arXiv:2606. 32034v1 Announce Type: cross Abstract: LLM agents increasingly act over long horizons, where a single trajectory can contain hundreds or thousands of actions.
arXiv:2609.05837v1 Announce Type: new Abstract: LLM-based agents are increasingly deployed in real-world applications through tool-use APIs, yet training them for specific environments remains fundam...
FLARE introduces a dense supervision paradigm for long‑horizon coding agents, leveraging a Generative Reward Model (GRM) trained via the RADAR diagnostic framework. The GRM provides real‑time, step‑level risk feedback, enabling FLARE to act as an active scaffold that intercepts high‑risk steps during inference and supplies structured signals for post‑training fine‑tuning and reinforcement learning. Experiments show FLARE outperforms existing methods, achieving a 5× reduction in token consumption and significant performance gains in both supervised fine‑tuning and RL settings.
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:2606. 26027v1 Announce Type: cross Abstract: Tool use enables large language models (LLMs) to perform complex tasks, and recent agentic reinforcement learning (RL) methods show promise for enhancing model capabilities.
arXiv:2608.23493v1 Announce Type: new Abstract: Self-reflection is a powerful mechanism for credit assignment in human learning, converting sparse outcome feedback into actionable guidance. However,...
The paper introduces ActObs, a supervised fine‑tuning method that, unlike standard approaches, also predicts environment observations in agent trajectories. While both ActObs and action‑only training perform similarly after initial fine‑tuning, ActObs diverges during subsequent reinforcement learning, yielding higher pass@k scores on several benchmarks and better cross‑domain task performance. The authors attribute this advantage to ActObs’s joint supervision, which preserves observation gradients and prevents the policy from over‑specializing on actions alone.
arXiv:2609.38334v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed as agents for multi-step decision-making, yet transfer poorly to unseen environments. World-mode...
SWE-Prime introduces a two-stage supervised fine-tuning data selection process for large language models tackling software issues. The first stage filters entire trajectories by quality and representativeness, while the second stage selects meaningful semantic segments based on contribution, learnability, and risk. Experiments on SWE-Bench Pro and Verified demonstrate that training on just 10% of trajectories chosen by SWE-Prime surpasses full-dataset training, achieving up to 12.2% and 24.2% performance gains.
arXiv:2609.36641v1 Announce Type: cross Abstract: Process reward models (PRMs) have become a key component for LLMs, as their step-level feedback supports both post-training and test-time reasoning....
arXiv:2609.18417v1 Announce Type: new Abstract: Multi-turn agent trajectories often contain redundant rounds (failed tool calls, parallel sub-queries, verification-only steps) that inflate both train...
arXiv:2607. 27973v1 Announce Type: new Abstract: Recently, Reinforcement Learning (RL) has emerged as a crucial paradigm for the post-training of Large Language Model (LLM) agents.
arXiv:2608. 03632v1 Announce Type: new Abstract: On-Policy distillation (OPD) transfers teacher capabilities by supervising student-sampled trajectories with dense token-level teacher signals.