Researchers introduced CoSkill, a multi-agent reinforcement learning framework that jointly trains a Reasoning Agent and a Meta-Skill Agent over a hierarchical skill library, achieving success rates o…
A new arXiv preprint (2609.0289v1) introduces HARNESSEVO, which decomposes an LLM agent's textual harness into four separately evolvable slots, and finds that on ALFWorld with a frozen 7B backbone, ne…
Researchers propose Potential-Guided Policy Optimization (PGPO), a new reinforcement learning method for multi-turn agentic tasks that estimates empirical state potentials from anchor-state-group retu…
Researchers propose VICT (Verifier-Instrumented Credit Tracing), a training-time interface that improves credit assignment in reinforcement learning for long-horizon LLM agents by tracing verifier-int…
Researchers propose MileGPO, a method for credit assignment in long-horizon agentic reinforcement learning that derives process-level credit from grouped on-policy rollouts via Milestone Discovery, Re…
Researchers propose PlanPO, a group planning-aware policy optimization method that improves multi-turn agentic large language models by distinguishing advantages among successful trajectories based on…
Researchers propose Stateful Knowledge Learning (SKL), a method that trains large language model agents to maintain explicit, state-anchored predictive knowledge instead of relying on trajectory-level…
Researchers propose CAST (Credit Assignment from Solver Teachers), a method that converts game solver state-value changes into turn-level signals to improve reinforcement learning for LLM agents in lo…
Researchers propose Progress-conditioned Group Policy Optimization (ProGPO), a method that uses first-visit observation coverage to assign higher advantages to trajectories visiting new states when al…
Researchers introduce Branching Policy Optimization (BPO), a reinforcement learning algorithm for LLM agents that exploits deterministic, snapshottable sandboxes to reduce variance and improve trainin…
Researchers have introduced normalized entropy and the STAPO framework to address trajectory neglect in reinforcement learning, where AI models lose track of goals during complex tasks. Tests on ALFWo…
Researchers introduced TRIAGE, a novel framework that refines credit assignment in agentic reinforcement learning by classifying actions based on their role, improving success rates and reducing ineff…
Researchers propose TurnOPD, a turn-level budgeting strategy for efficient on-policy distillation of long-horizon language agents. The method addresses inefficiencies in vanilla agent OPD by using ada…
Researchers introduced RSEA, a Recursive Self-Evolving Agent that improves LLM agents by rewriting natural-language artifacts without weight updates, using a held-out selection gate to prevent regress…
Researchers introduced Agentic Abstention, a framework for LLM agents to decide when to stop acting under uncertainty, and found that many agents fail to abstain or do so too late. Testing 13 LLM agen…
Researchers propose ATOD, a hybrid online distillation algorithm that combines on-policy distillation and reinforcement learning to train small language-model agents for multi-turn tasks. ATOD uses an…
Researchers introduced a prompt-based uncertainty decomposition method that separates action confidence from request uncertainty, enabling LLM agents to proactively seek clarification when task specif…