Retrieved PHREEQC output lowers GPT agent accuracy on fixed simulations
GPT-5.1 and GPT-5.2 lose 11.3 and 7.9 points via a section index, while two Claude models show no detectable drop.
Stories per day · 30 days
3 RSS
Relatedllm-agents3phreeqc2tool-use2claude1evidence-substitution1gpt1long-horizon1osworld1token-efficiency1
10 stories, newest first · one card per story
Stories tagged #context-management
Retrieved PHREEQC reports cost some GPT agents accuracy
GPT-5.1 and GPT-5.2 lost 11.3 and 7.9 points reading reports via a section index; Claude models did not.
CarryOn organizes long-horizon agent context around task objects
Authors report gains of 5.8% and 7.0% with token cuts of 51.9% and 22.9% on two benchmarks.
Clearing chat history helps AI agents find better solutions
Microsoft Research shows long-running AI agents plateau in "idea basins"; a Fork-and-Flush context-reset method boosts scores 66% on equal compute.
8
RunningTab: Direct Workspace Interaction with Environment-Side Tabs
RunningTab adds an environment-side task tab so LLM agents track unread files and unmet requirements.
Context Language Models
Context Language Models edit their own context file, beating external managers on agent benchmarks while cutting FLOPs.
An Empirical Study of Harness Design for Coding Agents
Empirical study of coding agent harnesses across 176 settings shows context management prevents overflow failures and bash-only interfaces cut costs for capable models.
An Empirical Study of Harness Design for Coding Agents
Empirical study of 176 matched coding-agent harness configurations shows context management cuts overflow failures while planning and action-space choices trade accuracy against cost.
The Missing Boundary: How Autonomous Agents Lose Control
Tencent research finds agents lose control in 55-62% of trajectories when degraded control boundaries coincide with executable unsafe opportunities across five models and 16 domains.
The /wayfinder Skill: Navigating the “Fog of War” of Planning
Matt Pocock released the /wayfinder skill, an orchestrator layer that manages planning sessions, maps, and tickets for AFK coding agents.
4