collaborators

5 papers

cs.AI2026

ArbiGraph: Arbitrarily Scalable Verifiable Task Graphs for Evaluating Context Management

Pavel Golikov, Evgenii Opryshko, Gennady Pekhimenko +1

We introduce ARBIGRAPH, a benchmark generator for evaluating whether tool-assisted language agents can retain, update, compose, and discard task-relevant context across extended re…

cs.LG2026

Modification-Considering Value Learning for Reward Hacking Mitigation in RL

Evgenii Opryshko, Umangi Jain, Igor Gilitschenski

Reinforcement learning agents can exploit misspecified reward signals to achieve high apparent returns while failing on the intended objective, a failure mode known as reward hacki…

cs.RO2026

Update-Free On-Policy Steering via Verifiers

Maria Attarian, Ian Vyse, Claas Voelcker +7

In recent years, Behavior Cloning (BC) has become one of the most prevalent methods for learning manipulation from human demonstrations. Despite their successes, BC policies are of…

cs.LG2026

Test-Time Graph Search for Goal-Conditioned Reinforcement Learning

Evgenii Opryshko, Junwei Quan, Claas Voelcker +2

Offline goal-conditioned reinforcement learning (GCRL) often struggles with long-horizon tasks, where errors in value estimation accumulate and produce unreliable policies. It is t…

cs.LG2026

Robust Reasoning Benchmark

Pavel Golikov, Evgenii Opryshko, Gennady Pekhimenko +1

While Large Language Models (LLMs) achieve high performance on standard mathematical benchmarks, their problem-solving abilities depend on the context and textual formatting. We in…