Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
Learning What Not to Forget: Long-Horizon Agent Memory from a Few Kilobytes of Learning
Nusrat Jahan Lia, Aritra Mazumder
Long-running language-model systems accumulate interaction history that outgrows the context window, so they must continually evict. When an eviction policy drops a task-critical d…
cs.CL2026
AgentCollabBench: Diagnosing When Good Agents Make Bad Collaborators
Aritra Mazumder, Shubhashis Roy Dipta, Nusrat Jahan Lia +10
Multi-agent systems achieve state-of-the-art outcomes through peer collaboration. However, when an agent in the pipeline silently drops a constraint, the system's final output may…