works on

From the 1 of 61 linked papers with an AI index.

activity
20242026
collaborators
Showing cs.CLShow all

37 papers · 1 filter

cs.CL2026

Knowing When to Quit: Diagnosing and Training LLMs to Abort Futile Reasoning

Xinyan Guan, Jiali Zeng, Chunlei Xin +5

Large language models generate computationally expensive yet semantically void reasoning on beyond-capability tasks, creating risks where plausible-sounding but incorrect derivatio…

cs.CL2026

PraMem: Practice-derived Experiential Memory for Long-horizon Behavior Prediction

Zhuoqun Li, Boxi Cao, Jiawei Chen +11

Long-horizon behavior prediction aims to infer a user's next action based on a lengthy historical sequence, playing a crucial role in artificial intelligence field. The rise of lar…

cs.CL2026

ReasoningLens: Hierarchical Visualization and Diagnostic Auditing for Large Reasoning Models

Jun Zhang, Jiasheng Zheng, Boxi Cao +5

The emergence of Large Reasoning Models has introduced exceptionally long Chain-of-Thought traces, creating a transparency burden where critical logic is often buried under massive…

cs.CL2026

Verifiable Environments Are LEGO Bricks: Recursive Composition for Reasoning Generalization

Hao Xiang, Qiaoyu Tang, Le Yu +8

Reinforcement Learning (RL) with verifiable environments has emerged as a powerful approach for enhancing the reasoning capabilities of Large Language Models (LLMs). While prior re…

cs.CL2026

Combinatorial Synthesis: Scaling Code RLVR via Atomic Decomposition and Recombination

Jiasheng Zheng, Boxi Cao, Boxi Yu +6

Reinforcement Learning with Verifiable Rewards (RLVR) has recently emerged as the cornerstone for shaping the remarkable coding abilities of Large Language Models (LLMs). However,…

cs.CL2026

Your Teacher Can't Help You Here: Combating Supervision Fidelity Decay in On-Policy Distillation

Yanjiang Liu, Jie Lou, Xinyan Guan +7

On-policy distillation transfers reasoning capabilities by training a student model on its own generated trajectories using token-level feedback from a teacher. However, we identif…