Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
ReFold: Training-Free Reversible Inter-Turn Context Folding for Long-Horizon Agents
Yupeng Su, Jiayi Tian, Zheng Zhang +1
Long-horizon LLM agents act on an append-only interaction history that is re-sent to the model at every step, so the context and its cost grow with steps until the sessions exceed…
cs.CL2026
One Token Away from Collapse: The Fragility of Instruction-Tuned Helpfulness
Erfan Baghaei Potraghloo, Seyedarmin Azizi, Souvik Kundu +1
Instruction-tuned large language models produce helpful, structured responses, but how robust is this helpfulness under trivial constraints? We show that simple lexical constraints…