Cover Image

Toward Scalable Verifiable Reward: Proxy State-Based Evaluation for Multi-turn Tool-Calling LLM Agents

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chuang, Yun-Shiuan, Kulkarni, Chaitanya, Chiu, Alec, Thangali, Avinash, Pan, Zijie, Shekhar, Shivani, Ge, Yirou, Li, Yixi, Kona, Uma, Pang, Linsey, Mehrotra, Prakhar
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Ada-RS: Adaptive Rejection Sampling for Selective Thinking
by: Ge, Yirou, et al.
Published: (2026)

NEMO-4-PAYPAL: Leveraging NVIDIA's Nemo Framework for empowering PayPal's Commerce Agent
by: Garg, Sudhanshu, et al.
Published: (2025)

Backdoor Collapse: Eliminating Unknown Threats via Known Backdoor Aggregation in Language Models
by: Lin, Liang, et al.
Published: (2025)

MCPShield: A Security Cognition Layer for Adaptive Trust Calibration in Model Context Protocol Agents
by: Zhou, Zhenhong, et al.
Published: (2026)

THE MAKING OF MODERNITY: VIOLENCE AND SOCIAL REVOLUTION IN THE SOUTH ASIAN CONTEXT
by: Prakash Kona
Published: (2018)

Calibrating Attribution Proxies for Reward Allocation in Participatory Weather Sensing
by: Ballandies, Mark C., et al.
Published: (2026)

Philosophy of Health Sciences Library Management--A Panel Discussion
by: Kona, Martha, et al.
Published: (1976)

$C^\ast$-extreme points of unital completely positive maps invariant under group action
by: Kulkarni, Chaitanya J.
Published: (2026)

Mitigating Lost in Multi-turn Conversation via Curriculum RL with Verifiable Accuracy and Abstention Rewards
by: Li, Ming, et al.
Published: (2025)

PROXIMA: A Reliability Scoring Framework for Proxy Metrics in Online Controlled Experiments
by: Amudala, Avinash
Published: (2026)

Youth Smart-City Readiness — replication package
by: Kóňa, Andrej, et al.
Published: (2026)

Bootstrapped Mixed Rewards for RL Post-Training: Injecting Canonical Action Order
by: Gupta, Prakhar, et al.
Published: (2025)

Pivoting Retail Supply Chain with Deep Generative Techniques: Taxonomy, Survey and Insights
by: Wang, Yuan, et al.
Published: (2024)

SuperdropNet: a Stable and Accurate Machine Learning Proxy for Droplet-based Cloud Microphysics
by: Sharma, Shivani, et al.
Published: (2024)

Structural Gender Bias in Credit Scoring: Proxy Leakage
by: SD, Navya, et al.
Published: (2026)

On (2,2)-decomposable genus 4 Jacobians
by: Bruin, Nils, et al.
Published: (2023)

Generalized Orthogonal Measures on the Space of Unital Completely Positive Maps
by: Bhattacharya, Angshuman, et al.
Published: (2022)

Barycentric decompositions in the space of weak expectations
by: Bhattacharya, Angshuman, et al.
Published: (2022)

Ergodic decomposition in the space of unital completely positive maps
by: Bhattacharya, Angshuman, et al.
Published: (2023)

vApps: Verifiable Applications at Internet Scale
by: Zhang, Isaac, et al.
Published: (2025)

The Delusional Hedge Algorithm as a Model of Human Learning from Diverse Opinions
by: Chuang, Yun-Shiuan, et al.
Published: (2024)

From Self-Evolving Synthetic Data to Verifiable-Reward RL: Post-Training Multi-turn Interactive Tool-Using Agents
by: Gao, Jiaxuan, et al.
Published: (2026)

Truncated Step-Level Sampling with Process Rewards for Retrieval-Augmented Reasoning
by: Samarinas, Chris, et al.
Published: (2026)

Reimagining Self-Adaptation in the Age of Large Language Models
by: Donakanti, Raghav, et al.
Published: (2024)

Extreme points of unital completely positive maps invariant under partial action
by: Kulkarni, Chaitanya J., et al.
Published: (2025)

Direct integral of locally Hilbert spaces
by: Kulkarni, Chaitanya J., et al.
Published: (2025)

Direct integral of locally Hilbert spaces over a locally measure space
by: Kulkarni, Chaitanya J., et al.
Published: (2025)

On the Haagerup property for partial crossed products
by: Hossain, Md Amir, et al.
Published: (2026)

Direct Integral and Decompoisitions of Locally Hilbert spaces
by: Kulkarni, Chaitanya J., et al.
Published: (2024)

Sequential Recommendation via Adaptive Robust Attention with Multi-dimensional Embeddings
by: Pang, Linsey, et al.
Published: (2024)

Logical Relations for Formally Verified Authenticated Data Structures
by: Gregersen, Simon Oddershede, et al.
Published: (2025)

Reward Hacking Mitigation using Verifiable Composite Rewards
by: Tarek, Mirza Farhan Bin, et al.
Published: (2025)

KnotResolver: Tracking self-intersecting filaments in microscopy using directed graphs
by: Khatri, Dhruv, et al.
Published: (2024)

Physical Principles of Size and Frequency Scaling of Active Cytoskeletal Spirals
by: Soni, Aman, et al.
Published: (2025)

Robust Optimization for Mitigating Reward Hacking with Correlated Proxies
by: Liu, Zixuan, et al.
Published: (2026)

Rethinking the Role of Proxy Rewards in Language Model Alignment
by: Kim, Sungdong, et al.
Published: (2024)

Translation as a Scalable Proxy for Multilingual Evaluation
by: Issaka, Sheriff, et al.
Published: (2026)

Call for a Pacific Centre for Disease Control!
by: George P. Drewett, et al.
Published: (2025)

Verifiable Process Rewards for Agentic Reasoning
by: Yuan, Huining, et al.
Published: (2026)

Temporal Context Awareness: A Defense Framework Against Multi-turn Manipulation Attacks on Large Language Models
by: Kulkarni, Prashant, et al.
Published: (2025)