Tech Meridian ← ENTITY INDEX
PROMY MERIDIAN RU

COMPANY · ENTITY #13378

WebShop

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

EVENT TIMELINE

4

RESEARCH · 1 SOURCE · arXiv cs.AI

Study: More reasoning raises LLM shopping agents' confidence but not correctness

The arXiv paper (arXiv:2611.22033v1) benchmarks ten leading LLMs on three product-choice datasets (WebShop, Amazon SQID, Wayfair WANDS) and finds that asking models to 'think harder' does not improve purchase decision quality, while it significantly increases reported confidence. The authors also show most models are poorly calibrated across effort levels and that errors are strongly shared—many models tend to make the same wrong choices.

7.0

RESEARCH · 1 SOURCE · arXiv cs.AI

EvoDisco: evolutionary strategy discovery to evolve agent memory

EvoDisco (arXiv:2611.22102v1) frames agent memory evolution as an evolutionary strategy discovery problem: a learned policy selects and instantiates one of four semantic operators—Abstract, Refine, Bridge, Reframe—rather than applying a fixed memory-update schedule. Using a bi-level fitness (inner retrieval-quality regularized by complexity; outer strategic efficacy over past decisions), EvoDisco outperforms strong memory baselines MemP and MemRL on ALFWorld, WebShop, and LifelongAgentBench, with the largest gains on ALFWorld (+8.8 online / +12.9 frozen-transfer vs MemP; +16.4 / +17.9 vs MemRL).

6.0

RESEARCH · 1 SOURCE · arXiv cs.AI

M-Plan: closed-loop multi-agent framework integrating long- and short-term memory for LLM agents

M-Plan is a closed-loop multi-agent system (MAS) framework that combines long-term and short-term memory via global-local and past-current task-specific guidance. The paper (arXiv:2610.27032v1) describes guidance generation during execution, local hints when agents are confused, post-task memory optimization for future retrieval, and reports improved accuracy and efficiency on multi-turn benchmarks including ALFWorld, WebShop, and PDDL compared to several baselines.

6.0

RESEARCH · 1 SOURCE · arXiv cs.AI

Tropical Reinforcement Learning (TROPIC) swaps sum for max to enable compositional solutions

The arXiv preprint proposes Tropical Reinforcement Learning, which replaces the usual sum-over-trajectories objective with a max (the tropical semiring) so state values reflect the log-probability of the most likely verified solution and yield explicit replayable paths. The authors present TROPIC, a training algorithm for deterministic, resettable environments with verifiable outcomes, and report up to 16 percentage points improvement over strong on-policy baselines on four tasks (Sokoban, Countdown, FrozenLake, WebShop).

7.0