multi-turn-agents

Tag

Cards List
#multi-turn-agents

@sheriyuo: TRACE assigns dense credit at tool boundaries by asking a frozen reference model whether each new observation raises th…

X AI KOLs Timeline · 2026-07-16 Cached

TRACE is a dense credit assignment method for multi-turn agentic reinforcement learning that uses a frozen reference model to compute per-action rewards from log-probability changes at tool boundaries, eliminating the need for a critic or process reward model. It significantly improves long-horizon tool-use performance on benchmarks like BrowseComp-Plus.

0 favorites 0 likes
#multi-turn-agents

Information Gain-based Rollout Policy Optimization: An Adaptive Tree-Structured Rollout Approach for Multi-Turn LLM Agents

arXiv cs.AI · 2026-07-08 Cached

Proposes IGRPO, a framework that adaptively allocates rollout budget based on informativeness of intermediate states for multi-turn LLM agents, unifying adaptive tree-structured exploration with policy learning. Experiments on seven search-augmented QA benchmarks show consistent improvements over baselines.

0 favorites 0 likes
#multi-turn-agents

GAGPO: Generalized Advantage Grouped Policy Optimization

arXiv cs.AI · 2026-06-15 Cached

GAGPO proposes a critic-free RL method that uses a non-parametric grouped value proxy for step-level credit assignment in multi-turn agentic tasks, outperforming strong baselines on ALFWorld and WebShop.

0 favorites 0 likes
#multi-turn-agents

SynAE: A Framework for Measuring the Quality of Synthetic Data for Tool-Calling Agent Evaluations

arXiv cs.CL · 2026-05-22 Cached

SynAE is a framework for evaluating the quality of synthetic data used in tool-calling agent evaluations, assessing validity, fidelity, and diversity across multiple axes. It addresses challenges of insufficient or sensitive real data by providing metrics to guide synthetic data generation.

0 favorites 0 likes
#multi-turn-agents

@maximelabonne: That's so cool! The same team at @Meituan_LongCat wrote Skill0, where they propose an RL recipe for skill internalizati…

X AI KOLs Following · 2026-05-17 Cached

The tweet highlights a paper by the Meituan team on Skill0, an RL recipe for skill internalization, and references a related paper on self-distilled agentic RL.

0 favorites 0 likes
#multi-turn-agents

Self-Distilled Agentic Reinforcement Learning

Hugging Face Daily Papers · 2026-05-14 Cached

SDAR enhances multi-turn agent training by integrating self-distillation with a sigmoid gate to selectively strengthen positive token-level guidance while mitigating negative teacher rejections, achieving significant improvements over GRPO across multiple benchmarks.

0 favorites 0 likes
← Back to home

Submit Feedback