arXiv:2610.03634v1 Announce Type: new Abstract: Terminal-using agents benefit from reinforcement learning (RL) in coding, debugging, and other multi-step terminal tasks. In these tasks, later command...
The paper introduces TASPO, a method that transforms privileged information (PI) into outcome‑grounded action credit for language‑model agents. TASPO constructs decision‑applicable PI from verified successful experience, aggregates PI‑induced likelihood shifts at the executable‑action level, and converts relative action support into positive, bounded, mean‑preserving weights on the original trajectory advantage. Experiments on three agentic benchmarks show TASPO improves over GRPO by 10.6% and generalizes better to unseen tasks, while reducing supervision mismatch and stabilizing policy optimization.
arXiv:2608. 05102v1 Announce Type: new Abstract: Long-horizon search agents must make multiple sequential actions (steps) to search, retrieve, verify, and integrate evidence to reach a final answer.
arXiv:2609.36178v1 Announce Type: cross Abstract: Group Relative Policy Optimization (GRPO) has become a promising approach for training large language model agents. However, its uniform assignment o...
HarnessEvolve is a self‑evolving framework that improves agent harnesses—prompts, skills, tools, and execution logic—by learning from reference trajectories. It separates execution, evaluation, optimization, and gating into independent modules, addressing credit assignment failure, shortcut learning, and catastrophic forgetting. The approach uses reference trajectories to extract error signals, applies quality and performance gates to candidate updates, and validates updates on held‑out data, consistently outperforming state‑of‑the‑art baselines across diverse benchmarks.
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.
arXiv:2610.30933v1 Announce Type: new Abstract: With external tools, large language models (LLMs) can tackle complex tasks through sustained environmental interaction. LLM-based agents are therefore...
Self-Credit is an agentic reinforcement learning method that transforms sparse outcome rewards into dense supervision signals through self-generated credit assignment and intra-group rescaling. The approach involves the policy model summarizing key evidence with citations, refining these citations by comparing actions across successful and failed rollouts, and reweighting advantages based on the rescaled credit. Experiments on BrowseComp-Plus, GAIA, and xBench-DeepSearch show significant performance gains over baseline models and other agentic RL methods.
The paper introduces Influence-Aware Policy Optimization (IAPO), a method that models multi‑turn agent rollouts as typed influence‑dependency graphs to better assign credit to actions based on how information and errors flow through user and tool interactions. IAPO transforms the structure of support and failure usage into routing weights that redistribute trajectory‑level advantage, enabling more effective learning from sparse final rewards. Experiments with Qwen3‑4B and Qwen3‑8B on three service‑agent benchmarks show that IAPO outperforms existing multi‑turn reinforcement learning baselines without harming function‑calling performance.
Long-horizon large language model (LLM) agents are typically optimized with sparse terminal outcomes, making fine-grained credit assignment across multi-step interactions difficult. Existing approache...
LLM agents are commonly trained with RLVR, but the sparse nature of typical RLVR rewards makes credit assignment challenging, especially for long-horizon tasks. We propose Self-Credit, an end-to-end a...
Large Language Model (LLM) agents increasingly solve long-horizon tasks through multi-turn interactions with users and external tools. In these settings, relevant task information often unfolds over t...