A Matter of TASTE: Improving Coverage and Difficulty of Agent Benchmarks

TASTE reverses benchmark construction by evolving tool sequences to automatically generate harder, broader-coverage agent tasks that expose severe performance drops and saturation in existing benchmarks.

Tomer Keren, Nitay Calderon, Asaf Yehudai, Yotam Perlitz and 2 more

Paris Poster Session 6, Fri, Dec 11, 2:30 PM–4:30 PM, Paris Poster Hall · Published 2026 · ▲ 74 on Hugging Face · Code ★ 4

Exact Unlearning via Quantized Sufficient Statistics

Ami Tavory, Shripad Gade, Tal Sarig, Noam Touitou and 1 more

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

Surjective Pseudo-Invertible Neural Networks

Yamit Ehrlich, Amit Arad, Nimrod Berman, Assaf Shocher

Paris Poster Session 5, Fri, Dec 11, 11:30 AM–1:30 PM, Paris Poster Hall · Published 2026

Agentic AI Design Should be Mediated to Promote Social Welfare

Omer Madmon, Moshe Tennenholtz

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

WORD: Diffusion-Based Posterior Inference for Online Goal Recognition

Almog Anschel, Sarah Keren

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

Unpaired Canonical Correlation Analysis

Nir Ben-Ari, Ronen Talmon, Uri Shaham

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

Bandits via Additive Quantized Representations

Residual Quantization maps contexts to discrete additive codes enabling nonlinear contextual bandits with strictly bounded memory, beating linear variants on 11 of 13 datasets and matching heavy retrained baselines with up to 1000x less memory.

Ami Tavory, Noam Touitou, Tal Sarig, Frank Cheng and 1 more

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

When Metropolis and Hastings Meet Bradley and Terry: Exact MCMC From Preference Voting

Pref-MH samples from judge-conditioned distributions via exact Metropolis-Hastings using only stochastic binary pairwise preferences and converges to the target with optimal acceptance rules.

Ariel Smogorghevski, Nir Rosenfeld, Yaniv Romano

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

Weisfeiler-Leman Is Incomplete on Simple Spectrum Graphs, so Canonicalize Them

For every k, k-WL fails to distinguish some non-isomorphic simple-spectrum graphs, so PRiSM provides the first complete canonicalization of their eigendecompositions to enable universal approximation.

Snir Hordan, Nadav Dym, Tim Seppelt

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

Beyond Oversquashing: Understanding Signal Propagation in GNNs Via Observables

Standard spectral GNNs exhibit poor signal propagation; Schrödinger GNNs route signals across graphs more effectively via observable-based modeling inspired by quantum mechanics.

Eden Nagar, Ya-Wei Eileen Lin, Ron Levie

Paris Poster Session 3, Thu, Dec 10, 12:30 PM–2:30 PM, Paris Poster Hall · Published 2026

Strategic PAC Learnability via Geometric Definability

Strategic classification can make VC dimension 1 problems unlearnable, but geometric definability via first-order formulas over real exponentiation preserves learnability with controlled sample complexity.

Yuval Filmus, Shay Moran, Elizaveta Nesterova, Nir Rosenfeld and 1 more

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