works on

From the 4 of 16 linked papers with an AI index.

activity
20242026
collaborators

16 papers

cs.AI2026

PCSD: Persistent Consistency for Self-Distillation in Agentic Reinforcement Learning

Chunji Lv, Yangguang Wei, Junlin Liu +6

Large language model agents have shown strong potential in complex interactive tasks, yet their reinforcement learning (RL) is often hindered by sparse rewards, as a long multi-tur…

cs.LG2026

ClawTrack: Towards Trace-Level Evaluation and Improvement of Real-World Autonomous Agents

Xingjian Wu, Xuhang Zhu, Xingchen Liu +6

The paper introduces ClawTrack, a benchmark that evaluates both the final outcomes and the step-by-step reasoning processes of LLM-based autonomous agents across multiple dimension…

cs.LG2026

Contrastive Reinforced Policy Optimization via Privileged Self-Distillation

Xingjian Wu, Junlin Liu, Xingchen Liu +6

The paper introduces Contrastive Reinforced Policy Optimization (CRPO), a method that frames on‑policy self‑distillation for large language models as a contrastive learning problem…

cs.AI2026

DecoEvo: Score-Decoupled Co-Evolution of Solver and Rubric-Generator Skills in Text Space

Jiangwang Chen, Zixin Song, Junlin Liu +10

The paper introduces DecoEvo, a method that co-evolves a solver and a rubric-generator for large language models in text space using decoupled objectives, allowing the solver to im…

cs.AI2026

From Proprietary to Open-Source: Bridging the Distribution Gap via Multi-Agent Protocol Distillation in Agentic Search

Junlin Liu, Jiangwang Chen, Zixin Song +7

Agentic search enables large language models to solve knowledge-intensive tasks by interleaving multi-step reasoning with retrieval, yet optimizing this with outcome-based reinforc…

cs.CL2026

Beyond Relevance-Centric Retrieval: Rubric-Oriented Document Set Selection and Ranking

Kailin Jiang, Lei Liu, Jian Xi +8

As large language models and AI agents become the primary consumers of search results, document set quality determines the upper bound of downstream generation. Yet existing evalua…