arxiv arXiv cs.CL · 78d ago · research

DeepRubric: Efficient RL for Deep Research Agents

from English

DeepRubric introduces a data construction framework that builds query-rubric pairs by first defining verifiable evaluation targets through an evidence tree. It generates 9K supervision examples and trains a 8B model with GRPO, achieving performance comparable to state-of-the-art models using 13x fewer RL GPU-hours.

Importance 3/3 Beats a top-lab benchmark New feature vs. leaders New harness with differentiators arXiv cs.CL OpenAI Google DeepMind Mistral AI AI agents Reasoning models Training methods

Read original

arxiv arXiv cs.AI · 74d ago · 4 views

LedgerAgent: Structured State for Policy-Adherent Tool-Calling Agents

LedgerAgent introduces a structured ledger to maintain task states separately in tool-calling agents. It renders states into prompts and enforces policy constraints before tool execution, reducing policy violations and improving performance across customer-service domains.

arxiv arXiv cs.LG · 74d ago · 2 views

Marginal Advantage Accumulation for Memory-Driven Agent Self-Evolution

This paper introduces Marginal Advantage Accumulation (MAA), a post-processing architecture that addresses cross-batch inconsistency in memory-driven agent self-evolution. MAA formalizes alignment and comparability as structural conditions, uses differential signals and exponential moving average to accumulate signed evidence per operation, and ensures traceability via semantic identity merging. It outperforms batch-level baselines in 14 out of 16 settings and reduces token consumption by about 75%.

arxiv arXiv cs.CL · 75d ago · 4 views

LedgerAgent: Structured State for Policy-Adherent Tool-Calling Agents

LedgerAgent introduces a structured ledger to maintain task states separately in tool-calling agents. It renders these states into prompts and enforces policy constraints before tool execution, reducing policy violations and improving performance across customer-service domains.

arxiv arXiv cs.AI · 75d ago · 4 views

Dual-Agent Framework for Cross-Model Verified Translation

A dual-agent framework converts natural-language experiment protocols into executable commands for robotic lab platforms. It uses a Parser Agent and a rule-based mapping engine to translate protocols, with a heterogeneous LLM Validation Agent ensuring accuracy and triggering self-correction. The framework successfully enables end-to-end autonomous execution of microplate-based experiments like the Bradford assay.

arxiv arXiv cs.LG · 75d ago · 5 views

LLM-based Hierarchical Control in Multi-Agent Games

A hierarchical system using a pretrained LLM to select RL skill policies outperforms flat RL in a 2v2 King of the Hill environment. It matches hand-crafted behavior tree performance in win rate and is perceived as more human-like by 60% of users, highlighting effective coordination and adaptability without manual rule design.