · ▲ 29 on Hugging Face · Code ★ 3

– ReadersNo votes yet

12/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

78%Highly rated

?Highly ratedVote to see the score

arXivAutoregressive generation

ProAR: Learning Prospective Reasoning with Autoregressive Video Models

ProAR introduces goal-frame prediction and future self-alignment to enable goal-directed reasoning in autoregressive video models, surpassing baselines with 25% training steps.

Linghui Shen, Tinghui Zhu, Sheng Zhang, Muhao Chen

Published Oct 2, 2026 · 0 citations · ▲ 26 on Hugging Face · Code ★ 2

– ReadersNo votes yet

11/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

78%Highly rated

?Highly ratedVote to see the score

arXivInstruction tuning

Local Support Learning

Local Support Learning pairs weight adapters with GMM gating to keep updates local, resolving catastrophic forgetting in LLMs up to 7B parameters without prior data.

Assaf Ben-Kish, Akarsh Kumar, James Glass, Raja Giryes

Published Oct 1, 2026 · 0 citations · ▲ 25 on Hugging Face · Code ★ 13

– ReadersNo votes yet

11/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

89%Must read

?Must readVote to see the score

arXivAgent benchmarks & environments

LMBuild: Evaluating LLM Agents for Generating Buildable and Functional Structures

LMBuild evaluates LLM agents on generating buildable, functional 3D structures and finds physical operability and functional affordance remain challenging despite improved soundness.

Jiateng Liu, Rushi Wang, Cheng Qian, Xuejun Zhang and 8 more

Published Oct 3, 2026 · ▲ 24 on Hugging Face · Code ★ 1

– ReadersNo votes yet

16/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 16 of 20 reviewers recommend it

lenient 5/5

medium 9/10

strict 2/5

84%Must read

?Must readVote to see the score

arXiv3D vision & reconstruction

4DCodeBench: Benchmarking Agents on Inverse Graphics of Dynamic Scenes

4DCodeBench benchmarks agents reconstructing dynamic scenes from video as executable graphics code, finding strong static models fail at complex dynamics.

Ruihong Shen, Žiga Kovačič, Peter Kulits, Xingrui Wang and 5 more

Published Oct 2, 2026 · 0 citations · ▲ 23 on Hugging Face · Code ★ 67

100% Readers1 of 1 upvoted

12/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

88%Must read

?Must readVote to see the score

arXivRL for LLMs

MetaRubric: Learning to Reward for Rubric-Based Reinforcement Learning

MetaRubric fixes vacuous rubric credit via evidence-aware optimization and counterfactual rubric adaptation, improving PubMedQA accuracy by up to 20.40 points over static-judge GRPO.

Yuxuan Fan, Jaehong Yoon

Published Oct 2, 2026 · 0 citations · ▲ 22 on Hugging Face · Code ★ 2

– ReadersNo votes yet

15/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

83%Must read

?Must readVote to see the score

arXivCode generation

FrugalEvo: Towards Cost-Aware LLM-Guided Program Evolution

FrugalEvo pairs expensive LLM strategy exploration with cheap LLM implementation and caching to maximize optimization gain per cost under a budget, outperforming baselines on 10 tasks at significantly lower expense.

Hui Chen, Xuan Qi, James Zhao, Zhaopeng Feng and 4 more

Published Oct 2, 2026 · 0 citations · ▲ 22 on Hugging Face · Code ★ 5

– ReadersNo votes yet

13/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

78%Highly rated

?Highly ratedVote to see the score

arXivLLM agents & planning

EVISKILL: Grounding Skill Evolution in Replayable Evidence

EVISKILL grounds LLM skill evolution in replayable evidence cards linking edits to supporting contexts, using targeted replay for verification and global validation for incorporation.

Yan Zhou, Yili Wang, Yiwei Dai, Qinggang Zhang and 1 more

Published Oct 4, 2026 · ▲ 11 on Hugging Face · Code ★ 8

100% Readers1 of 1 upvoted

9/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 9 of 20 reviewers recommend it

lenient 4/5

medium 4/10

strict 1/5

76%Highly rated

?Highly ratedVote to see the score

arXivTest-time compute

Learning to Predict Distributions over Weight Updates for Test-Time Adaptation

Query-conditioned hypernetworks predict distributions over LoRA weight updates from input queries, enabling test-time scaling via sampled adapted models that outperform deterministic and token-sampling baselines.

Azal Ahmad Khan, Keshav Ramji, Tahira Naseem, Ali Anwar and 1 more

Published Oct 1, 2026 · 0 citations

– ReadersNo votes yet

10/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

82%Must read

?Must readVote to see the score

NeurIPS 2026Distribution shift & OOD detection

Optimal Transport Reweighting for Robust Learning under Spurious Correlations and Label Noise

POTER uses optimal transport geometry between training and reference distributions to downweight mislabeled or shortcut-aligned samples, achieving state-of-the-art worst-group accuracy with a single training stage.

Sung Ho Jo, Seonghwi Kim, Wonsang Yun, Minwoo Chae

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published Oct 1, 2026 · 0 citations

100% Readers1 of 1 upvoted

11/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

73%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026Representation & contrastive learning

Structure-agnostic Causal Representation Learning

SaCRL jointly identifies causal structure and learns invariant representations via soft optimization over HSIC-based invariance violations without prior structural knowledge. It guarantees structure identification, invariance satisfaction, and out-of-distribution generalization while achieving state

Arman Behnam, Binghui Wang

Atlanta Poster Session 2, Wed, Dec 9, 4:30 PM–7:30 PM, Hall C1 · Published Oct 1, 2026 · 0 citations

0% Readers0 of 1 upvoted

15/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

72%Highly rated

?Highly ratedVote to see the score

arXivSingapore University of Technolo Zhejiang Music

Diptych: Scoped, AI-Interpreted Comparison for Reference Listening in Music Production

Diptych lets musicians define comparison scopes for reference listening, helping surface differences experts partially support while avoiding overreaching AI judgments.

Chongjun Zhong, Abhinaba Roy, Archishman Ghosh, Kejun Zhang and 1 more

Published Sep 30, 2026 · 0 citations · ▲ 20 on Hugging Face

– ReadersNo votes yet

8/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 8 of 20 reviewers recommend it

lenient 3/5

medium 4/10

strict 1/5

90%Must read

?Must readVote to see the score

arXivTool use & function calling

From Evidence to Action: How Tool-Using Agents Fail

Tool-using agents often fail by acting before establishing required evidence or leaving multi-action workflow prerequisites unresolved, despite accurate static action assessment. SafeActBench reveals failures stem from how agents use established evidence during execution, not just missing informatio

Hongzhan Lin, Shidong Cao, Ziyang Luo, Wenhao Chai and 2 more

Published Oct 6, 2026 · ▲ 20 on Hugging Face · Code ★ 3

100% Readers1 of 1 upvoted

15/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 15 of 20 reviewers recommend it

lenient 5/5

medium 7/10

strict 3/5

90%Must read

?Must readVote to see the score

arXivRobot manipulation

World Action Learning via Interaction-Centric Spectral Latent Guidance

WING distills interaction-centric latent actions from egocentric video and uses cross-embodiment spectral low-frequency guidance to transfer them to robot policies, achieving high success rates on LIBERO, RoboTwin, RoboCasa, and real-world tasks.

Zhiming Liu, Yikun Miao, Ying Chen, Hongrui Yin and 6 more

Published Oct 2, 2026 · 0 citations · ▲ 20 on Hugging Face

100% Readers1 of 1 upvoted

15/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

89%Must read

?Must readVote to see the score

arXivTest-time compute

Self-Generated Feedback Destabilizes Test-Time Training: A Causal Decomposition of Long-Horizon Adaptation

Self-generated feedback in long-horizon test-time training causes weight updates that improve synthetic text but degrade real-text prediction, and settlement on independent evidence prevents this failure.

Cheng Luo, Bing Li, Bernard Ghanem

Published Oct 4, 2026 · ▲ 19 on Hugging Face · Code ★ 1

– ReadersNo votes yet

16/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 16 of 20 reviewers recommend it

lenient 4/5

medium 9/10

strict 3/5

83%Must read

?Must readVote to see the score

arXivLLM pretraining & scaling laws

Towards Looped Models Done Right, Part II: Rethinking at Fixed Points

Looped language models use fixed-point convergence to enable truncated training, shared KV caches, faster prefill, and faster RL updates, while a learned depth prior and orthogonal input injection improve perplexity across scales.

Benhao Huang, Chufan Shi, Junlin Chen, Shicheng Wen and 3 more

Published Oct 5, 2026 · ▲ 17 on Hugging Face · Code ★ 30

– ReadersNo votes yet

13/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 13 of 20 reviewers recommend it

lenient 3/5

medium 8/10

strict 2/5

80%Must read

?Must readVote to see the score

arXivMultimodal reasoning

OmniReasoning: Pushing the Limits of Audio-Visual Joint Reasoning

OmniReasoning introduces a benchmark, data engine, and self-distillation method to improve audio-visual joint reasoning, boosting Qwen3-Omni-30B-A3B-Thinking by up to 12.8 points.

Junming Lin, Yuxuan Wang, Zhenxin Lei, Yuxin Liu and 10 more

Published Sep 30, 2026 · 0 citations · ▲ 17 on Hugging Face · Code ★ 1

– ReadersNo votes yet

12/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 12 of 20 reviewers recommend it

lenient 4/5

medium 8/10

strict 0/5

83%Must read

?Must readVote to see the score

arXivLLM agents & planning

ASCENT: Online Test-Time Training of Long-Horizon Agents via Self-Distillation of Verified Experience

ASCENT online test-time trains agents by self-distilling verified deployment trajectories into LoRA weights via a frozen hindsight model, improving long-horizon success and efficiency without external teachers or memory retrieval.

Haodong Lu, Dong Gong

Published Oct 4, 2026 · ▲ 17 on Hugging Face

– ReadersNo votes yet

13/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 13 of 20 reviewers recommend it

lenient 5/5

medium 8/10

strict 0/5

86%Must read

?Must readVote to see the score

arXivAgent benchmarks & environments

AutoSciBench: Autonomous Benchmark Generation for Evaluating Scientific Agents

AutoSciBench autonomously generates and iteratively adapts scientific agent benchmarks via recipes and concepts, reducing solver accuracy by over 22 points versus human benchmarks while improving quality ratings.

Dongki Kim, Namkyeong Lee, Surag Nair, Carl Edwards and 6 more

Published Oct 4, 2026 · ▲ 17 on Hugging Face

100% Readers1 of 1 upvoted

13/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 13 of 20 reviewers recommend it

lenient 5/5

medium 7/10

strict 1/5

83%Must read

?Must readVote to see the score

arXivSim-to-real

Skill2Real: Agentic Skill Learning for Zero-Shot Sim-to-Real Robot Manipulation

Skill2Real learns simulation skills via a shared robot API with a Proposer-Verifier-Governor loop, transferring frozen skill hierarchies to real robots without fine-tuning to reach 78.75% real-world manipulation success.

Xincheng He, Siyu Ma, Chang Yu, Yunuo Chen and 4 more

Published Oct 2, 2026 · 0 citations · ▲ 16 on Hugging Face

– ReadersNo votes yet

13/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

80%Must read

?Must readVote to see the score

arXivMultimodal reasoning

CANOPY: Adaptive-Granularity Evidence Compression for Multimodal RAG

CANOPY adaptively compresses multimodal evidence via hierarchical region scoring and targeted retrieval, improving QA accuracy while reducing input tokens by up to 27.7%.

Hyojeong Yun, Jueun Kim, Wook-Shin Han

Published Oct 1, 2026 · 0 citations · ▲ 16 on Hugging Face

– ReadersNo votes yet

12/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

71%Highly rated

?Highly ratedVote to see the score

arXivAlignment & preference optimization

Representation-Space MMD for Diffusion Language Models

Post-training minimizes representation-space MMD between diffusion language model outputs and references via retained token features, improving perplexity, accuracy, and parallel decoding.

Ilya Drobyshevskiy, Ilia Sudakov, Maksim Semenov, Denis Kuznedelev and 6 more

Published Oct 5, 2026 · ▲ 16 on Hugging Face · Code ★ 10

– ReadersNo votes yet

7/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 7 of 20 reviewers recommend it

lenient 3/5

medium 3/10

strict 1/5

83%Must read

?Must readVote to see the score

arXivLLM pretraining & scaling laws

Looping Beyond Twice: A Scalable Recipe for Looped Mixture-of-Experts

LOOM stabilizes looped MoE via bounded residual updates and per-loop routers to scale loops to 9, 12, cutting perplexity from 9.62 to 7.77.

Di He, Pengxiang Li, Da Chang, Qingyan Meng and 2 more

Published Oct 1, 2026 · 0 citations · ▲ 16 on Hugging Face · Code ★ 8

– ReadersNo votes yet

13/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

88%Must read

?Must readVote to see the score

arXivU Notre Dame Vision-language-action models

Learning from Runtime Feedback through Failure-Bank Self-Evolution for Vision-Language-Action Models

FailBank turns runtime shield feedback into persistent VLA policy updates via failure-bank self-evolution, raising success rates up to 25.4 points and cutting policy-induced cost up to 35.6%.

Mingyue Cui, Zheyuan Liu, Yihan Zhu, Zheyuan Zhang and 1 more

Published Sep 30, 2026 · 0 citations · ▲ 15 on Hugging Face · Code ★ 2

– ReadersNo votes yet

15/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 15 of 20 reviewers recommend it

lenient 5/5

medium 8/10

strict 2/5

91%Must read

ICML 2026Alignment & preference optimization

HuatuoGPT-3: RL-Only Domain Adaptation from Base Models

OnePO enables RL-only medical domain adaptation via adaptive objective evolution and teacher retirement, yielding HuatuoGPT-3 that surpasses frontier models.

Junying Chen, Xinyuan Xie, Ziniu Li, Wenyuan Gu and 6 more

Published Oct 5, 2026 · ▲ 15 on Hugging Face · Code ★ 12

100% Readers1 of 1 upvoted

16/20 AI panelreviewers recommend it

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 16 of 20 reviewers recommend it

lenient 5/5

medium 10/10

strict 1/5

86%Must read

?Must readVote to see the score

arXivRetrieval-augmented generation

UNREAL: Unifying Retrieval and Long-Context with a Single Model

UNREAL unifies retrieval and long-context evidence selection via frozen LLM representations with minimal parameters, outperforming state-of-the-art retrievers and improving long-context accuracy substantially.

Edan Kinderman, Elad Hoffer, Yochai Blau, Brian Chmiel and 3 more

Published Oct 6, 2026 · ▲ 15 on Hugging Face

– ReadersNo votes yet

14/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 14 of 20 reviewers recommend it

lenient 4/5

medium 7/10

strict 3/5

80%Must read

?Must readVote to see the score

arXivLLM agents & planning

SearchJev: A Fast and Calibrated System-1 Model for Search Agents

SearchJev is a fast calibrated System-1 model that scores search decisions directly without autoregressive generation, improving decision quality, speed, and calibration over same-size language models.

Congfeng Cao, Lipeng Zuo, Konstantinos Papakostas, Qiwei Xu and 5 more

Published Oct 4, 2026 · ▲ 14 on Hugging Face · Code ★ 4

– ReadersNo votes yet

12/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 12 of 20 reviewers recommend it

lenient 5/5

medium 6/10

strict 1/5

74%Highly rated

?Highly ratedVote to see the score

arXivFairness & bias

Collective Bias Mitigation via Model Routing and Collaboration

Collective Bias Mitigation routes queries among diverse LLMs and fosters collaboration to substantially reduce bias over single-model baselines.

Mingzhe Du, Luu Anh Tuan, Xiaobao Wu, Yichong Huang and 6 more

Published Oct 2, 2026 · 0 citations · ▲ 14 on Hugging Face

– ReadersNo votes yet

9/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

88%Must read

?Must readVote to see the score

arXivFairness & bias

Noise Out, Bias In: Targeted Bias Injection in Diffusion Language Models via Closed-Loop Activation Steering

Targeted bias injection via closed-loop activation steering exploits diffusion language model denoising trajectories to steer frozen models toward adversarial demographic answers with minimal corruption.

Sarim Hashmi, Mukul Ranjan, Abdelrahman Elsayed, Muhammad Umer Sheikh and 2 more

Published Oct 5, 2026 · ▲ 14 on Hugging Face · Code ★ 3

– ReadersNo votes yet

15/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 15 of 20 reviewers recommend it

lenient 5/5

medium 9/10

strict 1/5

83%Must read

?Must readVote to see the score

arXivAgent benchmarks & environments

World Editing: Intervening on Executable Worlds at Increasing Depth

World editing intervenes on executable environments at increasing depth via IGMWorld and IGMBench, where top agents achieve 78.2% task success with reliability declining by depth.

Max Ku, Nok-Kan Law, Yu-Chien Tang, Shih-Ying Yeh and 14 more

Published Oct 1, 2026 · ▲ 14 on Hugging Face · Code

– ReadersNo votes yet

13/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 13 of 20 reviewers recommend it

lenient 5/5

medium 5/10

strict 3/5

76%Highly rated

?Highly ratedVote to see the score

arXivRobot manipulation

RobotUse: Allocating Computation, Context, and Decisions

RobotUse organizes robot computation, context, and decisions around revisable physical actions via visual target selection and persistent playbooks, achieving 45% RoboLab success and real-world learning.

Junhoo Lee, Injun Baek, Seungyeon Kim, Suhyun Jeon and 3 more

Published Oct 4, 2026 · ▲ 14 on Hugging Face · Code ★ 4

– ReadersNo votes yet

10/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 10 of 20 reviewers recommend it

lenient 4/5

medium 5/10

strict 1/5

71%Highly rated

?Highly ratedVote to see the score

arXivRL for LLMs

From Gradients to Capabilities: Understanding Multi-Teacher On-Policy Distillation

Multi-teacher on-policy distillation integrates RL teacher gradients via loss averaging, Adam smoothing, and BF16 rounding, with averaging rules significantly altering math accuracy outcomes.

Siqi Zhu, Suozhi Huang, Kaixuan Zhang, Yuheng Yang and 3 more

Published Oct 1, 2026 · 0 citations · ▲ 13 on Hugging Face

– ReadersNo votes yet

7/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

80%Must read

?Must readVote to see the score

arXivU Illinois Urbana-Champaign U Michigan Nvidia Nvidia AI oversight & deception

Covert Assistance: Helpful LLM Agents Evade Oversight in Multi-Agent Systems

Benign multi-agent LLM planners disguise secrets to help developers evade oversight, with rare per-episode leaks compounding to high breach risk across repeated exchanges.

Deema Alnuhait, Gengyu Wang, Muhammad Khalifa, Hao Peng

Published Sep 30, 2026 · 0 citations · ▲ 13 on Hugging Face

– ReadersNo votes yet

12/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 12 of 20 reviewers recommend it

lenient 5/5

medium 6/10

strict 1/5

89%Must read

arXivUncertainty & calibration

Certification of Real Images through Calibrated Content Authentication

Deepfake detectors degrade to 76% accuracy and near-zero under attacks, so calibrated reconstruction-based authentication bounds false real-image certification to 1%.

Sarim Hashmi, Abdelrahman Elsayed, Mohammed Talha Alam, Samuele Poppi and 1 more

Published Oct 5, 2026 · ▲ 13 on Hugging Face · Code ★ 2

– ReadersNo votes yet

16/20 AI panelreviewers recommend it

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 16 of 20 reviewers recommend it

lenient 5/5

medium 9/10

strict 2/5

76%Highly rated

?Highly ratedVote to see the score

arXivTime series forecasting

SEER: Self-Evolving Event Reasoning and Retrieval for Time Series Forecasting

SEER uses self-evolving event reasoning and retrieval to dynamically optimize forecasting with exogenous events via reflective memory and causal knowledge, outperforming state-of-the-art baselines.

Mingtian Tan, Palash Goyal, Mihir Parmar, Sarkar Snigdha Sarathi Das and 5 more

Published Oct 2, 2026 · ▲ 13 on Hugging Face · Code

– ReadersNo votes yet

10/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 10 of 20 reviewers recommend it

lenient 5/5

medium 5/10

strict 0/5

80%Must read

?Must readVote to see the score

arXivLLM reasoning & chain of thought

Efficient Reasoning Training Does Not Always Harm CoT Faithfulness and Monitorability

Efficient reasoning training differs in impact: faithfulness usually drops due to inconsistency, but monitorability remains robust.

Samuel Lewis-Lim, Xingwei Tan, Mario Sänger, Zhixue Zhao and 1 more

Published Oct 2, 2026 · 0 citations · ▲ 13 on Hugging Face

– ReadersNo votes yet

12/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

83%Must read

arXivVision-language-action models

PerturBot: Breaking Shortcut Priors in Vision-Language-Action Models with Perturbative Training

PerturbBot breaks vision-language-action shortcut priors via perturbative training while GroundingFscore diagnoses shortcut reliance, enabling healthier scaling without altering inference.

Mingyu Liu, Chonghao Sima, Tianjian Feng, Hanqing Wang and 3 more

Published Oct 3, 2026 · ▲ 13 on Hugging Face · Code ★ 6

– ReadersNo votes yet

13/20 AI panelreviewers recommend it

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 13 of 20 reviewers recommend it

lenient 5/5

medium 7/10

strict 1/5

88%Must read

?Must readVote to see the score

arXivVision-language-action models

When to Switch: Reliable Action-Chunk Extension for Vision-Language-Action Models

RACE predicts subskill transition timing to extend VLA action chunks reliably, reducing stop-and-go idle time ~5x on real robots while improving success rates.

Seonghoon Yu, Dongwon Kim, HyungRok Jung, Yoonjae Baek and 3 more

Published Oct 5, 2026 · ▲ 13 on Hugging Face · Code ★ 3

– ReadersNo votes yet

15/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 15 of 20 reviewers recommend it

lenient 5/5

medium 9/10

strict 1/5

91%Must read

NeurIPS 2026Video-language models

Rethinking Long-Video Efficiency: A Joint Allocation Perspective on Frames, Pixels, and Front-End Latency

LoHi trades per-frame resolution for denser temporal sampling via low-resolution streams plus sparse high-resolution frames, boosting long-video accuracy up to 10.6 points and cutting front-end latency up to 7x.

Sixun Dong, Wei Li, Andong Deng, Qi Qian and 3 more

Atlanta Poster Session 1, Wed, Dec 9, 10:00 AM–1:00 PM, Hall C1 · Published Oct 3, 2026 · ▲ 13 on Hugging Face

– ReadersNo votes yet. 1 from authors or colleagues not counted

17/20 AI panelreviewers recommend it

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 17 of 20 reviewers recommend it

lenient 4/5

medium 10/10

strict 3/5

89%Must read

?Must readVote to see the score

arXivRetrieval-augmented generation

AGO AI Quality Gate: Evidence-First Release Decisions for Retrieval-Augmented Generation

AGO is an evidence-first quality gate for RAG that treats judge errors and missing data as explicit outcomes, using stratified beta-binomial gates and mandatory meta-evaluation to reduce unsafe promotion to 22.2%-35.1% versus 29.3%-41.8% for naive gates.

Giulio Zeloni, Enrico Lo Conte, Salvatore Rionero, Giuseppe Santoro and 2 more

Published Oct 1, 2026 · 0 citations · ▲ 13 on Hugging Face

– ReadersNo votes yet

16/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

71%Highly rated

arXivVision-language-action models

RealtimeWAM: One-Step Asynchronous World Action Models

RealtimeWAM uses teacher-anchored consistency distillation and cross-expert wavefront pipelining for one-step asynchronous action generation, achieving near-lossless performance with ~25x speedup.

Chengtao Lv, Jinyang Du, Shuyi Feng, Yang Yong and 6 more

Published Oct 5, 2026 · ▲ 12 on Hugging Face · Code ★ 2,880

0% Readers0 of 1 upvoted

14/20 AI panelreviewers recommend it

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 14 of 20 reviewers recommend it

lenient 4/5

medium 9/10

strict 1/5

88%Must read

?Must readVote to see the score

WWW 2026LLM reasoning & chain of thought

Base Models Can Reason By Taking a Cue From Training Data

Fixing initial token cues in base models boosts reasoning to match RL performance, with effects traced to training data associations that can be causally edited.

Sophie L. Wang, Amil Dravid, Rulin Shao, Kevin Farhat and 2 more

Published Oct 5, 2026 · ▲ 12 on Hugging Face · Code ★ 2

– ReadersNo votes yet

15/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 15 of 20 reviewers recommend it

lenient 4/5

medium 9/10

strict 2/5

91%Must read

?Must readVote to see the score

arXivAgent benchmarks & environments

UndoBench: Separating Task Competence from Recovery Capability in Tool-Using AI Agents

UndoBench separates tool-using agent competence from fault recovery via paired enterprise workflow trials, finding 83.54% nominal success but only 46.72% recovery success with phase-dependent vulnerabilities.

Dolly Sah, Tanmay Sah, Harshul Jain, Tanya Sah

Published Oct 4, 2026 · ▲ 11 on Hugging Face · Code ★ 1

– ReadersNo votes yet

17/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 17 of 20 reviewers recommend it

lenient 5/5

medium 9/10

strict 3/5

Trending