Tech Meridian ← ENTITY INDEX
PROMY MERIDIAN RU

TOPIC · ENTITY #15091

mini-SWE-agent

Related event timeline, sources and context from the news index.

EVENT TIMELINE

4

RESEARCH · 1 SOURCE · The Decoder

Study finds agent 'harnesses' drive token costs but rarely improve coding performance

Researchers at Shandong University (Liu and Han) ran five models through three shipped coding-agent harnesses (Claude Code, OpenCode, mini-SWE-agent) on SWE-bench Verified and a larger 447-task pool, and found that swapping harnesses changes results little beyond run-to-run noise while token costs can triple because of large system prompts and repeated context. OpenCode consistently trailed the others on the larger pool (partly due to output limits), and many reported leaderboard gaps fall below statistical detectability given sample sizes and noise.

7.0

RESEARCH · 1 SOURCE · arXiv cs.AI

ReuF2F: Lean 4 benchmark of 244 REU open math problems for coding agents

ReuF2F is a new Lean 4 benchmark (arXiv:2610.27046v1) of 244 formalized open problems sourced from Research Experiences for Undergraduates (REU). The benchmark packages each problem and its negation in a Lean project inside a Docker container, provides a unified evaluation harness (Leanimum-agent built on mini-SWE-agent), and reports that the best model in their evaluation solves only ~40% of the problems.

7.0

RESEARCH · 1 SOURCE · Cohere

Study: delegating exploration and planning lets agent teams reach near-frontier coding performance at far lower cost

A controlled study of coding-agent teams finds that well-organized multi-agent systems can outperform single agents on ProgramBench by up to ~10 percentage points but typically cost 3–7× more. Crucially, delegating only exploration and planning can match the performance of delegating planning, implementation, and verification together at roughly half the cost — e.g., a Sol lead with 16 inexpensive Luna planning workers reached 61.8% reward vs 63.2% for an all‑Sol team while cutting API cost from $510 to $155; the paper also situates these results amid recent large multi-agent coding projects (Claude, Cursor, Bun).

7.0

RESEARCH · 1 SOURCE · Microsoft Research

Microsoft Research Asia open-sources Agent Lightning v1.0, a lightweight harnessed agentic RL framework

Microsoft Research Asia released Agent Lightning v1.0, a roughly 3,500-line open-source implementation of a Harnessed Agentic RL training paradigm that trains on the same agent harness used in deployment via an LLM proxy. The framework runs agents as native Kubernetes jobs, avoids reimplementing agent harnesses, and includes an end-to-end coding-agent example that raised Qwen3.5-9B’s Pass@1 on SWE-bench Verified from 41.8% to 56.4% using about 6,000 training samples.

7.0