8 papers
Verifier-Harness Co-Evolution for Training-Free Self-Improvement on Open-Ended Tasks
Tianyi Xu, Yaolun Zhang, Yiran Wu +6
Training-free self-improvement lets an agent use feedback to revise the response it is about to return and to update the harness state that shapes how it handles later tasks. On op…
EvalResearchBench: Can AI Agents Build Their Own Feedback for Recursive Self-Improvement?
Yaolun Zhang, Tianyi Xu, Yujie Zhao +3
Recursive self-improvement (RSI) relies on evaluation feedback to assess progress and guide further research, yet repeatedly running complex benchmarks is costly and slows iteratio…
LatentSkill: From In-Context Textual Skills to In-Weight Latent Skills for LLM Agents
Aofan Yu, Chenyu Zhou, Tianyi Xu +8
Agent systems increasingly use textual skills to encode reusable task procedures, but injecting these skills into the prompt at every step incurs substantial context overhead and e…
EVOCHAMBER: Test-Time Co-evolution of Multi-Agent System at Individual, Team, and Population Scales
Yaolun Zhang, Tianyi Xu, Shengyu Dai +3
We argue that multi-agent test-time evolution is not single-agent evolution replicated N times. A single-agent learner can only evolve its own context and memory. A multi-agent sys…
From Soliloquy to Agora: Memory-Enhanced LLM Agents with Decentralized Debate for Optimization Modeling
Jianghao Lin, Zi Ling, Chenyu Zhou +4
Optimization modeling underpins real-world decision-making in logistics, manufacturing, energy, and public services, but reliably solving such problems from natural-language requir…
Logos: An evolvable reasoning engine for rational molecular design
Haibin Wen, Zhe Zhao, Fanfu Wang +4
The discovery and design of functional molecules remain central challenges across chemistry,biology, and materials science. While recent advances in machine learning have accelerat…
MGSM-Pro: A Simple Strategy for Robust Multilingual Mathematical Reasoning Evaluation
Tianyi Xu, Kosei Uemura, Alfred Malengo Kondoro +6
Large language models have made substantial progress in mathematical reasoning. However, benchmark development for multilingual evaluation has lagged behind English in both difficu…
AfriqueLLM: How Data Mixing and Model Architecture Impact Continued Pre-training for African Languages
Hao Yu, Tianyi Xu, Michael A. Hedderich +3
Large language models (LLMs) are increasingly multilingual, yet open models continue to underperform relative to proprietary systems, with the gap most pronounced for African langu…