ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory

ReasoningBank distills reasoning strategies from agent successes and failures into a retrievable memory bank that improves over time, with memory-aware test-time scaling amplifying gains across web and software benchmarks.

Siru Ouyang, Yan, Jun, I-Hung Hsu, Yanfei Chen and 13 more

Published Sep 29, 2025 · 0 citations · ▲ 15 on Hugging Face

Surprises in Proper Positive-Only Learning

Shai Ben-David, Farnam Mansouri, Anay Mehrotra, Manolis Zampetakis

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Nearly Optimal Attention Coresets

Alexandr Andoni, Eldar Kleiner, Edo Liberty

Atlanta Poster Session 6, Fri, Dec 11, 4:30 PM–7:30 PM, Hall C1 · Published 2026

Make Each Token Count: Towards Improving Long-Context Performance with KV Cache Eviction

Ngoc Bui, Trung Hieu Nguyen, Arman Cohan, Rex Ying

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · Code ★ 21

Reasoning with Sampling: Cutting at Decision Points

Felix Zhou, Anay Mehrotra, Quanquan C Liu

Atlanta Poster Session 3, Thu, Dec 10, 10:00 AM–1:00 PM, Hall C1 · Published 2026

Programmatic Reasoning with Structural Schema: A Unified Framework for Multi-Table Inference

Jialin Chen, Brandon Mayer, Michael Galkin, Sami Abu-El-Haija and 2 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Bounds on Extrapolation across Phase Transitions with Generalized Regression

Jeffrey Wei, Manolis Zampetakis, John Sous

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Reading Positional Coupling in Transformers with Diffusion Scores

Savik Kinger, Johannes Bertram, Luciano Dyballa, Andy Keller and 1 more

Atlanta Poster Session 4, Thu, Dec 10, 4:30 PM–7:30 PM, Hall C1 · Published 2026

Extending 3D Reconstruction Models to Any Camera

Ruxiao Duan, Yunwen (Verse) Zhou, Erin Hong, Dongxu Zhao and 3 more

Atlanta Poster Session 6, Fri, Dec 11, 4:30 PM–7:30 PM, Hall C1 · Published 2026

Geometry is an Operator: Lie-Algebraic Space Routing for View-Robust 3D MLLMs

Jingjun Yi, Chen Hu, Qi Bi, Hao Zheng and 6 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Pareto Preference Optimization for Structure- and Stability-Aware RNA Inverse Folding

Minghao Sun, Hanqun Cao, Zhou Zhang, Chen Wei and 9 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Static-Dynamic Disentanglement for Efficient Multi-Frame Vision-Language-Action Models

Weikang Qiu, Huashuo Lei, Tinglin Huang, Aosong Feng and 1 more

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

Youdunit: Single-Call Counterfactual Necessity in Multi-Agent LLM Systems

Marissa Li, Stephanie Gao, Kenny Guo, Xingjian Li and 2 more

Atlanta Poster Session 6, Fri, Dec 11, 4:30 PM–7:30 PM, Hall C1 · Published 2026

Demystifying Classifier-Free Guidance for Auto-Regressive Image Generation

Zhiling Zhou, Jiachun Pan, Fengzhuo Zhang, Dirk Bergemann and 1 more

Atlanta Poster Session 4, Thu, Dec 10, 4:30 PM–7:30 PM, Hall C1 · Published 2026

Rethinking "RL Generalizes, SFT Memorizes": The Role of SFT Data

Yunlong Hou, Fengzhuo Zhang, Yuan Cheng, Jiachun Pan and 2 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Agnostic Online Learning with Reliable Abstention

Omar Montasser

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

OTel: Open Telco AI Datasets, Benchmarks, and Models

Farbod Tavakkoli, Gregory Diamos, Kenneth Church, David Kanter and 14 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Learning Interpretable Switching Dynamics in Shared Neural-Behavioral Latent Space

Yongxu Zhang, Josue Ortega Caro, Rachel L Oren, Michael J Higley and 3 more

Atlanta Poster Session 6, Fri, Dec 11, 4:30 PM–7:30 PM, Hall C1 · Published 2026

Revisiting The Power of Closed-Form: Robust Deep Image Prototype Discovery via Scale Mixtures

Zhikang Xu, Jiarui Xing, Jian Wang

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Busemannformer: Horospherical Self-Attention for Hyperbolic Graph Transformers

Youheng Yao, Ziyao Zeng, Wenbo Liao, Tianqi Wang

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Long-Term Risks of Risk-Based Allocation

Jivat Neet Kaur, Jane Lee, Manolis Zampetakis

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

SP$^2$ec: Adaptive Self-Speculative Decoding for Vision-Language Models

Yuqi Huang, Xingyao Li, Yunlong Hou, Fengzhuo Zhang and 2 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Characterizing Underrepresentation in Generalizing Causal Survival Estimates

Bolun Liu, Sean McGrath, Yiren Hou, Elizabeth Stuart and 1 more

Atlanta Poster Session 5, Fri, Dec 11, 10:00 AM–1:00 PM, Hall C1 · Published 2026

Class-Domain Incremental Learning with Extensible Multi-Center Modeling

Xuetong Yang, Yuxiang Yan, Zhiyuan Zhou, Xin Gao and 2 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Agent-Native Research Artifacts

Jiachen Liu, Jiaxin Pei, Jintao Huang, Chenglei Si and 33 more

Atlanta Poster Session 6, Fri, Dec 11, 4:30 PM–7:30 PM, Hall C1 · Published 2026

sMMC-22M: A Context-Aware Dataset and Benchmark for Single-Cell Spatial Transcriptomics

Xi Li, Yaqi Hu, Ziheng Duan, Xinyi Wang and 4 more

Atlanta Poster Session 4, Thu, Dec 10, 4:30 PM–7:30 PM, Hall C1 · Published 2026

Accelerated last-iterate convergence of Extragradient via power-law stepsizes

Yue Wu, Weiqiang Zheng, Yang Cai, Haipeng Luo

Atlanta Poster Session 1, Wed, Dec 9, 10:00 AM–1:00 PM, Hall C1 · Published 2026

PhyTS: A Benchmark for Scientific Time Series

Benedict Armstrong, Jeroen Audenaert, Hannah P Binney, Alice Cheng and 22 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

BrainTRACE: Tracing Longitudinal, Multimodal, and Volumetric Evidence in Brain MRI Clinical Reasoning

Qizhen Lan, Mengchen Fan, Hang Zhang, Jingwei Duan and 4 more

Atlanta Poster Session 3, Thu, Dec 10, 10:00 AM–1:00 PM, Hall C1 · Published 2026

DrugSAGE: Self-evolving Agent Experience for Efficient State-of-the-Art Drug Discovery

Yikun Zhang, Xiwei Cheng, Tianyu Liu, Yuanqi Du and 1 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Why Muon Outperforms Adam: A Curvature Perspective

Muon achieves larger one-step loss decreases than Adam via lower curvature penalties driven by reduced normalized directional sharpness rather than update scale, with advantages amplified by data imbalance and within-layer curvature.

Shuche Wang, Fengzhuo Zhang, Jiaxiang Li, Dirk Bergemann and 1 more

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

Understanding Private Evolution as Learning-Augmented Clustering

Private Evolution is recast as learning-augmented clustering to derive tighter bounds via generative models and propose a geometry-aware variant with convergence guarantees.

Audra McMillan, Kunal Talwar, Felix Zhou

Atlanta Poster Session 1, Wed, Dec 9, 10:00 AM–1:00 PM, Hall C1 · Published 2026

Pushing Biomolecular Utility-Diversity Frontiers with Supergroup Relative Policy Optimization

SGRPO directly rewards set-level diversity via leave-one-out contributions in a flexible GRPO framework, expanding the utility-diversity Pareto frontier across biomolecular design tasks.

Xinwu Ye, He CAO, Li Hao, Bin Feng and 4 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 1 on Hugging Face · Code ★ 3

Test-Time Defense Against Adversarial Attacks via Stochastic Resonance of Latent Ensembles

A training-free test-time defense uses stochastic resonance of latent ensembles via input translations to recover up to 68.1% of adversarial accuracy loss on classification and dense prediction tasks.

DONG LAO, Yuxiang Zhang, Haniyeh E Oskouie, Yangchao Wu and 2 more

Atlanta Poster Session 1, Wed, Dec 9, 10:00 AM–1:00 PM, Hall C1 · Published 2026

When Riemann flows with Wasserstein: Generative Modeling of Probability Distributions on Manifolds

RWEFM generatively models meta-distributions on manifolds via Riemannian Wasserstein flow matching, yielding valid flows and efficient GPU-optimal transport approximations for non-Euclidean data.

Doron Haviv, Edward De Brouwer, Rishabh Anand, Rex Ying and 2 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Decoupled Descent: Exact Test Error Tracking Via Approximate Message Passing

Decoupled descent cancels data-reuse biases via approximate message passing so training error tracks test error, enabling zero-cost validation and shrinking the generalization gap versus gradient descent.

Max Lovig

Atlanta Poster Session 3, Thu, Dec 10, 10:00 AM–1:00 PM, Hall C1 · Published 2026

INFUSER: Influence-Guided Self-Evolution Improves Reasoning

INFUSER co-evolves a question generator and solver via influence-guided rewards, improving reasoning by over 20% on math benchmarks without curated data.

Siyu Chen, Miao Lu, Beining Wu, Heejune Sheen and 6 more

Atlanta Poster Session 4, Thu, Dec 10, 4:30 PM–7:30 PM, Hall C1 · Published 2026

WorldMemArena: Evaluating Multimodal Agent Memory Through Action–World Interaction

WorldMemArena evaluates multimodal agent memory through an action-world loop, showing writing and storage improvements do not guarantee performance and harness-based memory remains costly and unreliable.

Chengzhi Liu, Yuzhe YANG, Sophia Xiao Pu, Yepeng Liu and 15 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 13 on Hugging Face · Code ★ 29

Path Dependence under Adaptive AI Delegation

Adaptive AI delegation couples error-driven skill decay with performance-driven reliance, producing path-dependent bistability where stronger AI can enlarge the low-skill basin and cause long-run performance below no-AI baselines.

Lingxiao Huang, Nisheeth K. Vishnoi

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

PieArena: Ranking and Profiling Language Agents in Realistic Negotiation Scenarios

PieArena benchmarks LLM negotiation via multi-agent MBA scenarios, ranking agents with order-invariant payoffs and finding GPT-5 matches trained human baselines while profiling cross-model behavioral heterogeneity.

Chris Zhu, Sasha Cui, Will S Dufallo, Runzhi Jin and 3 more

Paris Poster Session 6, Fri, Dec 11, 2:30 PM–4:30 PM, Paris Poster Hall · Published 2026

Rank Is Not Capacity: Spectral Occupancy for Latent Graph Models

Spectra replaces fixed latent rank with a train-time controllable effective-rank coordinate via trace-normalized spectral prefixes, making model capacity a fitted property rather than a hyperparameter.

Nikolaos Nakis, Panagiotis Promponas, Konstantinos Tsirkas, Katerina Mamali and 3 more

Atlanta Poster Session 4, Thu, Dec 10, 4:30 PM–7:30 PM, Hall C1 · Published 2026

MITO: A Millimeter-Wave Dataset and Simulator for Non-Line-of-Sight Perception

MITO introduces millimeter-wave dataset with synthetic aperture imaging and simulator for non-line-of-sight object segmentation and classification.

Tara Boroushaki, Laura Dodds, Cusuh Ham, Fadel Adib

Atlanta Poster Session 1, Wed, Dec 9, 10:00 AM–1:00 PM, Hall C1 · Published 2026

Spatial-IQ: Deconstructing Spatial Intelligence via Hierarchical Capability Tests

Spatial-IQ hierarchically decomposes spatial reasoning into perceptual and cognitive sub-tasks, showing models use shortcuts and that hierarchical chain-of-thought training improves consistency and accuracy.

Patrick Rim, Tom Long, Ekta Prashnani, Ruth Rosenholtz and 5 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Memory Inception: Latent-Space KV Cache Manipulation for Steering LLMs

Memory Inception steers LLMs by inserting text-derived KV banks at selected layers, improving control with up to 118× less storage than prompting.

Zeyi (Andy) Liu, Michael Zhang, Ilana Greenberg, Adam Alnasser and 2 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Learning How to Cube

A neuro-symbolic framework trains a 4B-parameter model via MCTS-curated preference data and two-stage post-training to learn SAT cubing heuristics matching top symbolic methods.

Ferhat Erata, Sam Kouteili, Thanos Typaldos, Timos Antonopoulos and 3 more

Atlanta Poster Session 3, Thu, Dec 10, 10:00 AM–1:00 PM, Hall C1 · Published 2026

Generate in Reconstruction Space, Match in Semantic Space: Transport Geometry for One-Step Generation

Matching in self-supervised feature spaces improves one-step generation via compact geometry, reducing ImageNet FID by 39x and revealing metric hacking risks.

Hugues Van Assel, Edward De Brouwer, Saeed Saremi, Gabriele Scalia and 1 more

Paris Poster Session 4, Thu, Dec 10, 5:30 PM–7:30 PM, Paris Poster Hall · Published 2026

Benchmark for Assessing Olfactory Perception of Large Language Models

The Olfactory Perception benchmark evaluates LLM smell reasoning across 1,010 questions, finding compound names outperform molecular structures and best accuracy reaches 64.4%.

Eftychia Makri, Nikolaos Nakis, Laura Sisson, Geetanjali Minsky and 3 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Controllable Generative Sandbox for Causal Inference

CausalMix couples mixture Gaussian latent priors with type-specific decoders to generate realistic mixed-type tabular data with explicit, independent control over overlap, confounding, and treatment effect heterogeneity.

Qi Zhang, Harsh Parikh, Ashley I Naimi, Razieh Nabi and 2 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

URSA: Chemistry-Aware Benchmark for Utilitarian Retrosynthesis Assessment

URSA benchmarks retrosynthesis via chemistry-aware formal and plausibility metrics, finding specialized models outperform LLMs at reliable synthesis planning.

Bogdan Zagribelnyy, Ivan Ilin, Nikita Bondarev, Anton Morgunov and 6 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 1 on Hugging Face

From Retrieval to Reasoning: Agentic Mechanism Prediction from Cell Painting Profiles

PhenoAIR reformulates Cell Painting mechanism prediction as calibrated evidence reasoning via multi-agent evaluation of noisy retrieved neighbors, outperforming matching and LLM baselines across open-world settings.

Jiayuan Chen, Botao Yu, Tianyu Liu, Thai-Hoang Pham and 2 more

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

Pointwise Lipschitz Continuous Graph Algorithms

This paper proposes a linear programming-based minimum s-t cut algorithm with an optimal Lipschitz constant, yielding the first dynamic algorithm with non-trivial recourse and improved b-matching stability.

Quanquan C Liu, Grigoris Velegkas, Yuichi Yoshida, Felix Zhou

Atlanta Poster Session 4, Thu, Dec 10, 4:30 PM–7:30 PM, Hall C1 · Published 2026

FLUX: Geometry-Aware Longitudinal Flow Matching with Mixture of Experts

FLUX uses geometry-aware flow matching with mixture-of-experts to reconstruct longitudinal transport and discover latent regimes from unpaired biological snapshots.

Josue Ortega Caro, Yongxu Zhang, Hannah M Batchelor, Sizhuang He and 2 more

Atlanta Poster Session 1, Wed, Dec 9, 10:00 AM–1:00 PM, Hall C1 · Published 2026

RuleSmith: Multi-Agent LLMs for Automated Game Balancing

RuleSmith uses multi-agent LLM self-play and Bayesian optimization to automatically balance complex games and find highly balanced rule configurations.

Ziyao Zeng, Hao Wang, Chen Liu, Youheng Yao and 10 more

Atlanta Poster Session 6, Fri, Dec 11, 4:30 PM–7:30 PM, Hall C1 · Published 2026

Hyper Input Convex Neural Networks for Shape Constrained Learning and Optimal Transport

HyCNNs combine Maxout and ICNN principles to learn convex functions with exponentially fewer parameters than ICNNs, outperforming baselines in convex regression and optimal transport.

Shayan Hundrieser, Insung Kong, Johannes Schmidt-Hieber

Atlanta Poster Session 4, Thu, Dec 10, 4:30 PM–7:30 PM, Hall C1 · Published 2026

BioBlobs: Unsupervised Discovery of Functional Substructures for Protein Function Prediction

BioBlobs is an encoder-agnostic framework that compresses proteins into cohesive substructures to predict function and unsupervisedly discovers functional sites like catalytic triads. It matches baselines using only a small residue fraction, recovers experimentally annotated catalytic sites, and sca

Xin(Allen) Wang, Kaiwen Shi, Carlos Oliver

Atlanta Poster Session 1, Wed, Dec 9, 10:00 AM–1:00 PM, Hall C1 · Published 2026