arXiv Machine Learning July 2, 2026 By Sadanand Singh, Allam Reddy, Manan Chopra

Verifiable Rewards for Calibrated Probabilistic Forecasting

Read the original on arXiv Machine Learning →

arXiv:2607. 00164v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards can in principle train calibrated probabilistic forecasters, since a proper scoring rule such as the Brier score is computed from outcomes alone and is minimized in expectation by the true probability.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv AI

Jul 15

Critic Experience Bank: Self-Evolving Step-Level Confidence Estimation for LLM Agents

arXiv:2607. 12397v1 Announce Type: new Abstract: LLM agents act in external environments where each action changes the state that later decisions condition on, and where a single wrong step can waste interaction budget or trigger irreversible side effects long before the final failure is observed.

By Yaopei Zeng, Congchao Wang, JianHang Chen, Nan Wang, Yurui Chang, Lu Lin

llms agents benchmarks

arXiv Machine Learning

Jul 8

More Convincing, Not More Correct: Self-Play Reward Hacking of Reference-Free LLM Judges

arXiv:2607. 05904v1 Announce Type: new Abstract: Training a language model against its own reference-free judgments (the premise of self-rewarding, self-play, and LLM-as-a-judge pipelines) assumes a model's verdict on a shown answer tracks correctness.

By Chenyu Zhou

llms reinforcement-learning

arXiv AI

Jul 14

LLMs as a Jury: Cross-Model Consensus Can Outperform Process Reward Models for LLM Reasoning

arXiv:2607. 10139v1 Announce Type: cross Abstract: Selecting the correct answer from a pool of candidate reasoning chains is the engine of test-time scaling, yet the standard selectors each carry a cost: self-consistency inherits the errors of the single model it resamples, and trained reward models need labeled data and transfer poorly off-distribution.

By Ning Liu

llms benchmarks

arXiv AI

Jul 21

FIFA World Cup 2026 as a Contamination-Free Benchmark for LLM Forecasting Agents: Four Models, a Bookmaker, and 104 Matches

arXiv:2607. 17765v1 Announce Type: cross Abstract: We introduce WC2026-Agents, a benchmark and dataset for evaluating large language models (LLMs) as autonomous forecasting agents on real, future events.

By Jiacheng Ding, Cong Guo, Jason Xu

llms agents benchmarks

arXiv Machine Learning

6d ago

When Offline Evaluation Misleads: A Diagnostic Protocol for Reward and Policy Selection in Delayed-Feedback Contextual Bandits

arXiv:2608. 11560v1 Announce Type: new Abstract: Personalizing marketing messages with contextual multi-armed bandits (CMABs) drives real business value, yet the objective that ultimately matters - a downstream conversion - is observed only weeks later, too late to drive online learning.

By Sang Su Lee, Vineeth Loganathan, Shishir Dash, Vijay Raghavan

reinforcement-learning benchmarks safety

arXiv AI

Jul 7

Gradient Regularization Mitigates Reward Hacking in Reinforcement Learning from Human Feedback and Verifiable Rewards

arXiv:2602. 18037v2 Announce Type: replace-cross Abstract: Reinforcement Learning from Human Feedback (RLHF) or Verifiable Rewards (RLVR) are two key steps in the post-training of modern Language Models (LMs).

By Johannes Ackermann, Michael Noukhovitch, Takashi Ishida, Masashi Sugiyama

llms reinforcement-learning safety

Related stories

Critic Experience Bank: Self-Evolving Step-Level Confidence Estimation for LLM Agents

More Convincing, Not More Correct: Self-Play Reward Hacking of Reference-Free LLM Judges

LLMs as a Jury: Cross-Model Consensus Can Outperform Process Reward Models for LLM Reasoning

FIFA World Cup 2026 as a Contamination-Free Benchmark for LLM Forecasting Agents: Four Models, a Bookmaker, and 104 Matches

When Offline Evaluation Misleads: A Diagnostic Protocol for Reward and Policy Selection in Delayed-Feedback Contextual Bandits

Gradient Regularization Mitigates Reward Hacking in Reinforcement Learning from Human Feedback and Verifiable Rewards