Tobias Lindenbauer

Tobias Lindenbauer

Researcher working on post-training code models and agents: SFT, distillation, and RL.

Invited Talks

Code World Models

MunichNLP × JetBrains · Invited talk · October 13, 2026 · Approximately 100 attendees

Introduced the emerging Code World Models research direction: how LLMs model program behavior, reason about test outcomes without execution, and identify opportunities to improve runtime or memory performance. Shared early findings from an ongoing project at JetBrains Research.

Event details

It’s the Context, Stupid! Context Management Strategies for Long-Horizon Agents

Munich DataGeeks · Invited talk · September 24, 2026 · Approximately 200 attendees

Presented my context-management research for long-horizon agents, from summarization and observation masking to an outlook on learned meta-actions optimized through RL. Closed with a demo of automated trajectory analysis for finding failure patterns across thousands of agent runs.

Event details

Proactive Context Management for Long-Horizon Code Agents

TU Munich, Advanced NLP Masters’ course · Guest lecture · June 6, 2026

Gave a guest lecture on one of my passion topics: proactive context management for long-horizon code agents. As code agents operate over longer horizons, context management has evolved from an afterthought to a first-class post-training topic.

  • Until recently: the harness manages context by prompting the model to summarize once it crosses a heuristic threshold (e.g., 80% of the context window).
  • Now: learned meta-actions, where the model itself recognizes when a tool output is stale, or a subtask’s branch is dead, and folds it away on its own initiative.

We closed the session with a hands-on demo of using subagents to scale qualitative trajectory analysis, automating the painful part of debugging why an agent went sideways over a 100+ step run.

Thanks to Alexander F. and Miriam Anschütz for making this possible.

Context Engineering for Agentic Hybrid Applications

Berlin DataTalksClub · Invited talk with Ivan Potapov · March 10, 2026

Discussed the cost and reliability implications of context growth in long-horizon production agents, arguing for efficiency-focused, proactive context management. Built on findings from The Complexity Trap that simple observation masking matches LLM summarization at a fraction of the cost.

Watch on YouTube · Approximately 1,000 views as of November 2026.