arXiv Computation and Language September 1, 2026 By Amir Saeidi, Zehua Zhang, Rishitosh Singh, Naman Ahuja, Vivek Gupta, Ali Payani, Gaowen Liu, Jayanth Srinivasa, Chitta Baral

CAST: Critique-Aware Supervision for Training Reliable Long-Horizon Tool-Calling Agents

Read the original on arXiv Computation and Language →

CAST is a critique‑aware training framework that transforms sparse task outcomes into action‑level supervision for both critique learning and policy optimization. By analyzing agent trajectories, CAST synthesizes structured rationales that explain action validity under partial observability, enabling the creation of richer training data. Fine‑tuned Qwen3‑family models trained with CAST show significant reliability gains, outperforming GPT‑OSS‑120B by over 10% on Retail tasks and improving Telehealth performance by 9% in an out‑of‑domain setting.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

arXiv AI

Oct 7

Selective Critique for Cost-Aware LLM Agents in Long-Horizon Decision Making

arXiv:2610.07335v1 Announce Type: cross Abstract: Improving the reliability of large language model (LLM) agents in long-horizon decision-making remains a key challenge. When deployed as autonomous a...

By Heewon Park, Somin Im, Minhae Kwon

llms agents benchmarks

arXiv Computation and Language

Oct 15

Beyond Corrected Actions: Training LLM Agents on Textual Critiques

arXiv:2610.19367v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for multi-turn agentic tasks that require interactions with users and environments over extended seq...

By Thomas Zeng, Zelei Cheng, Mingyang Zhou, Sambit Sahu, William Campbell, Genta Indra Winata

llms agents reinforcement-learning fine-tuning efficiency

Hugging Face Trending Papers

Oct 14

Beyond Corrected Actions: Training LLM Agents on Textual Critiques

Large language models (LLMs) are increasingly used for multi-turn agentic tasks that require interactions with users and environments over extended sequences of actions. A common approach to improving...

llms agents reinforcement-learning fine-tuning efficiency

arXiv AI

Oct 21

GRADUS: Discovering and Recovering Agent Lessons from the Environment's Latent Syllabus

GRADUS introduces a method for training large language model agents in policy-constrained tool environments by decoupling task design from solutions. It treats a fixed environment as a latent syllabus, extracting guarded behavioral operators and composing them into progressively harder tasks while using corpus-level feedback to target missing outcome combinations. The approach jointly calibrates tasks and solutions against the environment, turning verification into a recovery signal that preserves difficult examples, leading to significant performance gains on benchmarks such as $ au^2$-Bench and CAR-Bench.

By Qing Ping, Wei Yang, Panpan Xu, Johannes Kirmayr, Lukas Stappen, Junjie Tang, Jun Huan

llms agents

arXiv Machine Learning

Oct 8

Training Advisors for LLM Agents from Task Outcomes

arXiv:2610.09858v1 Announce Type: cross Abstract: Large language model agents tackle multi-step tasks by interleaving reasoning and tool calls with observations from the environment. Prior work has s...

By Sergei Polezhaev, Barys Liskavets, Ori Press, Alexander Golubev

llms agents nlp reinforcement-learning benchmarks

arXiv AI

Jun 30

SCRIBE: Structured Mid-Level Supervision for Tool-Using Language Models

arXiv:2601. 03555v3 Announce Type: replace Abstract: Training reliable tool-augmented agents remains a significant challenge, largely due to the difficulty of credit assignment in multi-step reasoning.

By Yuxuan Jiang, Francis Ferraro

llms agents reinforcement-learning benchmarks

One email a morning, machine-written

Related stories

Selective Critique for Cost-Aware LLM Agents in Long-Horizon Decision Making

Beyond Corrected Actions: Training LLM Agents on Textual Critiques

Beyond Corrected Actions: Training LLM Agents on Textual Critiques

GRADUS: Discovering and Recovering Agent Lessons from the Environment's Latent Syllabus

Training Advisors for LLM Agents from Task Outcomes

SCRIBE: Structured Mid-Level Supervision for Tool-Using Language Models