Human Feedback and Eval Paper Explorer

Match reason: Keyword overlap 1/1 across title and protocol fields.

• Recently, LLM-based agents have become increasingly popular across many applications, including complex sequential decision-making problems.
• In ReDAct, an agent is equipped with two LLMs: a small, cheap model used by default, and a large, more reliable but expensive model.

Match reason: Keyword overlap 1/1 across title and protocol fields.

• Standard reinforcement learning (RL) for large language model (LLM) agents typically optimizes extrinsic rewards, prioritizing isolated task completion over continual adaptation.
• Inspired by human retrospective self-improvement, we introduce RetroAgent, an online RL framework that trains agents to master complex interactive environments not only by solving tasks, but by evolving under the joint guidance of extrinsic…

Match reason: Keyword overlap 1/1 across title and protocol fields.

• We evaluate on RewardPrediction, a new benchmark dataset spanning five diverse domains and comprising 2,454 unique action-observation trajectories with step-wise ground-truth rewards.
• Our method shows promising zero-shot results against both VLWM-critic and LLM-as-a-Judge reward models, achieving 60% and 8% lower EPIC distance, respectively.

Match reason: Keyword overlap 1/1 across title and protocol fields.

• Group-based reinforcement learning (RL), such as GRPO, has advanced the capabilities of large language models on long-horizon agentic tasks.
• To address the issue, in this paper, we propose Hierarchy-of-Groups Policy Optimization (HGPO) for long-horizon agentic tasks.

Match reason: Keyword overlap 1/1 across title and protocol fields.

• Large language models (LLMs) are increasingly deployed as multi-step decision-making agents, where effective reward design is essential for guiding learning.
• We introduce SELAUR: Self Evolving LLM Agent via Uncertainty-aware Rewards, a reinforcement learning framework that incorporates uncertainty directly into the reward design.

Match reason: Keyword overlap 1/1 across title and protocol fields.

• We propose GiG, a novel planning framework that structures embodied agents' memory using a Graph-in-Graph architecture.
• Furthermore, we introduce a novel bounded lookahead module that leverages symbolic transition logic to enhance the agents' planning capabilities through the grounded action projection.

Match reason: Keyword overlap 1/1 across title and protocol fields.

• Large language models (LLMs) exhibit strong capabilities as decision-making agents by interleaving reasoning and actions, as seen in ReAct-style frameworks.
• We propose Structured Agent Distillation, a framework that compresses large LLM-based agents into smaller student models while preserving both reasoning fidelity and action consistency.

Match reason: Keyword overlap 1/1 across title and protocol fields.

• Large Language Models (LLMs) based agents excel at diverse tasks, yet they suffer from brittle procedural memory that is manually engineered or entangled in static parameters.
• We propose Memp that distills past agent trajectories into both fine-grained, step-by-step instructions and higher-level, script-like abstractions, and explore the impact of different strategies for Build, Retrieval, and Update of…