reward-mechanism

Tag

Cards List
#reward-mechanism

Making Every Tool Call Count: Necessary Tool-Evidence Path Rewards for Agentic Vision-Language Models

arXiv cs.AI · 2026-09-04 Cached

This paper introduces NTEP-R, a novel supervision mechanism that rewards agentic vision-language models for making necessary tool calls and extracting relevant evidence, improving efficiency and accuracy in complex queries.

0 favorites 0 likes
#reward-mechanism

Mitigating LLM sycophancy with RL-based fine-tuning: Bayesian Truth Serum approach

arXiv cs.LG · 2026-08-27 Cached

This paper proposes using Bayesian Truth Serum as a reward in reinforcement learning fine-tuning to mitigate sycophancy in large language models, showing improved accuracy and reduced answer-flip rates without labeled data.

0 favorites 0 likes
#reward-mechanism

InfoMem: Training Long-Context Memory Agents with Answer-Conditioned Information Gain

arXiv cs.AI · 2026-06-03 Cached

InfoMem introduces a reward mechanism for training chunk-wise memory agents that evaluates final-memory utility using answer-conditioned information gain, improving long-context memory-agent performance under the same RL framework.

0 favorites 0 likes
#reward-mechanism

Verifiable Rewards Beyond Math and Code: Lightweight Corpus-Grounded Process Supervision for Factual Question Answering

Hugging Face Daily Papers · 2026-05-28 Cached

CorVer is a lightweight, corpus-grounded reward mechanism that uses Wikipedia co-occurrence statistics to provide efficient sentence-level feedback for reinforcement learning in factual question answering, outperforming neural verifiers while training 4.8 to 8.4x faster.

0 favorites 0 likes
#reward-mechanism

Geo-Align: Video Generation Alignment via Metric Geometry Reward

Hugging Face Daily Papers · 2026-05-22 Cached

Geo-Align presents a reinforcement learning framework for camera-controlled video re-rendering that improves generalization through scale-aware perceptual rewards and metric 3D estimation for camera trajectory extraction.

0 favorites 0 likes
← Back to home

Submit Feedback