The Flow has not summarised this story yet — read it at arXiv Computation and Language.
The paper introduces CTXAgent, a self‑controlled context management system for large language model agents that compacts conversation history when a token threshold is reached. It evaluates seven frontier models, comparing their ability to manage context with and without dedicated tools, and benchmarks performance across coding, scientific, and software engineering tasks. Results show that well‑managed models keep live context below 100k tokens, maintain high benchmark scores, and achieve significant cost reductions, with Claude Opus 5.5 outperforming its explicit configuration by 34% lower cost.
The paper introduces Humanize MLE Agents (HMA), a workflow that alternates two agents across sessions on a shared workspace, limiting each session to at most k experiments and resetting context between sessions. This approach, modeled as a context‑reset semi‑Markov decision process, outperforms single‑agent baselines, achieving a 78.2% any‑medal rate on 75 Kaggle MLE‑bench tasks—8.0 points higher than the best open‑source baseline and using only a quarter of its time budget. Across six heterogeneous agent pairs, HMA improves the any‑medal rate by an average of 6.4 points, and a supplementary kernel‑optimization case reaches 878 cycles, within 1.6% of the community leaderboard leader.
The paper investigates how test‑time computation can enhance language models and at what cost, introducing the SELF‑POT benchmark to evaluate this across competition mathematics, competitive programming, and agentic workflows. SELF‑POT separates candidate coverage from final accuracy, tracks correctness transitions under revision, and measures protocol completion alongside task success. Using a unified budget rule, the study compares direct inference, parallel sampling, and self‑revision across five low‑cost reasoning models, revealing that selection rules and failure handling significantly influence gains and cost savings.
arXiv:2605. 28556v2 Announce Type: replace Abstract: As agent capabilities advance, existing benchmarks, such as $\tau^2$-Bench, are becoming increasingly saturated.
arXiv:2607. 02255v1 Announce Type: new Abstract: Memory for a long-horizon LLM agent is a contract about what each future decision is allowed to see.
The paper introduces BenchAgent, a framework for evaluating multi‑agent large language model (LLM) workflows against a single‑agent baseline, BenchAgent Core. Using GPT‑4.1 across ten reasoning, coding, and tool‑use benchmarks, the study compares six multi‑agent configurations, finding that EvoAgent achieves the highest mean pooled accuracy (79.70%) while other agents lag by 1.71–8.76 percentage points. The analysis also highlights trade‑offs in token consumption and accuracy, offering guidance for selecting and optimizing LLM multi‑agent workflows.