arXiv Computation and Language
Beyond Corrected Actions: Training LLM Agents on Textual Critiques
Read the original on arXiv Computation and Language →The Flow has not summarised this story yet — read it at arXiv Computation and Language.
Related stories
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 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...
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...
arXiv AI
Jul 24
From Agent Failures to Text Policies: What Works and What Breaks
arXiv:2607. 20668v1 Announce Type: cross Abstract: TextGrad improves language-model systems by revising text from feedback.
arXiv AI
Oct 1
Rep2Skill: Representation-Guided Skill Self-Evolution for LLM Agents
Rep2Skill introduces a representation-guided framework that enables large language model agents to self-evolve their textual skills by analyzing internal representation trajectories from agent rollouts. The method identifies execution turns that deviate from successful dynamics and uses these signals, together with execution contexts, as actionable feedback for targeted skill revision. Experiments with two open-source LLMs across two agent environments demonstrate that Rep2Skill consistently outperforms purely text-based approaches, showing that incorporating internal representations can enhance agent self-improvement.
Hugging Face Trending Papers
Sep 28
Shockingly Simple Self-retrospection Improves Agentic Models Without RL
The paper explores Retrospection-Only Fine-Tuning (ROFT), a method where a language-model agent improves its behavior by generating and training on explanations of its own experiences, without external teachers or reward signals. In software‑engineering tasks with Qwen3.5‑4B, ROFT achieves comparable or better solve rates than GRPO while requiring fewer updates and training time, and can learn from failures alone. Behavioral analysis shows ROFT indirectly assigns credit to actions and can produce shorter, more direct solutions when prompted to focus on direct solutions.