arXiv Machine Learning
Training Advisors for LLM Agents from Task Outcomes
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Computation and Language
1d ago
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...
arXiv Computation and Language
Sep 1
CAST: Critique-Aware Supervision for Training Reliable Long-Horizon Tool-Calling Agents
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.
arXiv AI
Oct 2
Your Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor's Internal States
The paper introduces POISE, a reinforcement learning algorithm that uses a model’s internal states as a value estimator to reduce variance in reinforcement learning with verifiable rewards (RLVR). By employing a lightweight probe that reads internal signals during the forward pass, POISE predicts baselines online and uses a cross‑rollout construction to keep gradients unbiased. Experiments on Qwen3‑4B and OLMo3‑7B‑Instruct‑DPO across six domains show POISE outperforms existing RLVR baselines, offering more stable training and a value model that generalizes across tasks and scales with the policy.
arXiv AI
Jun 2
Critic-R: Improving Agentic Search using Instruction-tuned Retrievers with Natural Language Introspective Feedback
arXiv:2606. 00590v1 Announce Type: cross Abstract: Agentic search systems iteratively interact with retrieval models to answer complex queries.
arXiv Computation and Language
Sep 15
Learning to Coach for Experiential Learning
arXiv:2609.15851v1 Announce Type: new Abstract: Language models can learn from experience, but raw solution trajectories are often too long and noisy to provide effective guidance. In this work, we p...
arXiv AI
Jun 4
Efficiently Aligning Language Models with Online Natural Language Feedback
arXiv:2605. 04356v2 Announce Type: replace-cross Abstract: Reinforcement learning with verifiable rewards has been used to elicit impressive performance from language models in many domains.