6 papers
Bookkeeping, Composition, or Unreachable Gold? Reading MemoryAgentBench's Conflict-Resolution Scores Against a Frozen Last-Write Resolver
Egor Pakhomov, Erik Nijkamp
MemoryAgentBench's Conflict Resolution split is read as measuring "selective forgetting". We execute the benchmark's own rule - the newest statement about a fact wins - as a zero-l…
Does an Agent's History Tell You When Compaction Will Hurt? A Modest, Bounded Effect on the TRACE Paired-Replay Corpus
Egor Pakhomov, Erik Nijkamp
Many long-horizon agents compact their context on a global rule, usually a token budget, blind to what the agent was doing. We ask whether the agent's recent behaviour predicts whe…
An Architecture for Long-Horizon Agents: Levels, Ticks and Cascaded Intelligence
Erik Nijkamp, Anurag Koul, Egor Pakhomov +1
Language-model agents are increasingly asked to carry out work spanning days or weeks, such as an operations remediation or a research programme. Such a task outlives any context w…
Parsing the Stream: A Live Trace Model for Long-Horizon Agents and Their Observers
Egor Pakhomov, Erik Nijkamp
A long-horizon agent's trace outgrows both of its consumers: the human observer monitoring the run, and the agent itself, whose bounded context the trace must be folded back into.…
Convomem Benchmark: Why Your First 150 Conversations Don't Need RAG
Egor Pakhomov, Erik Nijkamp, Caiming Xiong
We introduce a comprehensive benchmark for conversational memory evaluation containing 75,336 question-answer pairs across diverse categories including user facts, assistant recall…
xGen-small Technical Report
Erik Nijkamp, Bo Pang, Egor Pakhomov +5
We introduce xGen-small, a family of 4B and 9B Transformer decoder models optimized for long-context applications. Our vertically integrated pipeline unites domain-balanced, freque…