collaborators

10 papers

cs.LG2026

ICR-RL: Deep Reinforcement Learning via In-Context Regression

David Schiff, Ofir Lindenbaum, Yonathan Efroni

Recent advancements in machine learning have largely been driven by foundation models (FMs) trained on large, diverse datasets, enabling them to generalize effectively to new, rela…

cs.GT2026

Neural Parameter Calibration for Finite-State Mean Field Games

Anna C. M. Thöni, Grégoire Lambrecht, Gökçe Dayanıklı +3

Mean field games efficiently approximate a very large population of strategic agents. While these games can aid the understanding of complex systems, their deployment in real-world…

cs.AI2026

Structure Enables Effective Self-Localization of Errors in LLMs

Ankur Samanta, Akshayaa Magesh, Ayush Jain +8

Self-correction in language models remains elusive. In this work, we explore whether language models can explicitly localize errors in incorrect reasoning, as a path toward buildin…

cs.AI2026

Credit Assignment with Resets in Language Model Reasoning

Ankur Samanta, Akshayaa Magesh, Ayush Jain +7

Contemporary reinforcement learning with verifiable reward methods post-train language models on multi-step reasoning by assigning a single outcome reward uniformly across all toke…

cs.LG2026

Hack-Verifiable Environments: Towards Evaluating Reward Hacking at Scale

Amit Roth, Ankur Samanta, Matan Halevy +2

Aligning autonomous agents with human intent remains a central challenge in modern AI. A key manifestation of this challenge is reward hacking, whereby agents appear successful und…

cs.AI2026

Self-Improvement of Language Models by Post-Training on Multi-Agent Debate

Ankur Samanta, Akshayaa Magesh, Runzhe Wu +7

Self-improvement, where models improve beyond their current performance without external supervision, remains a challenge. The core difficulty is sourcing a training signal stronge…